[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718F40B1GT9HDDHFPRW8R5T":3,"skill-same:01M718F40B1GT9HDDHFPRW8R5T":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},"01M718F40B1GT9HDDHFPRW8R5T","wage-hour-qa",null,"Jurisdiction-aware wage\u002Fhour and employment Q&A — classification, overtime, meal\u002Frest breaks, leave, final pay — answered for the specific state\u002Fcountry with the controlling rule researched and cited rather than stated from memory. Use when the user asks any employment law question, or says \"what's the rule in [state]\", \"is this exempt\", \"do we have to pay overtime for\", or \"can we classify this as\".","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\u002Femployment-legal\u002Fskills\u002Fwage-hour-qa\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"wage hour qa","qa","user","rule","q&a","classify","REST","state","with","can","when","pay","use","question","classification","employment","for","memory","do","as","2026-11-10 10:12:30",false,"---\nname: wage-hour-qa\ndescription: >\n  Jurisdiction-aware wage\u002Fhour and employment Q&A — classification, overtime,\n  meal\u002Frest breaks, leave, final pay — answered for the specific state\u002Fcountry\n  with the controlling rule researched and cited rather than stated from\n  memory. Use when the user asks any employment law question, or says \"what's\n  the rule in [state]\", \"is this exempt\", \"do we have to pay overtime for\",\n  or \"can we classify this as\".\nargument-hint: \"[question]\"\n---\n\n# \u002Fwage-hour-qa\n\n1. Load `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Femployment-legal\u002FCLAUDE.md` → jurisdictional footprint.\n2. Use the workflow below.\n3. Identify jurisdiction the question is about. If not specified, ask.\n4. Answer per that jurisdiction's rule. Cite. Flag if it's a close call or law is shifting.\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 `\u002Femployment-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\u002Femployment-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Purpose\n\n\"It depends\" is true but unhelpful. This skill produces a jurisdiction-specific\nanswer grounded in researched, cited primary sources — and flags when the\nquestion is close enough to need human judgment. It does not state rules from\nmemory: wage-and-hour thresholds, exemption criteria, and final-pay timing\nchange frequently and vary meaningfully by state.\n\n## Load context\n\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Femployment-legal\u002FCLAUDE.md` → jurisdictional footprint. If the question doesn't specify a\njurisdiction, ask — or answer for the state with the most employees and note\nthat.\n\n## The answer\n\n### Step 1: Jurisdiction\n\nWhich state\u002Fcountry is this about? If not stated:\n- If it's about a specific employee: where do they work?\n- If it's a policy question: identify the jurisdictions in the footprint that\n  are most likely to be the most restrictive on the question at hand, then\n  research those.\n\n### Step 2: Research the rule, then state it\n\n> **Research before answering.** For the jurisdiction and question, identify\n> the currently operative rule. Cite the controlling primary source (statute,\n> regulation, wage order, or case) with a pinpoint cite. Note the effective\n> date and whether the rule has been recently amended, indexed, or is in\n> litigation. If you are uncertain or cannot verify the current state of the\n> law, say so and flag for attorney verification — do not state a rule you\n> haven't confirmed.\n\nState the rule in one paragraph, tied to the cite. Use your tools (web search,\nlegal research integrations, team reference materials) to verify currency —\nespecially for:\n\n> **No silent supplement.** If a research query to the configured legal research tool (Westlaw, CourtListener, or firm platform) returns few or no results for the jurisdiction-and-question, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: \"The search returned [N] results from [tool]. Coverage appears thin for [jurisdiction \u002F question]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged `[web search — verify]` and should be checked against a primary source before relying, or (4) flag the question as unverified and stop here. Which would you like?\" A lawyer decides whether to accept lower-confidence sources.\n>\n> **Source attribution.** Tag every citation in the answer with where it came from: `[Westlaw]`, `[CourtListener]`, or the MCP tool name for citations retrieved from a legal research connector; `[web search — verify]` for web-search citations; `[model knowledge — verify]` for citations recalled from training data; `[user provided]` for citations the user supplied. Citations tagged `verify` carry higher fabrication risk and should be checked first. Never strip or collapse the tags.\n\n\n- Salary thresholds for any exemption (federal and state — several states\n  index annually and several have tiered thresholds by employer size).\n- Final-pay timing on termination vs. resignation (many states differ).\n- PTO payout requirements (jurisdiction-specific; some require, some leave\n  it to policy, some depend on accrual-plan design).\n- Meal and rest break rules and any penalty-pay consequence.\n- Daily or weekly overtime rules (some states have daily overtime and\n  double-time rules that federal law does not).\n- Classification tests — see the worker-classification skill; the applicable\n  test depends on jurisdiction and purpose.\n\nCommon question types you may be asked — for each, the answer is\njurisdiction-specific and time-sensitive. Do not state the rule here; route\nto research:\n\n- \"Is this role exempt?\" — Research the applicable federal and state salary\n  thresholds (verify current amounts and any employer-size tiers) and the\n  applicable duties test(s).\n- \"Do we have to pay overtime for X?\" — Research federal FLSA overtime plus\n  any state-specific overtime rules (daily OT, double-time, alternative\n  workweeks).\n- \"Do we have to provide meal\u002Frest breaks?\" — Research the applicable\n  state rule and any penalty-pay consequence for missed breaks.\n- \"When is final pay due?\" — Research the applicable state rule, including\n  whether timing differs for termination vs. resignation and whether\n  waiting-time or late-pay penalties apply.\n- \"Do we have to pay out accrued PTO?\" — Research the applicable state rule\n  and any carve-out for accrual-cap or use-it-or-lose-it policies.\n- \"Can we classify this person as a contractor?\" — Route to\n  `\u002Femployment-legal:worker-classification` if the facts are not already clear.\n\n### Step 2a: FLSA regular-rate and back-pay calculations\n\nWhen the question is a back-pay computation, unpaid-OT computation, or any\nquestion that turns on the FLSA \"regular rate,\" use this scaffold. Do not\nanswer from bare hourly wage × OT hours; that's the two most common errors\nthis skill exists to catch.\n\n**The regular rate is NOT just the hourly wage.** Under 29 U.S.C. §207(e),\nthe regular rate is **all remuneration** for employment EXCEPT the eight\nstatutory exclusions in §207(e)(1)–(8) (e.g., discretionary bonuses, gifts,\npremium pay, expense reimbursements, profit-sharing plans meeting the DOL\nregs, stock options meeting §207(e)(8), retirement\u002Finsurance contributions).\nAnything NOT within those eight exclusions is IN.\n\n1. **Non-discretionary bonuses are IN the regular rate.** Productivity\n   bonuses, attendance bonuses, commissions, shift differentials, contest\n   awards, and most \"bonuses\" a reasonable employee would expect as a matter\n   of course are non-discretionary under §207(e)(3) and 29 C.F.R. §778.211.\n   Divide the bonus by the total hours worked in the bonus period to get\n   the per-hour increase to the regular rate. True discretionary bonuses\n   (§207(e)(3)) require both the fact of payment AND the amount to be\n   within the employer's sole discretion, determined at or near the end of\n   the period — narrow category.\n2. **The unpaid OT premium is 0.5×, not 1.5× — when straight time was\n   already paid for all hours.** If the employee was paid straight time for\n   every hour (including the OT hours) but no premium, they are owed the\n   **half-time premium** on OT hours, not time-and-a-half: `unpaid OT =\n   0.5 × regular rate × OT hours`. 29 C.F.R. §778.110(b). If the employee\n   was NOT paid for the OT hours at all, the owed amount is 1.5× the\n   regular rate on those hours. **State which pay posture you're assuming\n   before you compute** — it determines 0.5× vs. 1.5× and is the most\n   common error in this computation.\n3. **Show your math.** Print the formula and the inputs explicitly:\n   ```\n   Regular rate    = (straight-time wages + non-discretionary bonuses + other non-excluded comp) ÷ total hours worked\n   OT premium owed = 0.5 × regular rate × OT hours    [if straight time already paid for OT hours]\n                   = 1.5 × regular rate × OT hours    [if OT hours were unpaid]\n   ```\n   A number without the formula is not usable by a wage-and-hour lawyer.\n4. **Liquidated damages double the back-pay.** 29 U.S.C. §216(b). Liquidated\n   damages equal the unpaid back-pay amount unless the employer proves, to\n   the court's satisfaction, that the violation was in good faith and based\n   on reasonable grounds to believe it was not a violation. 29 U.S.C.\n   §260. Default assumption is liquidated damages apply; the employer bears\n   the burden to avoid them.\n5. **Statute of limitations is 2 years; 3 for willful.** 29 U.S.C. §255(a).\n   State the lookback explicitly and compute both bookends unless the\n   willfulness posture is already established by the user.\n6. **State overlay.** Many states have longer lookback, higher overtime\n   multipliers (daily OT, double-time), and different regular-rate rules.\n   Check state wage-and-hour law against the jurisdiction gate from Step 1\n   and flag where state law compounds (higher cap) or replaces (different\n   rate) federal. California, New York, Massachusetts, and Washington are\n   the most frequent overlay hits.\n7. **Attach the verify tag to the number.** Any back-pay amount produced by\n   this skill carries `[verify — consult wage-and-hour counsel before\n   asserting or paying]` on the line the number appears. The computation is\n   specialist work; the skill is scaffolding, not opinion.\n\nIf the question is a back-pay calculation and any of these inputs are\nmissing (bonus breakdown, whether straight time was paid for OT hours,\nwillfulness posture, state jurisdiction), **ask before computing**. A\nconfident wrong number is the worst output this skill can produce.\n\n### Step 3: The flag\n\nIs this a close call? Be honest.\n\n- If the answer is clear on the researched rule: say so. \"Exempt — meets\n  each element of the applicable duties test and the current salary\n  threshold.\"\n- If it's close: say so. \"The duties test is borderline — this role could\n  go either way. Recommend classifying as non-exempt to be safe, or getting\n  a formal opinion.\"\n- If the law is in flux: say so. \"This rule has been amended recently — the\n  current version takes effect [date]. Confirm effective date before relying\n  on this answer.\"\n- If you could not verify currency: say so. Do not guess.\n\n## Output format\n\nConversational. This is a Q&A, not a memo.\n\n> **Research-connector pre-flight.** Before emitting the answer, check whether a legal research connector is reachable for this session — Westlaw, CourtListener, or any firm-configured research MCP. Collect this into the reviewer note per CLAUDE.md `## Outputs`: if no connector returns results in Step 2 (or none is configured at run time), record it in the **Sources:** line of the reviewer note — e.g., `not connected — cites from training knowledge; pinpoint cites (volume\u002Fpage\u002Fsubsection) carry the highest fabrication risk, spot-check those first`. Per-citation `[model knowledge — verify]` tags remain inline. Do not emit a standalone banner above the output.\n\n> **Jurisdiction assumption.** Answers apply only to the jurisdiction identified. Wage-hour rules, exemption thresholds, and final-pay timing vary materially by state and country, and many rules index or change year over year. If the employee works in another jurisdiction, or the question is answered for the default-footprint state, this answer may not apply as written.\n\n```\n**[Jurisdiction]:** [The researched rule, one paragraph, with pinpoint cite\nand currency note.]\n\n[If close call or shifting law: the flag.]\n\n[If the answer differs in other footprint jurisdictions: one line noting that,\nand whether the differences are material.]\n```\n\n> **Verify citations.** Any case, statute, regulation, or wage-order cite above was generated with AI assistance. Before relying on a cite, check it against Westlaw, CourtListener, the relevant state agency's site, or your firm's research tool for accuracy, currency, and subsequent history. Fabricated or misquoted citations in filings or formal advice have resulted in sanctions.\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- State the rule from memory — every answer is grounded in a researched,\n  cited primary source verified for currency.\n- Make classification decisions for borderline cases. It states the rule and\n  flags the close call. Human decides.\n- Give a 50-state survey unless asked. Answers for the relevant\n  jurisdiction(s).\n- Track when the answer changes. If thresholds index or law shifts, the\n  answer goes stale. Re-ask for current.\n","# \u002Fwage-hour-qa\n\n1. Load `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Femployment-legal\u002FCLAUDE.md` → jurisdictional footprint.\n2. Use the workflow below.\n3. Identify jurisdiction the question is about. If not specified, ask.\n4. Answer per that jurisdiction's rule. Cite. Flag if it's a close call or law is shifting.\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 `\u002Femployment-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\u002Femployment-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Purpose\n\n\"It depends\" is true but unhelpful. This skill produces a jurisdiction-specific\nanswer grounded in researched, cited primary sources — and flags when the\nquestion is close enough to need human judgment. It does not state rules from\nmemory: wage-and-hour thresholds, exemption criteria, and final-pay timing\nchange frequently and vary meaningfully by state.\n\n## Load context\n\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Femployment-legal\u002FCLAUDE.md` → jurisdictional footprint. If the question doesn't specify a\njurisdiction, ask — or answer for the state with the most employees and note\nthat.\n\n## The answer\n\n### Step 1: Jurisdiction\n\nWhich state\u002Fcountry is this about? If not stated:\n- If it's about a specific employee: where do they work?\n- If it's a policy question: identify the jurisdictions in the footprint that\n  are most likely to be the most restrictive on the question at hand, then\n  research those.\n\n### Step 2: Research the rule, then state it\n\n> **Research before answering.** For the jurisdiction and question, identify\n> the currently operative rule. Cite the controlling primary source (statute,\n> regulation, wage order, or case) with a pinpoint cite. Note the effective\n> date and whether the rule has been recently amended, indexed, or is in\n> litigation. If you are uncertain or cannot verify the current state of the\n> law, say so and flag for attorney verification — do not state a rule you\n> haven't confirmed.\n\nState the rule in one paragraph, tied to the cite. Use your tools (web search,\nlegal research integrations, team reference materials) to verify currency —\nespecially for:\n\n> **No silent supplement.** If a research query to the configured legal research tool (Westlaw, CourtListener, or firm platform) returns few or no results for the jurisdiction-and-question, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: \"The search returned [N] results from [tool]. Coverage appears thin for [jurisdiction \u002F question]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged `[web search — verify]` and should be checked against a primary source before relying, or (4) flag the question as unverified and stop here. Which would you like?\" A lawyer decides whether to accept lower-confidence sources.\n>\n> **Source attribution.** Tag every citation in the answer with where it came from: `[Westlaw]`, `[CourtListener]`, or the MCP tool name for citations retrieved from a legal research connector; `[web search — verify]` for web-search citations; `[model knowledge — verify]` for citations recalled from training data; `[user provided]` for citations the user supplied. Citations tagged `verify` carry higher fabrication risk and should be checked first. Never strip or collapse the tags.\n\n\n- Salary thresholds for any exemption (federal and state — several states\n  index annually and several have tiered thresholds by employer size).\n- Final-pay timing on termination vs. resignation (many states differ).\n- PTO payout requirements (jurisdiction-specific; some require, some leave\n  it to policy, some depend on accrual-plan design).\n- Meal and rest break rules and any penalty-pay consequence.\n- Daily or weekly overtime rules (some states have daily overtime and\n  double-time rules that federal law does not).\n- Classification tests — see the worker-classification skill; the applicable\n  test depends on jurisdiction and purpose.\n\nCommon question types you may be asked — for each, the answer is\njurisdiction-specific and time-sensitive. Do not state the rule here; route\nto research:\n\n- \"Is this role exempt?\" — Research the applicable federal and state salary\n  thresholds (verify current amounts and any employer-size tiers) and the\n  applicable duties test(s).\n- \"Do we have to pay overtime for X?\" — Research federal FLSA overtime plus\n  any state-specific overtime rules (daily OT, double-time, alternative\n  workweeks).\n- \"Do we have to provide meal\u002Frest breaks?\" — Research the applicable\n  state rule and any penalty-pay consequence for missed breaks.\n- \"When is final pay due?\" — Research the applicable state rule, including\n  whether timing differs for termination vs. resignation and whether\n  waiting-time or late-pay penalties apply.\n- \"Do we have to pay out accrued PTO?\" — Research the applicable state rule\n  and any carve-out for accrual-cap or use-it-or-lose-it policies.\n- \"Can we classify this person as a contractor?\" — Route to\n  `\u002Femployment-legal:worker-classification` if the facts are not already clear.\n\n### Step 2a: FLSA regular-rate and back-pay calculations\n\nWhen the question is a back-pay computation, unpaid-OT computation, or any\nquestion that turns on the FLSA \"regular rate,\" use this scaffold. Do not\nanswer from bare hourly wage × OT hours; that's the two most common errors\nthis skill exists to catch.\n\n**The regular rate is NOT just the hourly wage.** Under 29 U.S.C. §207(e),\nthe regular rate is **all remuneration** for employment EXCEPT the eight\nstatutory exclusions in §207(e)(1)–(8) (e.g., discretionary bonuses, gifts,\npremium pay, expense reimbursements, profit-sharing plans meeting the DOL\nregs, stock options meeting §207(e)(8), retirement\u002Finsurance contributions).\nAnything NOT within those eight exclusions is IN.\n\n1. **Non-discretionary bonuses are IN the regular rate.** Productivity\n   bonuses, attendance bonuses, commissions, shift differentials, contest\n   awards, and most \"bonuses\" a reasonable employee would expect as a matter\n   of course are non-discretionary under §207(e)(3) and 29 C.F.R. §778.211.\n   Divide the bonus by the total hours worked in the bonus period to get\n   the per-hour increase to the regular rate. True discretionary bonuses\n   (§207(e)(3)) require both the fact of payment AND the amount to be\n   within the employer's sole discretion, determined at or near the end of\n   the period — narrow category.\n2. **The unpaid OT premium is 0.5×, not 1.5× — when straight time was\n   already paid for all hours.** If the employee was paid straight time for\n   every hour (including the OT hours) but no premium, they are owed the\n   **half-time premium** on OT hours, not time-and-a-half: `unpaid OT =\n   0.5 × regular rate × OT hours`. 29 C.F.R. §778.110(b). If the employee\n   was NOT paid for the OT hours at all, the owed amount is 1.5× the\n   regular rate on those hours. **State which pay posture you're assuming\n   before you compute** — it determines 0.5× vs. 1.5× and is the most\n   common error in this computation.\n3. **Show your math.** Print the formula and the inputs explicitly:\n   ```\n   Regular rate    = (straight-time wages + non-discretionary bonuses + other non-excluded comp) ÷ total hours worked\n   OT premium owed = 0.5 × regular rate × OT hours    [if straight time already paid for OT hours]\n                   = 1.5 × regular rate × OT hours    [if OT hours were unpaid]\n   ```\n   A number without the formula is not usable by a wage-and-hour lawyer.\n4. **Liquidated damages double the back-pay.** 29 U.S.C. §216(b). Liquidated\n   damages equal the unpaid back-pay amount unless the employer proves, to\n   the court's satisfaction, that the violation was in good faith and based\n   on reasonable grounds to believe it was not a violation. 29 U.S.C.\n   §260. Default assumption is liquidated damages apply; the employer bears\n   the burden to avoid them.\n5. **Statute of limitations is 2 years; 3 for willful.** 29 U.S.C. §255(a).\n   State the lookback explicitly and compute both bookends unless the\n   willfulness posture is already established by the user.\n6. **State overlay.** Many states have longer lookback, higher overtime\n   multipliers (daily OT, double-time), and different regular-rate rules.\n   Check state wage-and-hour law against the jurisdiction gate from Step 1\n   and flag where state law compounds (higher cap) or replaces (different\n   rate) federal. California, New York, Massachusetts, and Washington are\n   the most frequent overlay hits.\n7. **Attach the verify tag to the number.** Any back-pay amount produced by\n   this skill carries `[verify — consult wage-and-hour counsel before\n   asserting or paying]` on the line the number appears. The computation is\n   specialist work; the skill is scaffolding, not opinion.\n\nIf the question is a back-pay calculation and any of these inputs are\nmissing (bonus breakdown, whether straight time was paid for OT hours,\nwillfulness posture, state jurisdiction), **ask before computing**. A\nconfident wrong number is the worst output this skill can produce.\n\n### Step 3: The flag\n\nIs this a close call? Be honest.\n\n- If the answer is clear on the researched rule: say so. \"Exempt — meets\n  each element of the applicable duties test and the current salary\n  threshold.\"\n- If it's close: say so. \"The duties test is borderline — this role could\n  go either way. Recommend classifying as non-exempt to be safe, or getting\n  a formal opinion.\"\n- If the law is in flux: say so. \"This rule has been amended recently — the\n  current version takes effect [date]. Confirm effective date before relying\n  on this answer.\"\n- If you could not verify currency: say so. Do not guess.\n\n## Output format\n\nConversational. This is a Q&A, not a memo.\n\n> **Research-connector pre-flight.** Before emitting the answer, check whether a legal research connector is reachable for this session — Westlaw, CourtListener, or any firm-configured research MCP. Collect this into the reviewer note per CLAUDE.md `## Outputs`: if no connector returns results in Step 2 (or none is configured at run time), record it in the **Sources:** line of the reviewer note — e.g., `not connected — cites from training knowledge; pinpoint cites (volume\u002Fpage\u002Fsubsection) carry the highest fabrication risk, spot-check those first`. Per-citation `[model knowledge — verify]` tags remain inline. Do not emit a standalone banner above the output.\n\n> **Jurisdiction assumption.** Answers apply only to the jurisdiction identified. Wage-hour rules, exemption thresholds, and final-pay timing vary materially by state and country, and many rules index or change year over year. If the employee works in another jurisdiction, or the question is answered for the default-footprint state, this answer may not apply as written.\n\n```\n**[Jurisdiction]:** [The researched rule, one paragraph, with pinpoint cite\nand currency note.]\n\n[If close call or shifting law: the flag.]\n\n[If the answer differs in other footprint jurisdictions: one line noting that,\nand whether the differences are material.]\n```\n\n> **Verify citations.** Any case, statute, regulation, or wage-order cite above was generated with AI assistance. Before relying on a cite, check it against Westlaw, CourtListener, the relevant state agency's site, or your firm's research tool for accuracy, currency, and subsequent history. Fabricated or misquoted citations in filings or formal advice have resulted in sanctions.\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- State the rule from memory — every answer is grounded in a researched,\n  cited primary source verified for currency.\n- Make classification decisions for borderline cases. It states the rule and\n  flags the close call. Human decides.\n- Give a 50-state survey unless asked. Answers for the relevant\n  jurisdiction(s).\n- Track when the answer changes. If thresholds index or law shifts, the\n  answer goes stale. Re-ask for current.\n",{"name":5,"description":44,"argument-hint":45},"Jurisdiction-aware wage\u002Fhour and employment Q&A — classification, overtime, meal\u002Frest breaks, leave, final pay — answered for the specific state\u002Fcountry with the controlling rule researched and cited rather than stated from memory. Use when the user asks any employment law question, or says \"what's the rule in [state]\", \"is this exempt\", \"do we have to pay overtime for\", or \"can we classify this as\".\n","[question]","main","4a6c651889c97cc9140580363c73e0eb17379c2b","employment-legal\u002Fskills\u002Fwage-hour-qa",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 wage-hour-qa",{"tool":60,"command":61},"bunx","bunx skills add anthropics\u002Fclaude-for-legal --skill wage-hour-qa",{"tool":63,"command":64},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-for-legal --skill wage-hour-qa","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Femployment-legal\u002Fskills\u002Fwage-hour-qa\u002FSKILL.md",true,[],[69,97,119,138,160,172],{"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",[81,82,83,84,85,86,87,88,35,33,89,90,31,91,29,92,93,94,95,96],"reg","watcher","reg feed watcher","running","feeds","filtered","diff","development","new","now","scheduled","check","last","update","report","regulatory",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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",[],[104,105,87,35,106,107,108,31,109,29,110,111,112,113,114,115,116,117,96,118],"policy","policy redraft","up","fix","produce","documents","drafting","gaps","review","draft","id","gap","mark","first","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",[],[87,104,126,127,29,128,129,81,130,82,131,132,133,134,31,135,115,136,137,96],"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",[],[145,146,127,147,148,149,89,31,29,128,150,151,152,153,154,155,156,157,158,159],"workspace","matter workspace","switch","manage","workspaces","keep","across","create","engagement","close","active","clients","list","it","context",{"skillNo":161,"name":111,"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",[],[111,114,115,166,154,167,168,169,170,31,171,29,21],"risk","tracker","remediation","status","open","accept",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":183,"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",[178],{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[115,184,185,186,87,104,187,170,188,189,190,191,111,27,192,193,194,167,168,195],"gap surfacer","shared","tracks","send","confirmation","aging","false","comments","work","slack","via","surfaces"]