[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718G1C24R4HF734H3JC6F9Z":3,"skill-same:01M718G1C24R4HF734H3JC6F9Z":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M718G1C24R4HF734H3JC6F9Z","infringement-triage",null,"Infringement triage across trademark, copyright, patent, and trade secret — a flag list with the factors cutting each way, not a finding. Use when assessing whether someone is infringing your IP or whether you might be infringing theirs, when a knockoff or copycat surfaces, or when deciding whether a matter is worth pursuing and how.","anthropics\u002Fclaude-for-legal","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7189QY7HXHMC9BW4MFHPZ6H",10006,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fip-legal\u002Fskills\u002Finfringement-triage\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"triage","infringement triage","patent","trade","with","facts","use","just","trademark","copyright","describe","list","surfaces","how","across","ask","you","when","ip","which","2026-11-10 10:12:30",false,"---\nname: infringement-triage\ndescription: >\n  Infringement triage across trademark, copyright, patent, and trade secret —\n  a flag list with the factors cutting each way, not a finding. Use when\n  assessing whether someone is infringing your IP or whether you might be\n  infringing theirs, when a knockoff or copycat surfaces, or when deciding\n  whether a matter is worth pursuing and how.\nargument-hint: \"[describe the facts and which right — or just the facts and I'll ask which right]\"\n---\n\n# \u002Finfringement-triage\n\n**This is a triage, not a finding of infringement or non-infringement.**\nInfringement analysis is fact-intensive and legally complex. Acting on a\ntriage — sending a cease-and-desist, refusing to stop, filing suit, or\ndeciding not to — without attorney review is how companies end up on the\nwrong side of fee awards, Rule 11 sanctions, declaratory-judgment actions,\nand (for patents) treble damages.\n\n## Instructions\n\n1. Read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. If it\n   contains `[PLACEHOLDER]`, stop and direct to `\u002Fip-legal:cold-start-interview`.\n2. Follow the workflow below.\n3. Ask which right is at issue — trademark \u002F copyright \u002F patent \u002F trade secret\n   \u002F mixed. If mixed, run each separately; do not blend.\n4. Run common intake (party posture — senior or accused, jurisdiction, timing,\n   exhibits).\n5. Walk the mode-specific factors:\n   - **Trademark** — circuit's confusion test + dilution (if famous) +\n     false advertising (if a comparative claim).\n   - **Copyright** — ownership + registration + access + substantial\n     similarity + fair use + DMCA safe harbor (if applicable).\n   - **Patent** — claim-chart first pass (route to `fto-triage` output\n     structure); literal + DOE; indirect + divided; invalidity defenses to\n     consider.\n   - **Trade secret** — secrecy + reasonable measures + misappropriation;\n     preemption + reverse-engineering flags.\n6. Produce a flag list with direction — what cuts toward the senior party,\n   what cuts toward the accused, what's mixed. Never conclude.\n7. Write the triage memo to the matter folder or practice outputs folder. Apply\n   the work-product header per role.\n8. End with recommended next steps, the non-lawyer gate if the role is\n   non-lawyer, and — if the practice posture supports assertion — an offer to\n   draft the C&D via `\u002Fip-legal:cease-desist` or the takedown via\n   `\u002Fip-legal:takedown`. Do not draft automatically.\n\nThis skill never concludes. If uncertain, flag — the attorney decides.\n\n## Examples\n\n```\n\u002Fip-legal:infringement-triage \"competitor launched a tool called APEXSEED in class 9 — we have APEXLEAF registered in class 9; likely confusion?\"\n```\n\n```\n\u002Fip-legal:infringement-triage \"former engineer took notes on our model architecture to a competitor — possible trade secret?\"\n```\n\n```\n\u002Fip-legal:infringement-triage\n```\n\n(And the skill will ask which right and for the facts.)\n\n---\n\n## THIS IS A TRIAGE, NOT A FINDING\n\n**The loudest guardrail in the plugin. Say this at the top of every output. Do\nnot drop it. Do not soften it.**\n\n> **This is a triage, not a finding of infringement or non-infringement.**\n> Infringement analysis is fact-intensive and legally complex. The triage\n> identifies the factors and flags the ones that matter most; it does not\n> conclude. A conclusion that something does or does not infringe is a legal\n> opinion that requires an attorney's judgment on the facts, the claim or\n> right scope, the relevant jurisdiction's law, and the likely defenses.\n> Acting on a triage — sending a cease-and-desist, refusing to stop, filing\n> suit, or deciding not to — without attorney review is how companies end up\n> on the wrong side of fee awards, Rule 11 sanctions, declaratory-judgment\n> actions, and (for patents) treble damages.\n\nUnder-calling a conflict is a one-way door — a C&D not sent and a mark goes\ngeneric in the market; a claim not chased and the statute of limitations runs;\na copied copyrighted work kept on the site. Over-calling is a two-way door —\nthe attorney narrows. Stay on the two-way door side.\n\n---\n\n## Matter context\n\n**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: \"Which matter is this for? Run `\u002Fip-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\nInfringement triages often lead into cease-and-desist drafting or takedown\nrouting. Open a matter if one isn't active and the practice is private — the\ntriage, the C&D, and any downstream response belong in one workspace.\n\n---\n\n## Load the practice profile first\n\nRead `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. Pull:\n\n- **Role** from `## Who's using this`.\n- **Enforcement posture** from `## Enforcement posture` — the triage output\n  should end with a routing suggestion consistent with the stated posture\n  (aggressive \u002F measured \u002F conservative) and the named approver for the\n  relevant letter type.\n- **Registered in \u002F enforce where** from `## IP practice profile` — determines\n  which circuit \u002F jurisdiction test to apply by default.\n- **Integrations** from `## Available integrations` — CourtListener,\n  Solve Intelligence each affects whether the triage can cite to case law,\n  prior rulings, or prior art.\n- **Decision posture** from `## Decision posture on subjective legal calls` —\n  this skill never concludes on a subjective threshold.\n\nIf the config has `[PLACEHOLDER]`, surface this bounce:\n\n> I notice you haven't configured your practice profile yet — that's how I tailor posture, jurisdictions, and approval chain to your practice.\n>\n> **Two choices:**\n> - Run `\u002Fip-legal:cold-start-interview` (2 minutes) to configure your profile, then I'll run this tailored to YOUR practice.\n> - Say **\"provisional\"** and I'll run this against generic defaults — US jurisdiction, middle risk appetite, lawyer role, no playbook — and tag every output `[PROVISIONAL — configure your profile for tailored output]` so you can see what I do before committing.\n\n### Provisional mode\n\nIf the user says \"provisional,\" run the infringement triage normally using these generic defaults: middle risk appetite, lawyer role, US jurisdiction, no playbook (do the full analysis rather than matching against a position list). Tag the reviewer note and every finding block with `[PROVISIONAL]`. At the end of the output, append:\n\n> \"That was a generic run against default assumptions. Run `\u002Fip-legal:cold-start-interview` to get output calibrated to YOUR practice — your playbook, your jurisdiction, your risk appetite. 2 minutes.\"\n\n---\n\n## Mode selection\n\nAsk at the top, before anything else:\n\n> Which right are we triaging?\n>\n> 1. **Trademark** — confusion, dilution, or false advertising\n> 2. **Copyright** — substantial similarity, fair use, DMCA safe harbor\n> 3. **Patent** — claim-chart first pass, literal read + doctrine of equivalents\n> 4. **Trade secret** — secrecy, reasonable measures, misappropriation\n> 5. **Mixed \u002F not sure** — describe the facts and I'll pick\n\nIf the user picks \"not sure,\" help them sort. The same facts can implicate\nmultiple rights (e.g., a competitor's product uses our logo — trademark; and\nthe product is a near-copy of ours — possible patent, copyright on packaging,\npossible trade dress; and a former employee launched it — trade secret).\n\n**If more than one right is in play, run the triage for each, separately.**\nDon't mash them together. Each right has different factors, different\njurisdictional rules, and different remedies.\n\n---\n\n## Intake (common to all modes)\n\n> Before I walk factors:\n>\n> 1. **Posture.** Are you the potentially senior party (they're taking\n>    yours) or the potentially accused party (we're the ones being looked at)?\n>    The factors are symmetric but the output differs — a \"mine's being\n>    copied\" triage routes toward an assertion letter; a \"we might be\n>    exposed\" triage routes toward a risk memo.\n> 2. **Jurisdiction.** Which country \u002F circuit \u002F court? US federal default if\n>    not specified. Flag if foreign law may apply.\n> 3. **Timing.** Is a statute of limitations or laches clock running?\n> 4. **What exhibits \u002F evidence \u002F source documents do you have?** A screenshot,\n>    a URL, a packaging photo, a code excerpt, an ex-employee contract.\n\nWait for the answer before walking factors.\n\n---\n\n## Trademark mode\n\n### Confusion\n\nUse the applicable circuit's multi-factor test. Cite the test (du Pont \u002F\nPolaroid \u002F Sleekcraft \u002F other — see the `clearance` skill for the case\ncitations and pick logic). Walk each factor and flag what cuts each way.\n\n- **Similarity of marks** — sight \u002F sound \u002F meaning \u002F commercial impression.\n- **Similarity of goods or services** — expected-source test, not identity.\n- **Channels of trade.**\n- **Consumer sophistication.**\n- **Strength of the senior mark** — fanciful \u002F arbitrary \u002F suggestive \u002F\n  descriptive with secondary meaning \u002F generic.\n- **Intent** — evidence of copying, knock-off trade dress, near-miss mark.\n- **Actual confusion** — any evidence (surveys, misdirected inquiries, social).\n- **Likelihood of expansion \u002F bridge-the-gap** — whether the zones overlap\n  commercially.\n\n### Dilution\n\nApply the federal TDRA (15 U.S.C. § 1125(c)) and any applicable state statute.\n\n- **Fame threshold.** The senior mark must be famous to the general consuming\n  public — a niche-famous mark is not enough. *Starbucks Corp. v. Wolfe's\n  Borough Coffee, Inc.*, 588 F.3d 97 (2d Cir. 2009) is representative.\n- **Blurring vs. tarnishment.** Blurring = distinctiveness harm; tarnishment\n  = reputation harm.\n- **Defenses** — comparative advertising, news reporting, fair use,\n  non-commercial use.\n\nIf the senior mark is not plainly famous nationally, flag dilution as a\nstretch.\n\n### False advertising \u002F comparative claims\n\nIf the triage is prompted by a competitor's comparative ad or a claim about\nproduct attributes:\n\n- Apply Lanham Act § 43(a) \u002F 15 U.S.C. § 1125(a) for the materiality,\n  falsity-or-misleading, deception, commercial-speech, and injury elements.\n- Flag whether the statement is literally false, implicitly false, or\n  puffery. Puffery is not actionable.\n- Substantiation evidence the claimant has or needs.\n\n### Output\n\nFactors table; what cuts each way; a \"not a finding\" conclusion line. End with\na routing suggestion against the enforcement posture in the practice profile.\n\n---\n\n## Copyright mode\n\n### Ownership\n\nIs the claimant the owner (or exclusive licensee with standing)? Work-for-hire\nissues; joint authorship; assignments; and termination rights all flag.\n\n### Registration\n\n17 U.S.C. § 411 requires registration (or preregistration) as a precondition\nto filing an infringement action in US federal court. *Fourth Estate Public\nBenefit Corp. v. Wall-Street.com, LLC*, 586 U.S. 296 (2019) — registration\nmeans actually issued, not just applied for. Flag registration status; if\nnot registered, flag the practical bar on filing.\n\n### Access + substantial similarity\n\nTwo paths to proving copying:\n\n- **Access + probative similarity** — defendant had access and the works share\n  features probative of copying.\n- **Striking similarity** — even absent proof of access, the similarity is so\n  striking that independent creation is unlikely.\n\nFor substantial similarity, apply the circuit's test (Second Circuit's\nordinary-observer; Ninth Circuit's extrinsic \u002F intrinsic under *Krofft* and\n*Swirsky*; Fourth \u002F Seventh \u002F Eleventh circuits' variations). Flag which\ntest applies.\n\n### Fair use\n\n17 U.S.C. § 107 four factors, analyzed as a whole:\n\n1. Purpose and character of the use (transformativeness; commercial vs.\n   non-commercial).\n2. Nature of the copyrighted work (factual \u002F functional vs. creative).\n3. Amount and substantiality of the portion used.\n4. Effect on the market for the original.\n\nRecent touchstones: *Google LLC v. Oracle America, Inc.*, 593 U.S. 1 (2021);\n*Andy Warhol Found. for the Visual Arts, Inc. v. Goldsmith*, 598 U.S. 508\n(2023). Flag the transformativeness analysis carefully — *Warhol* narrowed\nthe scope of transformative use and is still being applied by lower courts.\n\n### DMCA safe harbor\n\n17 U.S.C. § 512. If the accused is a service provider hosting user content,\nflag whether § 512(c) applies: designated agent, notice-and-takedown\nprocedure, no actual or red-flag knowledge, no financial benefit\nattributable to infringement the provider could control, expeditious\ntakedown on valid notice. Repeat-infringer policy required. Safe harbor does\nnot cover direct infringement by the service provider itself.\n\n### Output\n\nFactors flagged; fair-use balance with \"the triage does not conclude\";\nownership \u002F registration \u002F safe-harbor threshold notes. Routing per posture.\n\n---\n\n## Patent mode\n\n**Route to `\u002Fip-legal:fto-triage` for the detailed framework.** This mode is the\nmirror image of the FTO skill — same claim charts, same doctrine-of-equivalents\nflag, same all-elements rule — applied to an accused product instead of one's\nown.\n\n### Design patent (D-number) — branch before the workflow\n\n**Check the asserted patent's registration number FIRST.** If it has a `D`,\n`RE`, or `PP` prefix (e.g., `D712,345`), it's not a utility patent and the\nworkflow below does NOT apply. Branch per prefix:\n\n- **`D` prefix — design patent (35 U.S.C. §171).** Different test, different\n  claim structure, different damages. Do NOT build a claim chart, do NOT run\n  doctrine of equivalents, do NOT do element-by-element mapping. Design\n  patents have a single claim defined by the drawings; charting a figure as\n  if it were a utility claim element list is wrong doctrine.\n- **`RE` prefix — reissue patent.** Treat as the utility patent it reissued,\n  but flag reissue-specific defenses (intervening rights under §252,\n  recapture rule, original-patent requirement).\n- **`PP` prefix — plant patent.** Separate regime (35 U.S.C. §161). Asexually\n  reproduced plant varieties. Route to plant-patent counsel; this skill does\n  not analyze plant patents.\n\n**Design patent infringement test — ordinary observer.** *Egyptian Goddess,\nInc. v. Swisa, Inc.*, 543 F.3d 665 (Fed. Cir. 2008) (en banc). The question\nis whether an ordinary observer, **familiar with the prior art designs**,\nwould be deceived into thinking the accused design is the same as the\npatented design. Compare **overall ornamental appearance**, not individual\nelements. The accused product must appropriate the **novelty** that\ndistinguishes the patented design from the prior art (the \"point of novelty\"\nsurvives as a guidepost inside the ordinary-observer test, not as a separate\ntest).\n\n**Functional-vs-ornamental filter.** Design patents protect ornamental\nfeatures only; functional features are not protected. If the accused\nsimilarity is in features dictated by function, flag that the overlap may\nfall outside the patented scope.\n\n**§289 total-profit damages flag.** Design patent damages under 35 U.S.C.\n§289 are the infringer's **total profits on the \"article of manufacture,\"**\nwhich can be the whole product or a component. *Samsung Electronics Co. v.\nApple Inc.*, 580 U.S. 53 (2016). This is a separate analysis from utility\npatent reasonable-royalty \u002F lost-profits and is specialist work — do not\ncompute.\n\n**Trade dress cross-flag.** The same ornamental-shape facts are usually also\na **trade dress** question under Lanham Act §43(a) (15 U.S.C. §1125(a)).\nProduct configuration trade dress requires **secondary meaning** (*Wal-Mart\nStores, Inc. v. Samara Bros., Inc.*, 529 U.S. 205 (2000)) and must be\n**non-functional** (*TrafFix Devices, Inc. v. Marketing Displays, Inc.*,\n532 U.S. 23 (2001)). Flag trade dress as a parallel track; the tests are\ndifferent but the evidence overlaps.\n\n### Design patent triage — output\n\nBecause you cannot see the patent drawings or the accused product directly,\nthe design patent triage is mostly a request for the materials and a frame\nfor the analysis:\n\n- **Ask for the drawings.** \"I can't run the ordinary-observer test without\n  seeing the patent figures and the accused product. Paste or attach: (a)\n  the patent drawings (all figures, including any broken-line disclaimers),\n  (b) photos of the accused product from comparable angles, (c) any prior\n  art designs you're aware of.\"\n- **Prior-art landscape.** Ordinary observer is a *comparison* test — the\n  observer is \"familiar with the prior art,\" so the scope of the patented\n  design narrows as the prior-art field crowds. Flag what prior art is\n  known and what's missing.\n- **Functional-vs-ornamental analysis.** Walk the features and flag which\n  look functional (and therefore unprotected) vs. ornamental.\n- **Broken lines.** Design patents use solid lines for claimed features and\n  broken lines for unclaimed environmental context. Flag whether the\n  alleged copying is in claimed (solid-line) or unclaimed (broken-line)\n  territory.\n- **§289 damages flag** as above.\n- **Trade dress cross-flag** as above.\n\n**Route to a design patent specialist for anything beyond first-pass triage.**\nDesign patent litigation is a subspecialty (Perkins Coie, Sterne Kessler,\nDesmarais, Kirkland's design team, Gibson Dunn's design group are\nrepresentative; use your practice profile's IP litigation OC as the starting\npoint). This skill flags issues; it does not assess infringement.\n\n### Utility patent workflow\n\nThe rest of this mode assumes the asserted patent is a **utility patent**\n(no `D`\u002F`RE`\u002F`PP` prefix). If the D-number branch above applies, stop here.\n\n> **Patent systems differ by jurisdiction.** The US claim chart (all-elements rule, doctrine of equivalents, prosecution history estoppel, §284\u002F§289 damages) does not transfer to other systems:\n> - **Germany:** Utility models (Gebrauchsmuster), the Schneidmesser\u002FKunststoffrohrteil questions for DOE, bifurcated validity\u002Finfringement proceedings.\n> - **China:** Utility models (shiyong xinxing), CNIPA examination, different claim construction.\n> - **Japan:** Utility models, JPO examination, a narrower DOE.\n> - **Europe (unified patent court):** UPC procedure as of 2023.\n>\n> When non-US jurisdictions are in scope: \"This analysis uses the US claim-charting framework. A product manufactured in China and sold in the EU needs CNIPA and EP analysis, not a US claim chart. I can flag the issues a US analysis surfaces, but the infringement and validity calls require [jurisdiction]-specific review.\"\n\n### Workflow\n\n- Accused product \u002F process \u002F method — described in technical detail.\n- Identified patent(s) at issue.\n- Claim chart for each independent claim: element-by-element mapping to the\n  accused product.\n- Literal infringement first. DOE as a flag.\n- Indirect (induced, contributory) and divided infringement as flags.\n- **Invalidity defenses to consider** — anticipation (§ 102), obviousness\n  (§ 103), § 112 written-description \u002F enablement \u002F definiteness, § 101\n  subject-matter eligibility (*Alice* \u002F *Mayo*). Known IPR or PGR outcomes,\n  known prior art, known prosecution history. Flag each; do not opine.\n- **Unenforceability defenses** — inequitable conduct flag, prosecution\n  laches flag, assignor \u002F licensee estoppel flag. Each is attorney-only.\n- **Damages posture** — lost profits vs. reasonable royalty (Georgia-Pacific\n  factors), marking, pre-suit notice, willfulness (reading this triage may\n  factor into willfulness — see the FTO skill's willfulness note).\n\n### Output\n\nClaim charts. Element flags. Defense flags. Routing to patent counsel. See\nthe `fto-triage` skill for the full output structure — the infringement-triage\npatent mode uses the same format with \"accused product\" substituted for\n\"own product.\"\n\n### Handoff to the full claim chart\n\nFor a detailed element-by-element claim chart suitable for infringement or\ninvalidity contentions, run `\u002Flitigation-legal:claim-chart`. This triage's\nclaim chart is a first pass to identify the strongest and weakest mappings;\nthe litigation claim chart builds the full chart with pin cites, claim\nconstruction flags, dependent claims, and the verification workflow that\ncontentions require.\n\n---\n\n## Trade secret mode\n\n### Was it a secret?\n\nApply the Defend Trade Secrets Act (18 U.S.C. § 1836 et seq.) for federal\npurposes and the applicable state UTSA (or, in New York \u002F Massachusetts \u002F\nother non-UTSA jurisdictions, the state's common-law test). Flag:\n\n- **Not generally known** — to the public or to others in the industry who can\n  obtain economic value from disclosure.\n- **Economic value from secrecy** — independent economic value actual or\n  potential, derived from not being generally known.\n- **Combinations and compilations** — a combination of public elements can\n  be a trade secret (*Altavion v. Konica Minolta*, and the Restatement view).\n\n### Reasonable measures\n\n- NDAs with employees, contractors, counterparties. Scope, signed, enforced?\n- Access controls — technical (role-based), physical (doors, badges),\n  organizational (need-to-know).\n- Marking — confidentiality legends on documents, code, data.\n- Exit interviews \u002F return of materials on termination.\n- Trade-secret policy \u002F training.\n\nFlag what's in place and what's missing. *Reasonable* is fact-specific; the\ntriage does not decide whether the measures were reasonable — it lists them.\n\n### Misappropriation\n\nAcquisition by improper means, or disclosure \u002F use in breach of duty.\nImproper means includes theft, bribery, misrepresentation, breach or\ninducement of breach of a duty to maintain secrecy, or espionage (electronic\nor otherwise). 18 U.S.C. § 1839(6).\n\n- **Former employee fact pattern:** new employer, overlapping work,\n  departure timing, documents taken (and returned?), access logs, recruiting\n  channels, assignment and invention-assignment agreements.\n- **Inadvertent disclosure:** Was disclosure made by a person with a duty? Did\n  the recipient know or have reason to know of the breach?\n- **Reverse engineering** — a defense if the means were lawful. Flag whether\n  reverse engineering is plausible on the facts.\n\n### Preemption\n\nWhere state tort claims (unfair competition, conversion, breach of confidence)\nmight be preempted by the UTSA, flag preemption. Some jurisdictions preserve\ncontract claims; others preempt most tort claims addressing the same facts.\n\n### Output\n\nThree flag groups — secrecy, measures, misappropriation — each with what cuts\neach way. Routing per posture.\n\n---\n\n## Output format (all modes)\n\nPrepend the work-product header from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` `## Outputs`.\n\n```markdown\n[WORK-PRODUCT HEADER]\n\n# Infringement Triage — [Trademark | Copyright | Patent | Trade Secret] (NOT A FINDING)\n\n**This is a triage, not a finding of infringement or non-infringement.** The\ntriage identifies factors and flags what matters most; it does not conclude.\nA conclusion requires an attorney's judgment on the facts, the right scope,\njurisdiction, and defenses. Acting on a triage without attorney review is\nhow companies end up on the wrong side of fee awards, Rule 11 sanctions,\ndeclaratory-judgment actions, and enhanced damages.\n\n**Triage result:** [GREEN \u002F YELLOW \u002F RED — one sentence why]\n\n## Posture and scope\n\n- **Party posture:** [senior \u002F accused]\n- **Right at issue:** [trademark \u002F copyright \u002F patent \u002F trade secret]\n- **Jurisdiction:** [US federal — specific circuit \u002F state \u002F foreign]\n- **Legal framework applied:** [cite the governing test and statute]\n- **Statute of limitations \u002F laches posture:** [clock status]\n- **Exhibits \u002F evidence reviewed:** [list]\n\n## Factor analysis\n\n[Mode-specific factor table — confusion factors \u002F fair-use factors \u002F claim chart\n\u002F trade-secret elements. Each factor has a flag and a direction. This is\na flag list, not a verdict.]\n\n## Defenses and thresholds\n\n[Mode-specific: dilution fame threshold \u002F registration prerequisite \u002F\n§ 512 safe harbor \u002F invalidity \u002F inequitable conduct \u002F preemption \u002F\nreverse-engineering \u002F consent \u002F license \u002F laches \u002F statute of limitations.\nFlag each.]\n\n## What cuts which way — summary\n\n| Factor | Flag | Direction (senior \u002F accused \u002F mixed) |\n|---|---|---|\n| [factor 1] | [note] | [direction] |\n\n**Conclusion:** *This skill does not conclude.* Attorney judgment required\nbefore acting. The factors cutting [direction] are [brief summary]; the\nfactors cutting [direction] are [brief summary].\n\n## Recommended next steps\n\n- [formal opinion from counsel \u002F route to IP OC named in the practice profile]\n- [evidence preservation and hold — if a litigation clock is running]\n- [fact development needed before a decision — e.g., access logs, prosecution\n  history, market studies, survey evidence]\n- [routing per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`\n  `## Enforcement posture`, if the posture is to assert]\n\n## Citation verification\n\nEvery case, statute, registration number, claim quote, and exhibit cited here\nmust be verified against the authoritative source before relying on it.\nJurisdictional tests vary by circuit and change over time — confirm the\ncurrent controlling authority.\n```\n\n---\n\n## Non-lawyer gate\n\nBefore issuing the output, read `## Who's using this`. If the Role is Non-lawyer:\n\n> This output is a research triage, not legal advice. Sending a C&D, deciding\n> not to stop, filing suit, or relying on \"it's fair use\" based on this triage\n> alone has legal consequences — including Rule 11 sanctions for a baseless\n> assertion, declaratory-judgment exposure for a threatening letter, treble\n> damages on the patent side, and fee awards in unfair-competition cases.\n> An attorney needs to evaluate before you move.\n>\n> Here's a brief to bring to an attorney:\n>\n> [Generate a 1-page summary: the right at issue, the posture, the facts and\n> evidence, the factors surfaced, the defenses flagged, and the three\n> questions to ask the attorney.]\n>\n> If you need to find a licensed attorney, solicitor, barrister, or other authorised legal professional in your jurisdiction: your professional regulator's referral service is\n> the starting point (state bar in the US, SRA\u002FBar Standards Board in England & Wales, Law Society in Scotland\u002FNI\u002FIreland\u002FCanada\u002FAustralia, or your jurisdiction's equivalent). For patents in the US, the attorney must be registered before the\n> USPTO; for other jurisdictions, use the relevant patent office register. For trademarks, INTA maintains a directory of practitioners worldwide.\n\nDeliver the triage alongside the brief.\n\n---\n\n## Output location\n\nIf matter workspaces are enabled and a matter is active, write to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002Foutputs\u002Finfringe-\u003Cmode>-\u003Csubject-slug>-YYYY-MM-DD.md`.\nOtherwise write to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Foutputs\u002Finfringe-\u003Cmode>-\u003Csubject-slug>-YYYY-MM-DD.md`\nand surface the path.\n\nAppend a one-line entry to the matter's `history.md` if a matter is active.\n\n---\n\n## Handoff to enforcement skills\n\nIf the triage output points toward an assertion and the practice profile's\nposture supports it, offer:\n\n> Want me to draft a cease-and-desist on this? Run `\u002Fip-legal:cease-desist`.\n> I'll use the flag list from this triage as the factual basis and apply the\n> approval chain from your practice profile — the letter won't go anywhere\n> without the approver signing off.\n\nOr, if the mode is copyright and the accused is hosted content:\n\n> Want me to prepare a DMCA takedown? Run `\u002Fip-legal:takedown`.\n\nDo not draft the letter automatically from the triage. The decision to assert\nis the approver's, not the triage's.\n\n---\n\n## Close with the next-steps decision tree\n\nEnd with the next-steps decision tree per CLAUDE.md `## Outputs`. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.\n\n## What this skill does not do\n\n- **Conclude infringement or non-infringement.** Ever. The loudest guardrail.\n- **Substitute for survey evidence, damages experts, or claim construction.**\n- **Evaluate jurisdiction-specific defenses outside the triage's jurisdiction\n  scope.** If the facts cross borders, flag that foreign-law analysis is\n  required.\n- **Decide fair use as a matter of law.** Fair use is fact-intensive and\n  reserved for the attorney and, ultimately, the court.\n- **Draft the C&D, takedown, or complaint.** Those are separate skills\n  (`\u002Fip-legal:cease-desist`, `\u002Fip-legal:takedown`) gated by the approval\n  chain in the practice profile.\n- **Quote outputs to counterparties.** Privileged if the header applies.\n\n---\n\n## Tone\n\nFactor-by-factor, flag-by-flag. No hedging prose. The guardrail at the top\ndoes the scope work; the analysis does the analysis. A lawyer should leave\nthe output knowing exactly which factors are flagged, which defenses apply,\nand what they need to do next to either assert or stand down.\n","# \u002Finfringement-triage\n\n**This is a triage, not a finding of infringement or non-infringement.**\nInfringement analysis is fact-intensive and legally complex. Acting on a\ntriage — sending a cease-and-desist, refusing to stop, filing suit, or\ndeciding not to — without attorney review is how companies end up on the\nwrong side of fee awards, Rule 11 sanctions, declaratory-judgment actions,\nand (for patents) treble damages.\n\n## Instructions\n\n1. Read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. If it\n   contains `[PLACEHOLDER]`, stop and direct to `\u002Fip-legal:cold-start-interview`.\n2. Follow the workflow below.\n3. Ask which right is at issue — trademark \u002F copyright \u002F patent \u002F trade secret\n   \u002F mixed. If mixed, run each separately; do not blend.\n4. Run common intake (party posture — senior or accused, jurisdiction, timing,\n   exhibits).\n5. Walk the mode-specific factors:\n   - **Trademark** — circuit's confusion test + dilution (if famous) +\n     false advertising (if a comparative claim).\n   - **Copyright** — ownership + registration + access + substantial\n     similarity + fair use + DMCA safe harbor (if applicable).\n   - **Patent** — claim-chart first pass (route to `fto-triage` output\n     structure); literal + DOE; indirect + divided; invalidity defenses to\n     consider.\n   - **Trade secret** — secrecy + reasonable measures + misappropriation;\n     preemption + reverse-engineering flags.\n6. Produce a flag list with direction — what cuts toward the senior party,\n   what cuts toward the accused, what's mixed. Never conclude.\n7. Write the triage memo to the matter folder or practice outputs folder. Apply\n   the work-product header per role.\n8. End with recommended next steps, the non-lawyer gate if the role is\n   non-lawyer, and — if the practice posture supports assertion — an offer to\n   draft the C&D via `\u002Fip-legal:cease-desist` or the takedown via\n   `\u002Fip-legal:takedown`. Do not draft automatically.\n\nThis skill never concludes. If uncertain, flag — the attorney decides.\n\n## Examples\n\n```\n\u002Fip-legal:infringement-triage \"competitor launched a tool called APEXSEED in class 9 — we have APEXLEAF registered in class 9; likely confusion?\"\n```\n\n```\n\u002Fip-legal:infringement-triage \"former engineer took notes on our model architecture to a competitor — possible trade secret?\"\n```\n\n```\n\u002Fip-legal:infringement-triage\n```\n\n(And the skill will ask which right and for the facts.)\n\n---\n\n## THIS IS A TRIAGE, NOT A FINDING\n\n**The loudest guardrail in the plugin. Say this at the top of every output. Do\nnot drop it. Do not soften it.**\n\n> **This is a triage, not a finding of infringement or non-infringement.**\n> Infringement analysis is fact-intensive and legally complex. The triage\n> identifies the factors and flags the ones that matter most; it does not\n> conclude. A conclusion that something does or does not infringe is a legal\n> opinion that requires an attorney's judgment on the facts, the claim or\n> right scope, the relevant jurisdiction's law, and the likely defenses.\n> Acting on a triage — sending a cease-and-desist, refusing to stop, filing\n> suit, or deciding not to — without attorney review is how companies end up\n> on the wrong side of fee awards, Rule 11 sanctions, declaratory-judgment\n> actions, and (for patents) treble damages.\n\nUnder-calling a conflict is a one-way door — a C&D not sent and a mark goes\ngeneric in the market; a claim not chased and the statute of limitations runs;\na copied copyrighted work kept on the site. Over-calling is a two-way door —\nthe attorney narrows. Stay on the two-way door side.\n\n---\n\n## Matter context\n\n**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: \"Which matter is this for? Run `\u002Fip-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\nInfringement triages often lead into cease-and-desist drafting or takedown\nrouting. Open a matter if one isn't active and the practice is private — the\ntriage, the C&D, and any downstream response belong in one workspace.\n\n---\n\n## Load the practice profile first\n\nRead `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`. Pull:\n\n- **Role** from `## Who's using this`.\n- **Enforcement posture** from `## Enforcement posture` — the triage output\n  should end with a routing suggestion consistent with the stated posture\n  (aggressive \u002F measured \u002F conservative) and the named approver for the\n  relevant letter type.\n- **Registered in \u002F enforce where** from `## IP practice profile` — determines\n  which circuit \u002F jurisdiction test to apply by default.\n- **Integrations** from `## Available integrations` — CourtListener,\n  Solve Intelligence each affects whether the triage can cite to case law,\n  prior rulings, or prior art.\n- **Decision posture** from `## Decision posture on subjective legal calls` —\n  this skill never concludes on a subjective threshold.\n\nIf the config has `[PLACEHOLDER]`, surface this bounce:\n\n> I notice you haven't configured your practice profile yet — that's how I tailor posture, jurisdictions, and approval chain to your practice.\n>\n> **Two choices:**\n> - Run `\u002Fip-legal:cold-start-interview` (2 minutes) to configure your profile, then I'll run this tailored to YOUR practice.\n> - Say **\"provisional\"** and I'll run this against generic defaults — US jurisdiction, middle risk appetite, lawyer role, no playbook — and tag every output `[PROVISIONAL — configure your profile for tailored output]` so you can see what I do before committing.\n\n### Provisional mode\n\nIf the user says \"provisional,\" run the infringement triage normally using these generic defaults: middle risk appetite, lawyer role, US jurisdiction, no playbook (do the full analysis rather than matching against a position list). Tag the reviewer note and every finding block with `[PROVISIONAL]`. At the end of the output, append:\n\n> \"That was a generic run against default assumptions. Run `\u002Fip-legal:cold-start-interview` to get output calibrated to YOUR practice — your playbook, your jurisdiction, your risk appetite. 2 minutes.\"\n\n---\n\n## Mode selection\n\nAsk at the top, before anything else:\n\n> Which right are we triaging?\n>\n> 1. **Trademark** — confusion, dilution, or false advertising\n> 2. **Copyright** — substantial similarity, fair use, DMCA safe harbor\n> 3. **Patent** — claim-chart first pass, literal read + doctrine of equivalents\n> 4. **Trade secret** — secrecy, reasonable measures, misappropriation\n> 5. **Mixed \u002F not sure** — describe the facts and I'll pick\n\nIf the user picks \"not sure,\" help them sort. The same facts can implicate\nmultiple rights (e.g., a competitor's product uses our logo — trademark; and\nthe product is a near-copy of ours — possible patent, copyright on packaging,\npossible trade dress; and a former employee launched it — trade secret).\n\n**If more than one right is in play, run the triage for each, separately.**\nDon't mash them together. Each right has different factors, different\njurisdictional rules, and different remedies.\n\n---\n\n## Intake (common to all modes)\n\n> Before I walk factors:\n>\n> 1. **Posture.** Are you the potentially senior party (they're taking\n>    yours) or the potentially accused party (we're the ones being looked at)?\n>    The factors are symmetric but the output differs — a \"mine's being\n>    copied\" triage routes toward an assertion letter; a \"we might be\n>    exposed\" triage routes toward a risk memo.\n> 2. **Jurisdiction.** Which country \u002F circuit \u002F court? US federal default if\n>    not specified. Flag if foreign law may apply.\n> 3. **Timing.** Is a statute of limitations or laches clock running?\n> 4. **What exhibits \u002F evidence \u002F source documents do you have?** A screenshot,\n>    a URL, a packaging photo, a code excerpt, an ex-employee contract.\n\nWait for the answer before walking factors.\n\n---\n\n## Trademark mode\n\n### Confusion\n\nUse the applicable circuit's multi-factor test. Cite the test (du Pont \u002F\nPolaroid \u002F Sleekcraft \u002F other — see the `clearance` skill for the case\ncitations and pick logic). Walk each factor and flag what cuts each way.\n\n- **Similarity of marks** — sight \u002F sound \u002F meaning \u002F commercial impression.\n- **Similarity of goods or services** — expected-source test, not identity.\n- **Channels of trade.**\n- **Consumer sophistication.**\n- **Strength of the senior mark** — fanciful \u002F arbitrary \u002F suggestive \u002F\n  descriptive with secondary meaning \u002F generic.\n- **Intent** — evidence of copying, knock-off trade dress, near-miss mark.\n- **Actual confusion** — any evidence (surveys, misdirected inquiries, social).\n- **Likelihood of expansion \u002F bridge-the-gap** — whether the zones overlap\n  commercially.\n\n### Dilution\n\nApply the federal TDRA (15 U.S.C. § 1125(c)) and any applicable state statute.\n\n- **Fame threshold.** The senior mark must be famous to the general consuming\n  public — a niche-famous mark is not enough. *Starbucks Corp. v. Wolfe's\n  Borough Coffee, Inc.*, 588 F.3d 97 (2d Cir. 2009) is representative.\n- **Blurring vs. tarnishment.** Blurring = distinctiveness harm; tarnishment\n  = reputation harm.\n- **Defenses** — comparative advertising, news reporting, fair use,\n  non-commercial use.\n\nIf the senior mark is not plainly famous nationally, flag dilution as a\nstretch.\n\n### False advertising \u002F comparative claims\n\nIf the triage is prompted by a competitor's comparative ad or a claim about\nproduct attributes:\n\n- Apply Lanham Act § 43(a) \u002F 15 U.S.C. § 1125(a) for the materiality,\n  falsity-or-misleading, deception, commercial-speech, and injury elements.\n- Flag whether the statement is literally false, implicitly false, or\n  puffery. Puffery is not actionable.\n- Substantiation evidence the claimant has or needs.\n\n### Output\n\nFactors table; what cuts each way; a \"not a finding\" conclusion line. End with\na routing suggestion against the enforcement posture in the practice profile.\n\n---\n\n## Copyright mode\n\n### Ownership\n\nIs the claimant the owner (or exclusive licensee with standing)? Work-for-hire\nissues; joint authorship; assignments; and termination rights all flag.\n\n### Registration\n\n17 U.S.C. § 411 requires registration (or preregistration) as a precondition\nto filing an infringement action in US federal court. *Fourth Estate Public\nBenefit Corp. v. Wall-Street.com, LLC*, 586 U.S. 296 (2019) — registration\nmeans actually issued, not just applied for. Flag registration status; if\nnot registered, flag the practical bar on filing.\n\n### Access + substantial similarity\n\nTwo paths to proving copying:\n\n- **Access + probative similarity** — defendant had access and the works share\n  features probative of copying.\n- **Striking similarity** — even absent proof of access, the similarity is so\n  striking that independent creation is unlikely.\n\nFor substantial similarity, apply the circuit's test (Second Circuit's\nordinary-observer; Ninth Circuit's extrinsic \u002F intrinsic under *Krofft* and\n*Swirsky*; Fourth \u002F Seventh \u002F Eleventh circuits' variations). Flag which\ntest applies.\n\n### Fair use\n\n17 U.S.C. § 107 four factors, analyzed as a whole:\n\n1. Purpose and character of the use (transformativeness; commercial vs.\n   non-commercial).\n2. Nature of the copyrighted work (factual \u002F functional vs. creative).\n3. Amount and substantiality of the portion used.\n4. Effect on the market for the original.\n\nRecent touchstones: *Google LLC v. Oracle America, Inc.*, 593 U.S. 1 (2021);\n*Andy Warhol Found. for the Visual Arts, Inc. v. Goldsmith*, 598 U.S. 508\n(2023). Flag the transformativeness analysis carefully — *Warhol* narrowed\nthe scope of transformative use and is still being applied by lower courts.\n\n### DMCA safe harbor\n\n17 U.S.C. § 512. If the accused is a service provider hosting user content,\nflag whether § 512(c) applies: designated agent, notice-and-takedown\nprocedure, no actual or red-flag knowledge, no financial benefit\nattributable to infringement the provider could control, expeditious\ntakedown on valid notice. Repeat-infringer policy required. Safe harbor does\nnot cover direct infringement by the service provider itself.\n\n### Output\n\nFactors flagged; fair-use balance with \"the triage does not conclude\";\nownership \u002F registration \u002F safe-harbor threshold notes. Routing per posture.\n\n---\n\n## Patent mode\n\n**Route to `\u002Fip-legal:fto-triage` for the detailed framework.** This mode is the\nmirror image of the FTO skill — same claim charts, same doctrine-of-equivalents\nflag, same all-elements rule — applied to an accused product instead of one's\nown.\n\n### Design patent (D-number) — branch before the workflow\n\n**Check the asserted patent's registration number FIRST.** If it has a `D`,\n`RE`, or `PP` prefix (e.g., `D712,345`), it's not a utility patent and the\nworkflow below does NOT apply. Branch per prefix:\n\n- **`D` prefix — design patent (35 U.S.C. §171).** Different test, different\n  claim structure, different damages. Do NOT build a claim chart, do NOT run\n  doctrine of equivalents, do NOT do element-by-element mapping. Design\n  patents have a single claim defined by the drawings; charting a figure as\n  if it were a utility claim element list is wrong doctrine.\n- **`RE` prefix — reissue patent.** Treat as the utility patent it reissued,\n  but flag reissue-specific defenses (intervening rights under §252,\n  recapture rule, original-patent requirement).\n- **`PP` prefix — plant patent.** Separate regime (35 U.S.C. §161). Asexually\n  reproduced plant varieties. Route to plant-patent counsel; this skill does\n  not analyze plant patents.\n\n**Design patent infringement test — ordinary observer.** *Egyptian Goddess,\nInc. v. Swisa, Inc.*, 543 F.3d 665 (Fed. Cir. 2008) (en banc). The question\nis whether an ordinary observer, **familiar with the prior art designs**,\nwould be deceived into thinking the accused design is the same as the\npatented design. Compare **overall ornamental appearance**, not individual\nelements. The accused product must appropriate the **novelty** that\ndistinguishes the patented design from the prior art (the \"point of novelty\"\nsurvives as a guidepost inside the ordinary-observer test, not as a separate\ntest).\n\n**Functional-vs-ornamental filter.** Design patents protect ornamental\nfeatures only; functional features are not protected. If the accused\nsimilarity is in features dictated by function, flag that the overlap may\nfall outside the patented scope.\n\n**§289 total-profit damages flag.** Design patent damages under 35 U.S.C.\n§289 are the infringer's **total profits on the \"article of manufacture,\"**\nwhich can be the whole product or a component. *Samsung Electronics Co. v.\nApple Inc.*, 580 U.S. 53 (2016). This is a separate analysis from utility\npatent reasonable-royalty \u002F lost-profits and is specialist work — do not\ncompute.\n\n**Trade dress cross-flag.** The same ornamental-shape facts are usually also\na **trade dress** question under Lanham Act §43(a) (15 U.S.C. §1125(a)).\nProduct configuration trade dress requires **secondary meaning** (*Wal-Mart\nStores, Inc. v. Samara Bros., Inc.*, 529 U.S. 205 (2000)) and must be\n**non-functional** (*TrafFix Devices, Inc. v. Marketing Displays, Inc.*,\n532 U.S. 23 (2001)). Flag trade dress as a parallel track; the tests are\ndifferent but the evidence overlaps.\n\n### Design patent triage — output\n\nBecause you cannot see the patent drawings or the accused product directly,\nthe design patent triage is mostly a request for the materials and a frame\nfor the analysis:\n\n- **Ask for the drawings.** \"I can't run the ordinary-observer test without\n  seeing the patent figures and the accused product. Paste or attach: (a)\n  the patent drawings (all figures, including any broken-line disclaimers),\n  (b) photos of the accused product from comparable angles, (c) any prior\n  art designs you're aware of.\"\n- **Prior-art landscape.** Ordinary observer is a *comparison* test — the\n  observer is \"familiar with the prior art,\" so the scope of the patented\n  design narrows as the prior-art field crowds. Flag what prior art is\n  known and what's missing.\n- **Functional-vs-ornamental analysis.** Walk the features and flag which\n  look functional (and therefore unprotected) vs. ornamental.\n- **Broken lines.** Design patents use solid lines for claimed features and\n  broken lines for unclaimed environmental context. Flag whether the\n  alleged copying is in claimed (solid-line) or unclaimed (broken-line)\n  territory.\n- **§289 damages flag** as above.\n- **Trade dress cross-flag** as above.\n\n**Route to a design patent specialist for anything beyond first-pass triage.**\nDesign patent litigation is a subspecialty (Perkins Coie, Sterne Kessler,\nDesmarais, Kirkland's design team, Gibson Dunn's design group are\nrepresentative; use your practice profile's IP litigation OC as the starting\npoint). This skill flags issues; it does not assess infringement.\n\n### Utility patent workflow\n\nThe rest of this mode assumes the asserted patent is a **utility patent**\n(no `D`\u002F`RE`\u002F`PP` prefix). If the D-number branch above applies, stop here.\n\n> **Patent systems differ by jurisdiction.** The US claim chart (all-elements rule, doctrine of equivalents, prosecution history estoppel, §284\u002F§289 damages) does not transfer to other systems:\n> - **Germany:** Utility models (Gebrauchsmuster), the Schneidmesser\u002FKunststoffrohrteil questions for DOE, bifurcated validity\u002Finfringement proceedings.\n> - **China:** Utility models (shiyong xinxing), CNIPA examination, different claim construction.\n> - **Japan:** Utility models, JPO examination, a narrower DOE.\n> - **Europe (unified patent court):** UPC procedure as of 2023.\n>\n> When non-US jurisdictions are in scope: \"This analysis uses the US claim-charting framework. A product manufactured in China and sold in the EU needs CNIPA and EP analysis, not a US claim chart. I can flag the issues a US analysis surfaces, but the infringement and validity calls require [jurisdiction]-specific review.\"\n\n### Workflow\n\n- Accused product \u002F process \u002F method — described in technical detail.\n- Identified patent(s) at issue.\n- Claim chart for each independent claim: element-by-element mapping to the\n  accused product.\n- Literal infringement first. DOE as a flag.\n- Indirect (induced, contributory) and divided infringement as flags.\n- **Invalidity defenses to consider** — anticipation (§ 102), obviousness\n  (§ 103), § 112 written-description \u002F enablement \u002F definiteness, § 101\n  subject-matter eligibility (*Alice* \u002F *Mayo*). Known IPR or PGR outcomes,\n  known prior art, known prosecution history. Flag each; do not opine.\n- **Unenforceability defenses** — inequitable conduct flag, prosecution\n  laches flag, assignor \u002F licensee estoppel flag. Each is attorney-only.\n- **Damages posture** — lost profits vs. reasonable royalty (Georgia-Pacific\n  factors), marking, pre-suit notice, willfulness (reading this triage may\n  factor into willfulness — see the FTO skill's willfulness note).\n\n### Output\n\nClaim charts. Element flags. Defense flags. Routing to patent counsel. See\nthe `fto-triage` skill for the full output structure — the infringement-triage\npatent mode uses the same format with \"accused product\" substituted for\n\"own product.\"\n\n### Handoff to the full claim chart\n\nFor a detailed element-by-element claim chart suitable for infringement or\ninvalidity contentions, run `\u002Flitigation-legal:claim-chart`. This triage's\nclaim chart is a first pass to identify the strongest and weakest mappings;\nthe litigation claim chart builds the full chart with pin cites, claim\nconstruction flags, dependent claims, and the verification workflow that\ncontentions require.\n\n---\n\n## Trade secret mode\n\n### Was it a secret?\n\nApply the Defend Trade Secrets Act (18 U.S.C. § 1836 et seq.) for federal\npurposes and the applicable state UTSA (or, in New York \u002F Massachusetts \u002F\nother non-UTSA jurisdictions, the state's common-law test). Flag:\n\n- **Not generally known** — to the public or to others in the industry who can\n  obtain economic value from disclosure.\n- **Economic value from secrecy** — independent economic value actual or\n  potential, derived from not being generally known.\n- **Combinations and compilations** — a combination of public elements can\n  be a trade secret (*Altavion v. Konica Minolta*, and the Restatement view).\n\n### Reasonable measures\n\n- NDAs with employees, contractors, counterparties. Scope, signed, enforced?\n- Access controls — technical (role-based), physical (doors, badges),\n  organizational (need-to-know).\n- Marking — confidentiality legends on documents, code, data.\n- Exit interviews \u002F return of materials on termination.\n- Trade-secret policy \u002F training.\n\nFlag what's in place and what's missing. *Reasonable* is fact-specific; the\ntriage does not decide whether the measures were reasonable — it lists them.\n\n### Misappropriation\n\nAcquisition by improper means, or disclosure \u002F use in breach of duty.\nImproper means includes theft, bribery, misrepresentation, breach or\ninducement of breach of a duty to maintain secrecy, or espionage (electronic\nor otherwise). 18 U.S.C. § 1839(6).\n\n- **Former employee fact pattern:** new employer, overlapping work,\n  departure timing, documents taken (and returned?), access logs, recruiting\n  channels, assignment and invention-assignment agreements.\n- **Inadvertent disclosure:** Was disclosure made by a person with a duty? Did\n  the recipient know or have reason to know of the breach?\n- **Reverse engineering** — a defense if the means were lawful. Flag whether\n  reverse engineering is plausible on the facts.\n\n### Preemption\n\nWhere state tort claims (unfair competition, conversion, breach of confidence)\nmight be preempted by the UTSA, flag preemption. Some jurisdictions preserve\ncontract claims; others preempt most tort claims addressing the same facts.\n\n### Output\n\nThree flag groups — secrecy, measures, misappropriation — each with what cuts\neach way. Routing per posture.\n\n---\n\n## Output format (all modes)\n\nPrepend the work-product header from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md` `## Outputs`.\n\n```markdown\n[WORK-PRODUCT HEADER]\n\n# Infringement Triage — [Trademark | Copyright | Patent | Trade Secret] (NOT A FINDING)\n\n**This is a triage, not a finding of infringement or non-infringement.** The\ntriage identifies factors and flags what matters most; it does not conclude.\nA conclusion requires an attorney's judgment on the facts, the right scope,\njurisdiction, and defenses. Acting on a triage without attorney review is\nhow companies end up on the wrong side of fee awards, Rule 11 sanctions,\ndeclaratory-judgment actions, and enhanced damages.\n\n**Triage result:** [GREEN \u002F YELLOW \u002F RED — one sentence why]\n\n## Posture and scope\n\n- **Party posture:** [senior \u002F accused]\n- **Right at issue:** [trademark \u002F copyright \u002F patent \u002F trade secret]\n- **Jurisdiction:** [US federal — specific circuit \u002F state \u002F foreign]\n- **Legal framework applied:** [cite the governing test and statute]\n- **Statute of limitations \u002F laches posture:** [clock status]\n- **Exhibits \u002F evidence reviewed:** [list]\n\n## Factor analysis\n\n[Mode-specific factor table — confusion factors \u002F fair-use factors \u002F claim chart\n\u002F trade-secret elements. Each factor has a flag and a direction. This is\na flag list, not a verdict.]\n\n## Defenses and thresholds\n\n[Mode-specific: dilution fame threshold \u002F registration prerequisite \u002F\n§ 512 safe harbor \u002F invalidity \u002F inequitable conduct \u002F preemption \u002F\nreverse-engineering \u002F consent \u002F license \u002F laches \u002F statute of limitations.\nFlag each.]\n\n## What cuts which way — summary\n\n| Factor | Flag | Direction (senior \u002F accused \u002F mixed) |\n|---|---|---|\n| [factor 1] | [note] | [direction] |\n\n**Conclusion:** *This skill does not conclude.* Attorney judgment required\nbefore acting. The factors cutting [direction] are [brief summary]; the\nfactors cutting [direction] are [brief summary].\n\n## Recommended next steps\n\n- [formal opinion from counsel \u002F route to IP OC named in the practice profile]\n- [evidence preservation and hold — if a litigation clock is running]\n- [fact development needed before a decision — e.g., access logs, prosecution\n  history, market studies, survey evidence]\n- [routing per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`\n  `## Enforcement posture`, if the posture is to assert]\n\n## Citation verification\n\nEvery case, statute, registration number, claim quote, and exhibit cited here\nmust be verified against the authoritative source before relying on it.\nJurisdictional tests vary by circuit and change over time — confirm the\ncurrent controlling authority.\n```\n\n---\n\n## Non-lawyer gate\n\nBefore issuing the output, read `## Who's using this`. If the Role is Non-lawyer:\n\n> This output is a research triage, not legal advice. Sending a C&D, deciding\n> not to stop, filing suit, or relying on \"it's fair use\" based on this triage\n> alone has legal consequences — including Rule 11 sanctions for a baseless\n> assertion, declaratory-judgment exposure for a threatening letter, treble\n> damages on the patent side, and fee awards in unfair-competition cases.\n> An attorney needs to evaluate before you move.\n>\n> Here's a brief to bring to an attorney:\n>\n> [Generate a 1-page summary: the right at issue, the posture, the facts and\n> evidence, the factors surfaced, the defenses flagged, and the three\n> questions to ask the attorney.]\n>\n> If you need to find a licensed attorney, solicitor, barrister, or other authorised legal professional in your jurisdiction: your professional regulator's referral service is\n> the starting point (state bar in the US, SRA\u002FBar Standards Board in England & Wales, Law Society in Scotland\u002FNI\u002FIreland\u002FCanada\u002FAustralia, or your jurisdiction's equivalent). For patents in the US, the attorney must be registered before the\n> USPTO; for other jurisdictions, use the relevant patent office register. For trademarks, INTA maintains a directory of practitioners worldwide.\n\nDeliver the triage alongside the brief.\n\n---\n\n## Output location\n\nIf matter workspaces are enabled and a matter is active, write to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002Foutputs\u002Finfringe-\u003Cmode>-\u003Csubject-slug>-YYYY-MM-DD.md`.\nOtherwise write to\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Foutputs\u002Finfringe-\u003Cmode>-\u003Csubject-slug>-YYYY-MM-DD.md`\nand surface the path.\n\nAppend a one-line entry to the matter's `history.md` if a matter is active.\n\n---\n\n## Handoff to enforcement skills\n\nIf the triage output points toward an assertion and the practice profile's\nposture supports it, offer:\n\n> Want me to draft a cease-and-desist on this? Run `\u002Fip-legal:cease-desist`.\n> I'll use the flag list from this triage as the factual basis and apply the\n> approval chain from your practice profile — the letter won't go anywhere\n> without the approver signing off.\n\nOr, if the mode is copyright and the accused is hosted content:\n\n> Want me to prepare a DMCA takedown? Run `\u002Fip-legal:takedown`.\n\nDo not draft the letter automatically from the triage. The decision to assert\nis the approver's, not the triage's.\n\n---\n\n## Close with the next-steps decision tree\n\nEnd with the next-steps decision tree per CLAUDE.md `## Outputs`. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.\n\n## What this skill does not do\n\n- **Conclude infringement or non-infringement.** Ever. The loudest guardrail.\n- **Substitute for survey evidence, damages experts, or claim construction.**\n- **Evaluate jurisdiction-specific defenses outside the triage's jurisdiction\n  scope.** If the facts cross borders, flag that foreign-law analysis is\n  required.\n- **Decide fair use as a matter of law.** Fair use is fact-intensive and\n  reserved for the attorney and, ultimately, the court.\n- **Draft the C&D, takedown, or complaint.** Those are separate skills\n  (`\u002Fip-legal:cease-desist`, `\u002Fip-legal:takedown`) gated by the approval\n  chain in the practice profile.\n- **Quote outputs to counterparties.** Privileged if the header applies.\n\n---\n\n## Tone\n\nFactor-by-factor, flag-by-flag. No hedging prose. The guardrail at the top\ndoes the scope work; the analysis does the analysis. A lawyer should leave\nthe output knowing exactly which factors are flagged, which defenses apply,\nand what they need to do next to either assert or stand down.\n",{"name":5,"description":44,"argument-hint":45},"Infringement triage across trademark, copyright, patent, and trade secret — a flag list with the factors cutting each way, not a finding. Use when assessing whether someone is infringing your IP or whether you might be infringing theirs, when a knockoff or copycat surfaces, or when deciding whether a matter is worth pursuing and how.\n","[describe the facts and which right — or just the facts and I'll ask which right]","main","4a6c651889c97cc9140580363c73e0eb17379c2b","ip-legal\u002Fskills\u002Finfringement-triage",1968,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-14 23:30:58",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add anthropics\u002Fclaude-for-legal --skill infringement-triage",{"tool":60,"command":61},"bunx","bunx skills add anthropics\u002Fclaude-for-legal --skill infringement-triage",{"tool":63,"command":64},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-for-legal --skill infringement-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fip-legal\u002Fskills\u002Finfringement-triage\u002FSKILL.md",true,[],[69,99,121,138,158,171],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":80,"publishedAt":39},"01M718SG9G2R92ECCD0HYK2R5E","reg-feed-watcher","Check regulatory feeds now and report what's new since the last check, filtered by your materiality threshold. Use when the user says \"check the feeds\", \"what's new\", \"regulatory update\", when running from the scheduled agent, or when manually pasting a regulatory development for classification and diff.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Freg-feed-watcher\u002FSKILL.md",[75],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[81,82,83,84,85,86,87,88,89,90,91,92,25,93,36,94,95,96,97,98],"reg","watcher","reg feed watcher","running","feeds","filtered","diff","development","for","classification","new","now","scheduled","check","last","update","report","regulatory",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":39},"01M718SCRTBN55DMTVSPG67A7N","policy-redraft","Produce a proposed marked-up policy redraft that closes a gap found by \u002Fregulatory-legal:gaps or \u002Fregulatory-legal:policy-diff. A first draft for internal review — not for direct application to approved policy documents. Use when the user says \"redraft the policy\", \"draft the policy fix\", \"mark up the policy\", or when gap-surfacer hands off a gap for drafting.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fpolicy-redraft\u002FSKILL.md",[],[106,107,87,89,108,109,110,25,111,36,112,113,114,115,116,117,118,119,98,120],"policy","policy redraft","up","fix","produce","documents","drafting","gaps","review","draft","id","gap","mark","first","direct",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":39},"01M718S8RV0C4NMVKG078CBFXP","policy-diff","Diff a specific regulatory change against the indexed policy library. Use when a reg has changed and you need to know which policies it touches and what the gap is, when the user says \"diff this reg against our policies\", \"which policy does this affect\", or \"gap analysis\", or when reg-feed-watcher hands off a material item.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fpolicy-diff\u002FSKILL.md",[],[87,106,128,38,36,35,129,81,130,82,131,132,133,134,25,135,117,136,137,98],"policy diff","analysis","text","change","paste","library","material","gap analysis","what the","name",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":39},"01M718S6521Y0FT4T24VCFKVG5","matter-workspace","Manage matter workspaces — create, list, switch, close, or detach the active matter (practice-level). Use when working across multiple clients or matters and you need to keep one engagement's context separate from another, or when a substantive skill needs to know which matter it's working in.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fmatter-workspace\u002FSKILL.md",[],[145,146,38,147,148,149,91,25,36,35,150,33,151,152,153,154,155,30,156,157],"workspace","matter workspace","switch","manage","workspaces","keep","create","engagement","close","active","clients","it","context",{"skillNo":159,"name":113,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":39},"01M718S3FPEJNQGCMQ1AR8M4HE","Open gaps tracker — what's flagged and not yet closed. Use when the user asks \"what gaps are open\", \"gap tracker\", \"remediation status\", or wants to close (--close GAP-ID) or risk-accept (--accept GAP-ID) a tracked gap.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fgaps\u002FSKILL.md",[],[113,116,117,164,153,165,166,167,168,25,169,36,170],"risk","tracker","remediation","status","open","accept","user",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":182,"publishedAt":39},"01M718S06WSZ9Y24JKYM0VVPPE","gap-surfacer","Reference: shared gap- and comment-tracker framework backing \u002Fregulatory-legal:gaps and \u002Fregulatory-legal:comments. Tracks open policy gaps with remediation status, ingests gaps from policy-diff, surfaces what's open and aging, routes to owners, and notifies gap owners via Slack with per-send confirmation. Loaded by the gaps and comments skills before doing substantive work.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fregulatory-legal\u002Fskills\u002Fgap-surfacer\u002FSKILL.md",[177],{"categoryNo":178,"categoryName":179,"taxonomyType":180,"taxonomyTypeDesc":181},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[117,183,184,185,87,106,186,168,187,188,189,190,113,23,191,192,193,165,166,31],"gap surfacer","shared","tracks","send","confirmation","aging","false","comments","work","slack","via"]