[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718G52JXZFF4V3RHPERCRS2":3,"skill-same:01M718G52JXZFF4V3RHPERCRS2":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},"01M718G52JXZFF4V3RHPERCRS2","invention-intake",null,"Invention disclosure first-pass screen — novelty, obviousness, §101 eligibility, bar dates, detectability, and strategic value. Use when an invention disclosure comes in and needs triage on whether to pursue a prior-art search and patent counsel review, investigate further, or decline.","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\u002Finvention-intake\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"invention intake","invention","intake","screen","first","title","investigate","Counsel","review","ask","when","use","strategic","novelty","dates","Art","search","just","value","prior-art","2026-11-10 10:12:30",false,"---\nname: invention-intake\ndescription: >\n  Invention disclosure first-pass screen — novelty, obviousness, §101\n  eligibility, bar dates, detectability, and strategic value. Use when an\n  invention disclosure comes in and needs triage on whether to pursue a\n  prior-art search and patent counsel review, investigate further, or decline.\nargument-hint: \"[paste or describe the invention disclosure — or just the title and I'll ask]\"\n---\n\n# \u002Finvention-intake\n\n**This is a first-pass screen by a non-specialist, not a patentability\nopinion.** The screen never concludes that an invention is patentable — it\nconcludes that it passes the initial screen and warrants a prior-art search\nand registered-practitioner review, that it needs more information, or that\nit hits a disqualifier. A prior-art search is a separate step; this skill\ndoes not do one.\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`. If the\n   practice profile shows trademark- or copyright-only (no patent practice),\n   say so and route the user elsewhere — this is the wrong tool.\n2. Follow the workflow below.\n3. Run intake. If the user pasted or uploaded a disclosure, read it. If not,\n   ask the seven intake questions (what \u002F problem \u002F differences \u002F inventors \u002F\n   public disclosure \u002F status \u002F technology area) in one batch and wait.\n4. Run the six screens: novelty signals, obviousness flags, § 101 eligibility,\n   public disclosure \u002F bar dates, detectability, strategic value. Each screen\n   gets a ✓ \u002F 🟡 \u002F 🔴 verdict with one-line reasoning.\n5. Write the invention screen memo to the matter folder (if a matter is\n   active) or the practice outputs folder. Apply the work-product header per\n   role.\n6. Bottom-line verdict: **PURSUE** (schedule prior-art search and attorney\n   review) \u002F **INVESTIGATE** (needs more info on a specific open item) \u002F\n   **DECLINE** (state the concrete reason). Never say \"patentable.\"\n7. Close with the decision tree (prior-art search \u002F inventor follow-up \u002F\n   specialist review \u002F decline + thank-you \u002F trade-secret route) and the\n   non-lawyer gate if the role is non-lawyer.\n8. If the screen hit a within-one-year US disclosure or any public disclosure\n   with foreign rights in scope, flag at the top: **time-sensitive**.\n\nThis skill never concludes that an invention is patentable. If uncertain,\nflag — a registered patent attorney or agent decides.\n\n## Examples\n\n```\n\u002Fip-legal:invention-intake \"a new cache-eviction algorithm that uses a learned model rather than LRU; conceived Q1 this year, not yet disclosed, engineering prototype in internal staging\"\n```\n\n```\n\u002Fip-legal:invention-intake\n```\n\n(And the skill will ask for the invention, the problem it solves, how it\ndiffers, inventors, public disclosure status, usage status, and technology\narea.)\n\n---\n\n## THIS IS A FIRST-PASS SCREEN, NOT A PATENTABILITY OPINION\n\n**Say this at the top of every output. Do not drop it, do not soften it.**\n\n> **This is a first-pass screen by a non-specialist, not a patentability\n> opinion.** A patentability opinion requires a prior-art search, full claim\n> construction, and the judgment of a registered patent attorney or agent. This\n> screen does not do a prior-art search, does not assess what is in the art, and\n> does not construct claims. It screens for the obvious disqualifiers (the\n> invention is already on the market, it was publicly disclosed two years ago,\n> it is plainly an abstract idea) and the obvious go-aheads (new mechanism,\n> technical advance, recent conception, in-use secretly). Everything in between\n> needs a prior-art search and a registered practitioner's review. This screen\n> never concludes that something is \"patentable\" — it concludes that it \"passes\n> the initial screen, warrants investigation\" or that it does not.\n\nUnder-flagging an invention that should have been filed is a one-way door — the\none-year US bar runs, foreign rights are lost at first public disclosure, the\ncompetitor files first. Over-flagging just means a prior-art search that comes\nback empty. Stay on the two-way door side.\n\n---\n\n## Matter context\n\n**Matter context.** Check `## Matter workspaces` in the practice-level\nCLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest\nof this paragraph — skills use practice-level context and the matter machinery\nis invisible. If enabled and there is no active matter, ask: \"Which matter is\nthis for? Run `\u002Fip-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load\nthe active matter's `matter.md` for matter-specific context and overrides.\nWrite outputs to the matter folder at\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`.\nNever read another matter's files unless `Cross-matter context` is `on`.\n\nInvention disclosures are particularly common candidates for **clean-team** or\n**heightened** confidentiality at matter-open. Respect the matter's\nconfidentiality marking from `matter.md`. Invention content is inherently\nsensitive — do not summarize, quote, or reference it outside privileged\nchannels.\n\n---\n\n## Load the practice profile first\n\n**Before reading the disclosure, read\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`.** If it is\nmissing or still contains placeholders, stop and run `\u002Fip-legal:cold-start-interview`. The\npractice profile tells you:\n\n- The company's **patent filing strategy** — offensive (building an assertion\n  portfolio), defensive (filing to protect freedom to operate), hybrid, or\n  licensing-revenue. This determines the strategic-value bar.\n- The **technology areas of interest** — where the company files and where it\n  does not. An invention that falls outside the areas of interest is often a\n  decline even if the technical screen is clean.\n- The **filing budget posture** — aggressive (file everything that passes the\n  screen), selective (file the best few), or minimal (only what the business\n  needs to protect). This shapes the output's recommendation.\n- The **approval chain** — who signs off on a filing decision, and who the\n  invention gets routed to if it passes the screen.\n\nIf the practice profile shows trademark-only or copyright-only (no patent\npractice), this skill is the wrong tool — say so and route the user elsewhere.\n\n---\n\n## Workflow\n\n### Step 1: Intake the disclosure\n\nIf the user pastes or uploads a disclosure, read it. If not, ask — in one\nbatch, not one at a time:\n\n> To screen this, I need:\n>\n> 1. **What is the invention?** In plain language — what does it do, what makes\n>    it work, what is the key idea.\n> 2. **What problem does it solve?** What was broken or missing before.\n> 3. **How does it differ from what existed before?** What did people do\n>    previously? What does this do differently?\n> 4. **Who invented it, and when?** Names and rough conception date.\n> 5. **Has it been publicly disclosed?** Published, sold, offered for sale,\n>    demonstrated at a conference, shown to a customer under an NDA, posted to\n>    a public repo, written up in a paper, included in a product release note.\n>    If yes, when and where.\n> 6. **Is it in use or planned?** Shipping now? In a limited pilot? On the\n>    roadmap? Still on paper?\n> 7. **What technology area?** (Software, hardware, mechanical, biotech,\n>    method-of-doing-business, AI\u002FML, etc.)\n\nWait for answers. Do not proceed on a half-disclosure — a screen of \"a new\nmachine learning thing that helps users\" is worse than no screen.\n\nIf the disclosure is a formal invention disclosure form (IDF) from an IPMS or\na template, extract these fields from the form and only ask for what's missing.\n\n### Step 2: Screen against the checklist\n\nWalk the five screens in order. Each produces a per-screen verdict:\n`✓ clear`, `🟡 flagged — needs further look`, or `🔴 red flag`. Explain the\nreasoning briefly; do not pad.\n\n#### Screen 1: Novelty signals\n\nDoes the disclosure describe something new? This is not a full novelty\nanalysis — that requires a prior-art search. This screens the disclosure's own\ndescription for self-evident novelty problems.\n\n**Red flags (🔴):**\n- \"We just applied [known technique] to [new domain]\" — e.g., \"we took\n  gradient boosting and applied it to predicting customer churn\"\n- \"It's like [existing product] but for [X]\" — Uber-for-dog-walking framing\n- \"Competitors do something similar\" — if the disclosure itself says this,\n  novelty is in question\n- The disclosure describes a feature of an existing public product with minor\n  tuning\n\n**Green flags (✓):**\n- A new **mechanism** — a new way of doing the thing, not a new application\n- A new **combination** that produces an unexpected result (not just\n  additive — \"faster,\" \"smaller,\" \"cheaper\" are sometimes unexpected, sometimes\n  obvious)\n- Solving a problem the field **had not solved** — the disclosure explains why\n  the prior approaches failed and how this one doesn't\n\n**Flagged (🟡):** anything ambiguous. Prior-art search settles it.\n\n#### Screen 2: Obviousness flags\n\nWould a person of ordinary skill in the art (POSA) have arrived at this\ncombination based on what's known? This is a screen, not a § 103 analysis —\nflag for further investigation, never conclude obviousness or non-obviousness.\n\n**Red flags (🔴) for further investigation:**\n- Combining **known elements in a predictable way** — putting a known sensor\n  on a known machine to measure a known thing\n- **Routine optimization** — \"we tuned the existing parameter from X to Y and\n  got better results\"\n- **Design choice without functional advantage** — aesthetic, ergonomic, or\n  stylistic changes that don't change how the thing works\n- **Obvious to try** — one of a small number of identified solutions with a\n  reasonable expectation of success\n\n**Green flags (✓):**\n- Teaching away — prior art expected the opposite result or said this approach\n  wouldn't work\n- Unexpected result — the combination produces something the POSA would not\n  have predicted\n- Long-felt need — the problem was known, and attempts to solve it had failed\n\n#### Screen 3: Subject-matter eligibility (§ 101)\n\nIs this an abstract idea, law of nature, or natural phenomenon? This is the\nhardest screen, the most litigated, and the one most likely to require a\nspecialist read. Flag anything borderline for specialist review.\n\n**Red flags (🔴) for § 101:**\n- Pure **business method** without technical implementation — \"a method of\n  pricing widgets more efficiently\"\n- **Mathematical algorithm** on its own — even as dressed up in pseudocode\n- **Organizing human activity** — scheduling, pairing, matching, reviewing —\n  without a technical improvement\n- Claim that reads as \"**do [known thing] on a computer**\" with no\n  improvement to the computer itself\n- AI\u002FML invention where the claim is the **function** (recommend, classify,\n  predict) without the specific technical means that improves how the computer\n  performs the function\n\n**Green flags (✓) for software\u002FAI inventions:**\n- Technical improvement to the **computer itself** — new architecture, new\n  training technique, new hardware\u002Fsoftware interface, new security mechanism\n- Specific technical means, not just results\n- Improvement to a **technical field** (image processing, compression,\n  cryptography, robotics) with the technical means described\n\n**Anything borderline gets a 🟡 with \"§ 101 — route to specialist for\nAlice\u002FMayo analysis.\"** A non-specialist should not call a close § 101\nquestion.\n\nFor **biotech \u002F diagnostic** inventions, also flag for § 101 if the claim\nrecites:\n- A natural correlation (\"if level of X is above Y, patient has Z\")\n- A naturally occurring substance (isolated gene, natural product) without\n  significant human modification\n\n> **§101 is a US standard. Other patent offices are different.** The EPO's \"technical effect\" test (Art. 52 EPC) is materially more permissive for software and AI inventions than US §101 post-*Alice*. JPO and CNIPA also apply different standards. An invention that screens 🔴 under *Alice* may be perfectly eligible at EPO\u002FJPO\u002FCNIPA.\n>\n> When the practice profile includes non-US jurisdictions: \"This §101 screen is US-only. If you file internationally, the eligibility posture may be different — particularly for software, AI\u002FML, and business methods, which EPO is more permissive on. Don't decline based on US §101 alone if you have EP\u002FJP\u002FCN filing plans.\"\n\n#### Screen 4: Public disclosure \u002F bar dates\n\nHas the invention been disclosed, sold, offered for sale, or publicly used?\nThis is the most time-sensitive screen — the answer can kill patentability\nabsolutely, or start a clock that cannot be stopped.\n\nCategorize the disclosure status:\n\n**🔴 Likely barred:**\n- Publicly disclosed, sold, or offered for sale **more than 12 months ago**\n  in the US — 35 U.S.C. § 102(b) one-year grace period has run\n- **Any** public disclosure, anywhere, before filing — absolute novelty bar in\n  the EU, China, Japan, and most countries outside the US. If the business\n  cares about foreign rights, this is potentially fatal even if US is still\n  open.\n\n**🟡 Clock is running:**\n- Publicly disclosed within the last 12 months — US one-year clock is running,\n  foreign rights may already be lost. Urgent. Confirm the disclosure date and\n  route to filing immediately.\n\n**✓ Clear:**\n- No public disclosure. Confidential customer demonstrations under NDA, internal\n  use, beta releases to named parties under NDA, draft papers not yet submitted\n  — usually not \"public\" for § 102 purposes, but depends on the facts. When the\n  disclosure was to a customer or external party, even under NDA, flag the\n  specifics for the prosecution team to assess.\n\n**Ask specifically about:**\n- Papers submitted to journals or conferences (submission ≠ publication; but\n  check the journal's policy and whether preprints were posted)\n- Talks given at conferences, meetups, internal company events open to\n  non-employees\n- Posts to public repos, blogs, social media, or forums\n- Product releases, even in limited beta\n- Sales activity including quotes, RFP responses, and offers for sale\n- Disclosures to investors or board members who are not under NDA\n\nThe **on-sale bar** catches offers for sale of a product embodying the\ninvention, not just completed sales. An RFP response describing the invention\ncan trigger it.\n\n#### Screen 5: Detectability\n\nIf a competitor were to infringe this invention, could you tell? An invention\nthat's practiced in secret — server-side processing, back-office operations,\ninternal manufacturing techniques — may be better protected as a **trade\nsecret** than as a patent. Publishing a patent on an undetectable invention is\ngiving it to competitors in exchange for an asset you can never enforce.\n\n**🔴 Low detectability flags:**\n- Server-side algorithm with no observable output pattern\n- Internal manufacturing process (e.g., a novel etch step in a semiconductor\n  process)\n- Data-pipeline or analytics methodology that happens inside a competitor's\n  infrastructure\n- Training data composition or training technique for an ML model — visible\n  only through fine-grained probing, if at all\n\nFor these, flag for the **patent-vs-trade-secret decision**. The question is\nnot \"is this patentable\" but \"should we patent it if we could.\" Route to\nwhoever in the practice profile owns trade-secret classification decisions.\n\n**✓ High detectability:**\n- Consumer product — visible in the product\n- Published API, SDK, protocol — visible in network traffic or integration\n  docs\n- Physical mechanism in a distributed product — reverse-engineerable\n- Compiled code with distinctive signatures in a distributed binary\n\n#### Screen 6: Strategic value\n\nDoes this align with the company's patent strategy from the practice profile?\nThis is where the screen becomes company-specific rather than doctrinal.\n\nCheck against the profile:\n\n- **Offensive strategy (build to assert):** is this asset assert-worthy? A\n  narrow, easily designed-around patent has lower offensive value than a broad\n  mechanism claim. Is the competitive landscape one where you would want to\n  sue?\n- **Defensive strategy (build to protect FTO):** does this cover a technology\n  area where competitors are filing? A defensive filing in an area nobody\n  files in is a wasted spend.\n- **Licensing \u002F revenue strategy:** is this licensable? Who would pay for it,\n  and under what circumstances?\n\nAlso check:\n\n- Is this **core** technology (part of the product's differentiation) or\n  **peripheral** (incidental to a side feature)? Core is worth more.\n- What is the **competitive landscape**? Patent-heavy (semiconductors,\n  pharmaceuticals) — file early or lose the race. Patent-light (many\n  open-source-heavy software segments) — sometimes skip entirely and spend\n  the money elsewhere.\n- Is the technology area on the company's list of **tech areas of interest**\n  from the practice profile? If not, it is often a decline regardless of\n  doctrine.\n\n### Step 3: Assemble the invention screen memo\n\nFormat:\n\n> **Invention screen memo — [invention title]**\n>\n> **Bottom line: [PURSUE \u002F INVESTIGATE \u002F DECLINE]**\n>\n> *[One sentence — the reason in plain language.]*\n>\n> ---\n>\n> ### Screen results\n>\n> | Screen | Verdict | Notes |\n> |---|---|---|\n> | Novelty signals | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | Obviousness flags | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | § 101 eligibility | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | Public disclosure \u002F bar dates | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning + dates] |\n> | Detectability | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | Strategic value | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning, referenced to profile] |\n>\n> ---\n>\n> ### Open questions\n>\n> *Things that would change the answer. The inventor, the prosecution team, or\n> a specialist would need to address these before this screen converts to a\n> filing decision.*\n>\n> - [question]\n> - [question]\n>\n> ### Next steps (decision tree)\n>\n> Pick one and I'll help you build it out:\n>\n> 1. **Commission the prior-art search** — I'll draft the search request for\n>    [outside counsel \u002F search vendor] with the claim concepts, inventors,\n>    technology classification, and any known references.\n> 2. **Go back to the inventor for more facts** — I'll draft the follow-up\n>    questions on [specific open items above].\n> 3. **Route to outside counsel for § 101 \u002F patent-vs-trade-secret judgment** —\n>    I'll draft a transmittal summarizing what the screen found and what\n>    specialist judgment is needed.\n> 4. **Decline and send the standard thank-you** — I'll draft the inventor\n>    thank-you and archive the disclosure with the declination reason.\n> 5. **Flag for trade secret instead** — I'll draft a note to whoever owns\n>    trade-secret classification explaining why a trade-secret approach is a\n>    better fit.\n\nApply the work-product header per role. Apply the reviewer note. Keep the\ndeliverable clean of internal narration (\"I'm using the invention-intake\nskill...\" etc.).\n\n### Step 4: Recommend the bottom-line verdict\n\nThe bottom line is one of three:\n\n- **PURSUE** — enough screens are clear (or clearly fixable) to warrant a\n  prior-art search and attorney review. This is NOT \"patentable\" — it is\n  \"passes the initial screen, investigation warranted.\"\n- **INVESTIGATE** — one or more screens flagged something that needs more\n  information, specialist review, or a clarifying question back to the\n  inventor before a pursue\u002Fdecline decision can be made. Name the specific\n  open item.\n- **DECLINE** — a screen hit a fatal flag (barred by disclosure over 12\n  months old with no foreign rights concern, plainly obvious, plainly abstract\n  under Alice, outside the company's technology areas of interest, fundamentally\n  undetectable with no trade-secret path). State the reason clearly.\n\nA DECLINE should always be backed by a concrete reason the inventor can\nunderstand. \"Not patentable\" is not an acceptable decline reason; \"barred by\nyour paper at NeurIPS 2023 — the US one-year bar ran in December 2024\" is.\n\n## Guardrails\n\n**Never say \"patentable.\"** The closest you can come is \"passes the initial\nscreen, warrants further investigation.\" Patentability is a conclusion a\nregistered practitioner reaches after a prior-art search and claim\nconstruction.\n\n**Never do a prior-art search in this skill.** A WebSearch for \"does this\nalready exist\" is not a prior-art search — it's a credibility check the\nuser can also run. If you want to sanity-check novelty, say so explicitly\n(\"quick web check — the technique was discussed in [X] — this is not a prior-\nart search, it's context for the screen\") and flag it as `[web — verify]`.\n\n**Defer on § 101 calls.** For anything borderline under Alice\u002FMayo, flag for\nspecialist review. § 101 is where practitioners routinely disagree and where\na non-specialist's confident call ages badly.\n\n**Flag detectability before strategic value.** An undetectable invention that\nwould be \"high strategic value\" as a patent is usually higher strategic value\nas a trade secret. Do not recommend PURSUE on an undetectable invention\nwithout addressing the trade-secret alternative.\n\n**Urgent cases get urgent flagging.** If the screen hits a within-one-year\npublic disclosure in the US, or any public disclosure with foreign rights in\nscope, say so at the top of the memo. Bottom line, then: \"**Time-sensitive —\nUS bar runs [date], foreign rights already at risk.**\" This is the kind of\nfinding a lawyer needs to see in the first three seconds.\n\n**Respect the routing.** Per the practice profile, this screen is a triage\nstep. The person who decides what to file is the attorney or agent responsible\nfor patent prosecution. The screen feeds that person; it does not replace them.\n\n## Non-lawyer gate\n\nIf the role is **non-lawyer** (with or without attorney access), close the\nmemo with:\n\n> **This is a screening tool for your disclosure, not a patentability opinion.\n> The decision about whether to file — and how — belongs to a registered\n> patent attorney or agent. If this screen says PURSUE or INVESTIGATE, your\n> next step is not to file or draft claims; it is to share this memo (and the\n> underlying disclosure) with patent counsel. If there is no counsel engaged\n> yet, [contact from profile \u002F \"your professional regulator's IP referral service — 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\"] is the\n> starting point.**\n","# \u002Finvention-intake\n\n**This is a first-pass screen by a non-specialist, not a patentability\nopinion.** The screen never concludes that an invention is patentable — it\nconcludes that it passes the initial screen and warrants a prior-art search\nand registered-practitioner review, that it needs more information, or that\nit hits a disqualifier. A prior-art search is a separate step; this skill\ndoes not do one.\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`. If the\n   practice profile shows trademark- or copyright-only (no patent practice),\n   say so and route the user elsewhere — this is the wrong tool.\n2. Follow the workflow below.\n3. Run intake. If the user pasted or uploaded a disclosure, read it. If not,\n   ask the seven intake questions (what \u002F problem \u002F differences \u002F inventors \u002F\n   public disclosure \u002F status \u002F technology area) in one batch and wait.\n4. Run the six screens: novelty signals, obviousness flags, § 101 eligibility,\n   public disclosure \u002F bar dates, detectability, strategic value. Each screen\n   gets a ✓ \u002F 🟡 \u002F 🔴 verdict with one-line reasoning.\n5. Write the invention screen memo to the matter folder (if a matter is\n   active) or the practice outputs folder. Apply the work-product header per\n   role.\n6. Bottom-line verdict: **PURSUE** (schedule prior-art search and attorney\n   review) \u002F **INVESTIGATE** (needs more info on a specific open item) \u002F\n   **DECLINE** (state the concrete reason). Never say \"patentable.\"\n7. Close with the decision tree (prior-art search \u002F inventor follow-up \u002F\n   specialist review \u002F decline + thank-you \u002F trade-secret route) and the\n   non-lawyer gate if the role is non-lawyer.\n8. If the screen hit a within-one-year US disclosure or any public disclosure\n   with foreign rights in scope, flag at the top: **time-sensitive**.\n\nThis skill never concludes that an invention is patentable. If uncertain,\nflag — a registered patent attorney or agent decides.\n\n## Examples\n\n```\n\u002Fip-legal:invention-intake \"a new cache-eviction algorithm that uses a learned model rather than LRU; conceived Q1 this year, not yet disclosed, engineering prototype in internal staging\"\n```\n\n```\n\u002Fip-legal:invention-intake\n```\n\n(And the skill will ask for the invention, the problem it solves, how it\ndiffers, inventors, public disclosure status, usage status, and technology\narea.)\n\n---\n\n## THIS IS A FIRST-PASS SCREEN, NOT A PATENTABILITY OPINION\n\n**Say this at the top of every output. Do not drop it, do not soften it.**\n\n> **This is a first-pass screen by a non-specialist, not a patentability\n> opinion.** A patentability opinion requires a prior-art search, full claim\n> construction, and the judgment of a registered patent attorney or agent. This\n> screen does not do a prior-art search, does not assess what is in the art, and\n> does not construct claims. It screens for the obvious disqualifiers (the\n> invention is already on the market, it was publicly disclosed two years ago,\n> it is plainly an abstract idea) and the obvious go-aheads (new mechanism,\n> technical advance, recent conception, in-use secretly). Everything in between\n> needs a prior-art search and a registered practitioner's review. This screen\n> never concludes that something is \"patentable\" — it concludes that it \"passes\n> the initial screen, warrants investigation\" or that it does not.\n\nUnder-flagging an invention that should have been filed is a one-way door — the\none-year US bar runs, foreign rights are lost at first public disclosure, the\ncompetitor files first. Over-flagging just means a prior-art search that comes\nback empty. Stay on the two-way door side.\n\n---\n\n## Matter context\n\n**Matter context.** Check `## Matter workspaces` in the practice-level\nCLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest\nof this paragraph — skills use practice-level context and the matter machinery\nis invisible. If enabled and there is no active matter, ask: \"Which matter is\nthis for? Run `\u002Fip-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load\nthe active matter's `matter.md` for matter-specific context and overrides.\nWrite outputs to the matter folder at\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`.\nNever read another matter's files unless `Cross-matter context` is `on`.\n\nInvention disclosures are particularly common candidates for **clean-team** or\n**heightened** confidentiality at matter-open. Respect the matter's\nconfidentiality marking from `matter.md`. Invention content is inherently\nsensitive — do not summarize, quote, or reference it outside privileged\nchannels.\n\n---\n\n## Load the practice profile first\n\n**Before reading the disclosure, read\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fip-legal\u002FCLAUDE.md`.** If it is\nmissing or still contains placeholders, stop and run `\u002Fip-legal:cold-start-interview`. The\npractice profile tells you:\n\n- The company's **patent filing strategy** — offensive (building an assertion\n  portfolio), defensive (filing to protect freedom to operate), hybrid, or\n  licensing-revenue. This determines the strategic-value bar.\n- The **technology areas of interest** — where the company files and where it\n  does not. An invention that falls outside the areas of interest is often a\n  decline even if the technical screen is clean.\n- The **filing budget posture** — aggressive (file everything that passes the\n  screen), selective (file the best few), or minimal (only what the business\n  needs to protect). This shapes the output's recommendation.\n- The **approval chain** — who signs off on a filing decision, and who the\n  invention gets routed to if it passes the screen.\n\nIf the practice profile shows trademark-only or copyright-only (no patent\npractice), this skill is the wrong tool — say so and route the user elsewhere.\n\n---\n\n## Workflow\n\n### Step 1: Intake the disclosure\n\nIf the user pastes or uploads a disclosure, read it. If not, ask — in one\nbatch, not one at a time:\n\n> To screen this, I need:\n>\n> 1. **What is the invention?** In plain language — what does it do, what makes\n>    it work, what is the key idea.\n> 2. **What problem does it solve?** What was broken or missing before.\n> 3. **How does it differ from what existed before?** What did people do\n>    previously? What does this do differently?\n> 4. **Who invented it, and when?** Names and rough conception date.\n> 5. **Has it been publicly disclosed?** Published, sold, offered for sale,\n>    demonstrated at a conference, shown to a customer under an NDA, posted to\n>    a public repo, written up in a paper, included in a product release note.\n>    If yes, when and where.\n> 6. **Is it in use or planned?** Shipping now? In a limited pilot? On the\n>    roadmap? Still on paper?\n> 7. **What technology area?** (Software, hardware, mechanical, biotech,\n>    method-of-doing-business, AI\u002FML, etc.)\n\nWait for answers. Do not proceed on a half-disclosure — a screen of \"a new\nmachine learning thing that helps users\" is worse than no screen.\n\nIf the disclosure is a formal invention disclosure form (IDF) from an IPMS or\na template, extract these fields from the form and only ask for what's missing.\n\n### Step 2: Screen against the checklist\n\nWalk the five screens in order. Each produces a per-screen verdict:\n`✓ clear`, `🟡 flagged — needs further look`, or `🔴 red flag`. Explain the\nreasoning briefly; do not pad.\n\n#### Screen 1: Novelty signals\n\nDoes the disclosure describe something new? This is not a full novelty\nanalysis — that requires a prior-art search. This screens the disclosure's own\ndescription for self-evident novelty problems.\n\n**Red flags (🔴):**\n- \"We just applied [known technique] to [new domain]\" — e.g., \"we took\n  gradient boosting and applied it to predicting customer churn\"\n- \"It's like [existing product] but for [X]\" — Uber-for-dog-walking framing\n- \"Competitors do something similar\" — if the disclosure itself says this,\n  novelty is in question\n- The disclosure describes a feature of an existing public product with minor\n  tuning\n\n**Green flags (✓):**\n- A new **mechanism** — a new way of doing the thing, not a new application\n- A new **combination** that produces an unexpected result (not just\n  additive — \"faster,\" \"smaller,\" \"cheaper\" are sometimes unexpected, sometimes\n  obvious)\n- Solving a problem the field **had not solved** — the disclosure explains why\n  the prior approaches failed and how this one doesn't\n\n**Flagged (🟡):** anything ambiguous. Prior-art search settles it.\n\n#### Screen 2: Obviousness flags\n\nWould a person of ordinary skill in the art (POSA) have arrived at this\ncombination based on what's known? This is a screen, not a § 103 analysis —\nflag for further investigation, never conclude obviousness or non-obviousness.\n\n**Red flags (🔴) for further investigation:**\n- Combining **known elements in a predictable way** — putting a known sensor\n  on a known machine to measure a known thing\n- **Routine optimization** — \"we tuned the existing parameter from X to Y and\n  got better results\"\n- **Design choice without functional advantage** — aesthetic, ergonomic, or\n  stylistic changes that don't change how the thing works\n- **Obvious to try** — one of a small number of identified solutions with a\n  reasonable expectation of success\n\n**Green flags (✓):**\n- Teaching away — prior art expected the opposite result or said this approach\n  wouldn't work\n- Unexpected result — the combination produces something the POSA would not\n  have predicted\n- Long-felt need — the problem was known, and attempts to solve it had failed\n\n#### Screen 3: Subject-matter eligibility (§ 101)\n\nIs this an abstract idea, law of nature, or natural phenomenon? This is the\nhardest screen, the most litigated, and the one most likely to require a\nspecialist read. Flag anything borderline for specialist review.\n\n**Red flags (🔴) for § 101:**\n- Pure **business method** without technical implementation — \"a method of\n  pricing widgets more efficiently\"\n- **Mathematical algorithm** on its own — even as dressed up in pseudocode\n- **Organizing human activity** — scheduling, pairing, matching, reviewing —\n  without a technical improvement\n- Claim that reads as \"**do [known thing] on a computer**\" with no\n  improvement to the computer itself\n- AI\u002FML invention where the claim is the **function** (recommend, classify,\n  predict) without the specific technical means that improves how the computer\n  performs the function\n\n**Green flags (✓) for software\u002FAI inventions:**\n- Technical improvement to the **computer itself** — new architecture, new\n  training technique, new hardware\u002Fsoftware interface, new security mechanism\n- Specific technical means, not just results\n- Improvement to a **technical field** (image processing, compression,\n  cryptography, robotics) with the technical means described\n\n**Anything borderline gets a 🟡 with \"§ 101 — route to specialist for\nAlice\u002FMayo analysis.\"** A non-specialist should not call a close § 101\nquestion.\n\nFor **biotech \u002F diagnostic** inventions, also flag for § 101 if the claim\nrecites:\n- A natural correlation (\"if level of X is above Y, patient has Z\")\n- A naturally occurring substance (isolated gene, natural product) without\n  significant human modification\n\n> **§101 is a US standard. Other patent offices are different.** The EPO's \"technical effect\" test (Art. 52 EPC) is materially more permissive for software and AI inventions than US §101 post-*Alice*. JPO and CNIPA also apply different standards. An invention that screens 🔴 under *Alice* may be perfectly eligible at EPO\u002FJPO\u002FCNIPA.\n>\n> When the practice profile includes non-US jurisdictions: \"This §101 screen is US-only. If you file internationally, the eligibility posture may be different — particularly for software, AI\u002FML, and business methods, which EPO is more permissive on. Don't decline based on US §101 alone if you have EP\u002FJP\u002FCN filing plans.\"\n\n#### Screen 4: Public disclosure \u002F bar dates\n\nHas the invention been disclosed, sold, offered for sale, or publicly used?\nThis is the most time-sensitive screen — the answer can kill patentability\nabsolutely, or start a clock that cannot be stopped.\n\nCategorize the disclosure status:\n\n**🔴 Likely barred:**\n- Publicly disclosed, sold, or offered for sale **more than 12 months ago**\n  in the US — 35 U.S.C. § 102(b) one-year grace period has run\n- **Any** public disclosure, anywhere, before filing — absolute novelty bar in\n  the EU, China, Japan, and most countries outside the US. If the business\n  cares about foreign rights, this is potentially fatal even if US is still\n  open.\n\n**🟡 Clock is running:**\n- Publicly disclosed within the last 12 months — US one-year clock is running,\n  foreign rights may already be lost. Urgent. Confirm the disclosure date and\n  route to filing immediately.\n\n**✓ Clear:**\n- No public disclosure. Confidential customer demonstrations under NDA, internal\n  use, beta releases to named parties under NDA, draft papers not yet submitted\n  — usually not \"public\" for § 102 purposes, but depends on the facts. When the\n  disclosure was to a customer or external party, even under NDA, flag the\n  specifics for the prosecution team to assess.\n\n**Ask specifically about:**\n- Papers submitted to journals or conferences (submission ≠ publication; but\n  check the journal's policy and whether preprints were posted)\n- Talks given at conferences, meetups, internal company events open to\n  non-employees\n- Posts to public repos, blogs, social media, or forums\n- Product releases, even in limited beta\n- Sales activity including quotes, RFP responses, and offers for sale\n- Disclosures to investors or board members who are not under NDA\n\nThe **on-sale bar** catches offers for sale of a product embodying the\ninvention, not just completed sales. An RFP response describing the invention\ncan trigger it.\n\n#### Screen 5: Detectability\n\nIf a competitor were to infringe this invention, could you tell? An invention\nthat's practiced in secret — server-side processing, back-office operations,\ninternal manufacturing techniques — may be better protected as a **trade\nsecret** than as a patent. Publishing a patent on an undetectable invention is\ngiving it to competitors in exchange for an asset you can never enforce.\n\n**🔴 Low detectability flags:**\n- Server-side algorithm with no observable output pattern\n- Internal manufacturing process (e.g., a novel etch step in a semiconductor\n  process)\n- Data-pipeline or analytics methodology that happens inside a competitor's\n  infrastructure\n- Training data composition or training technique for an ML model — visible\n  only through fine-grained probing, if at all\n\nFor these, flag for the **patent-vs-trade-secret decision**. The question is\nnot \"is this patentable\" but \"should we patent it if we could.\" Route to\nwhoever in the practice profile owns trade-secret classification decisions.\n\n**✓ High detectability:**\n- Consumer product — visible in the product\n- Published API, SDK, protocol — visible in network traffic or integration\n  docs\n- Physical mechanism in a distributed product — reverse-engineerable\n- Compiled code with distinctive signatures in a distributed binary\n\n#### Screen 6: Strategic value\n\nDoes this align with the company's patent strategy from the practice profile?\nThis is where the screen becomes company-specific rather than doctrinal.\n\nCheck against the profile:\n\n- **Offensive strategy (build to assert):** is this asset assert-worthy? A\n  narrow, easily designed-around patent has lower offensive value than a broad\n  mechanism claim. Is the competitive landscape one where you would want to\n  sue?\n- **Defensive strategy (build to protect FTO):** does this cover a technology\n  area where competitors are filing? A defensive filing in an area nobody\n  files in is a wasted spend.\n- **Licensing \u002F revenue strategy:** is this licensable? Who would pay for it,\n  and under what circumstances?\n\nAlso check:\n\n- Is this **core** technology (part of the product's differentiation) or\n  **peripheral** (incidental to a side feature)? Core is worth more.\n- What is the **competitive landscape**? Patent-heavy (semiconductors,\n  pharmaceuticals) — file early or lose the race. Patent-light (many\n  open-source-heavy software segments) — sometimes skip entirely and spend\n  the money elsewhere.\n- Is the technology area on the company's list of **tech areas of interest**\n  from the practice profile? If not, it is often a decline regardless of\n  doctrine.\n\n### Step 3: Assemble the invention screen memo\n\nFormat:\n\n> **Invention screen memo — [invention title]**\n>\n> **Bottom line: [PURSUE \u002F INVESTIGATE \u002F DECLINE]**\n>\n> *[One sentence — the reason in plain language.]*\n>\n> ---\n>\n> ### Screen results\n>\n> | Screen | Verdict | Notes |\n> |---|---|---|\n> | Novelty signals | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | Obviousness flags | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | § 101 eligibility | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | Public disclosure \u002F bar dates | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning + dates] |\n> | Detectability | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning] |\n> | Strategic value | [✓ \u002F 🟡 \u002F 🔴] | [one-line reasoning, referenced to profile] |\n>\n> ---\n>\n> ### Open questions\n>\n> *Things that would change the answer. The inventor, the prosecution team, or\n> a specialist would need to address these before this screen converts to a\n> filing decision.*\n>\n> - [question]\n> - [question]\n>\n> ### Next steps (decision tree)\n>\n> Pick one and I'll help you build it out:\n>\n> 1. **Commission the prior-art search** — I'll draft the search request for\n>    [outside counsel \u002F search vendor] with the claim concepts, inventors,\n>    technology classification, and any known references.\n> 2. **Go back to the inventor for more facts** — I'll draft the follow-up\n>    questions on [specific open items above].\n> 3. **Route to outside counsel for § 101 \u002F patent-vs-trade-secret judgment** —\n>    I'll draft a transmittal summarizing what the screen found and what\n>    specialist judgment is needed.\n> 4. **Decline and send the standard thank-you** — I'll draft the inventor\n>    thank-you and archive the disclosure with the declination reason.\n> 5. **Flag for trade secret instead** — I'll draft a note to whoever owns\n>    trade-secret classification explaining why a trade-secret approach is a\n>    better fit.\n\nApply the work-product header per role. Apply the reviewer note. Keep the\ndeliverable clean of internal narration (\"I'm using the invention-intake\nskill...\" etc.).\n\n### Step 4: Recommend the bottom-line verdict\n\nThe bottom line is one of three:\n\n- **PURSUE** — enough screens are clear (or clearly fixable) to warrant a\n  prior-art search and attorney review. This is NOT \"patentable\" — it is\n  \"passes the initial screen, investigation warranted.\"\n- **INVESTIGATE** — one or more screens flagged something that needs more\n  information, specialist review, or a clarifying question back to the\n  inventor before a pursue\u002Fdecline decision can be made. Name the specific\n  open item.\n- **DECLINE** — a screen hit a fatal flag (barred by disclosure over 12\n  months old with no foreign rights concern, plainly obvious, plainly abstract\n  under Alice, outside the company's technology areas of interest, fundamentally\n  undetectable with no trade-secret path). State the reason clearly.\n\nA DECLINE should always be backed by a concrete reason the inventor can\nunderstand. \"Not patentable\" is not an acceptable decline reason; \"barred by\nyour paper at NeurIPS 2023 — the US one-year bar ran in December 2024\" is.\n\n## Guardrails\n\n**Never say \"patentable.\"** The closest you can come is \"passes the initial\nscreen, warrants further investigation.\" Patentability is a conclusion a\nregistered practitioner reaches after a prior-art search and claim\nconstruction.\n\n**Never do a prior-art search in this skill.** A WebSearch for \"does this\nalready exist\" is not a prior-art search — it's a credibility check the\nuser can also run. If you want to sanity-check novelty, say so explicitly\n(\"quick web check — the technique was discussed in [X] — this is not a prior-\nart search, it's context for the screen\") and flag it as `[web — verify]`.\n\n**Defer on § 101 calls.** For anything borderline under Alice\u002FMayo, flag for\nspecialist review. § 101 is where practitioners routinely disagree and where\na non-specialist's confident call ages badly.\n\n**Flag detectability before strategic value.** An undetectable invention that\nwould be \"high strategic value\" as a patent is usually higher strategic value\nas a trade secret. Do not recommend PURSUE on an undetectable invention\nwithout addressing the trade-secret alternative.\n\n**Urgent cases get urgent flagging.** If the screen hits a within-one-year\npublic disclosure in the US, or any public disclosure with foreign rights in\nscope, say so at the top of the memo. Bottom line, then: \"**Time-sensitive —\nUS bar runs [date], foreign rights already at risk.**\" This is the kind of\nfinding a lawyer needs to see in the first three seconds.\n\n**Respect the routing.** Per the practice profile, this screen is a triage\nstep. The person who decides what to file is the attorney or agent responsible\nfor patent prosecution. The screen feeds that person; it does not replace them.\n\n## Non-lawyer gate\n\nIf the role is **non-lawyer** (with or without attorney access), close the\nmemo with:\n\n> **This is a screening tool for your disclosure, not a patentability opinion.\n> The decision about whether to file — and how — belongs to a registered\n> patent attorney or agent. If this screen says PURSUE or INVESTIGATE, your\n> next step is not to file or draft claims; it is to share this memo (and the\n> underlying disclosure) with patent counsel. If there is no counsel engaged\n> yet, [contact from profile \u002F \"your professional regulator's IP referral service — 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\"] is the\n> starting point.**\n",{"name":5,"description":44,"argument-hint":45},"Invention disclosure first-pass screen — novelty, obviousness, §101 eligibility, bar dates, detectability, and strategic value. Use when an invention disclosure comes in and needs triage on whether to pursue a prior-art search and patent counsel review, investigate further, or decline.\n","[paste or describe the invention disclosure — or just the title and I'll ask]","main","4a6c651889c97cc9140580363c73e0eb17379c2b","ip-legal\u002Fskills\u002Finvention-intake",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 invention-intake",{"tool":60,"command":61},"bunx","bunx skills add anthropics\u002Fclaude-for-legal --skill invention-intake",{"tool":63,"command":64},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-for-legal --skill invention-intake","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Fip-legal\u002Fskills\u002Finvention-intake\u002FSKILL.md",true,[],[69,99,119,138,160,173],{"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",[81,82,83,84,85,86,87,88,89,90,91,92,30,93,29,94,95,96,97,98],"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",[],[106,107,87,89,108,109,110,30,111,29,112,113,27,114,115,116,117,23,98,118],"policy","policy redraft","up","fix","produce","documents","drafting","gaps","draft","id","gap","mark","direct",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[87,106,126,127,29,128,129,81,130,82,131,132,133,134,30,135,116,136,137,98],"policy diff","which","you","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",[],[145,146,127,147,148,149,91,30,29,128,150,151,152,153,154,155,156,157,158,159],"workspace","matter workspace","switch","manage","workspaces","keep","across","create","engagement","close","active","clients","list","it","context",{"skillNo":161,"name":113,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"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",[],[113,115,116,166,154,167,168,169,170,30,171,29,172],"risk","tracker","remediation","status","open","accept","user",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":184,"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",[179],{"categoryNo":180,"categoryName":181,"taxonomyType":182,"taxonomyTypeDesc":183},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[116,185,186,187,87,106,188,170,189,190,191,192,113,193,194,195,196,167,168,197],"gap surfacer","shared","tracks","send","confirmation","aging","false","comments","with","work","slack","via","surfaces"]