[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718HEVW6S2HCHE71HS3AV69":3,"skill-same:01M718HEVW6S2HCHE71HS3AV69":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},"01M718HEVW6S2HCHE71HS3AV69","irac-practice",null,"Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Does NOT rewrite the essay or show a model answer; tracks patterns across sessions. Use when the user says \"grade my IRAC\", \"check my essay\", or \"I wrote this, give me feedback\".","anthropics\u002Fclaude-for-legal","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7189QY7HXHMC9BW4MFHPZ6H",9977,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Flaw-student\u002Fskills\u002Firac-practice\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"irac practice","use","me","structure","essay","draft","check","across","analysis","rewrite","when","sessions","accuracy","depth","answer","for","model","tracks","feedback","show","2026-11-10 10:12:30",false,"---\nname: irac-practice\ndescription: >\n  Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis\n  depth, and organization. Does NOT rewrite the essay or show a model answer;\n  tracks patterns across sessions. Use when the user says \"grade my IRAC\",\n  \"check my essay\", or \"I wrote this, give me feedback\".\nargument-hint: \"[paste essay OR path to draft OR --generate-hypo]\"\n---\n\n# \u002Firac-practice\n\n1. Load `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002FCLAUDE.md` → classes, exam formats, outline locations, learning style.\n2. Apply the framework below.\n3. Establish mode: student-provided hypo + answer, OR skill-generated hypo with student's answer.\n4. Read the answer closely. Map against expected IRAC components.\n5. Output structured feedback: issues spotted\u002Fmissed, rule accuracy, analysis depth, organization, grade band, top 3 fixes, at most 1-2 labeled example phrasings (never a full IRAC model).\n6. Append to `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002Firac-sessions\u002F[student]\u002Ftracker.md` for pattern detection. Surface patterns after 3+ sessions.\n\n---\n\n## Real-matter check\n\nIf the question the student is asking sounds like it's about a REAL situation — their lease, their parking ticket, their family's business, their friend's arrest, a real dollar amount, a real deadline, a real party name — stop.\n\n> \"This sounds like a real situation, not a hypothetical. I can't give you legal advice, and you can't give it either — you're not a lawyer yet. If this is real, [the person] needs an actual lawyer: legal aid, your school's clinic, a lawyer referral service (your jurisdiction's bar association, law society, or legal aid body), or (if there's money) a private attorney. I'm happy to help you understand the general legal concepts involved, but that's study, not advice.\"\n\nWatch for: real names, real addresses, real dates, specific dollar amounts, \"my landlord\u002Fboss\u002Fparent\u002Ffriend,\" \"I got a ticket\u002Fletter\u002Fnotice,\" deadlines measured in days. Any one of these is a trigger.\n\n## Purpose\n\n1L writing is mostly IRAC. 2L-3L writing that touches legal analysis is IRAC under the hood. The exam rewards structure as much as content. This skill grades *structure* — did you spot the issues, did you state the rules correctly, did you apply rules to facts or just restate both?\n\n**Does not rewrite the essay.** Ever. The whole point is that you learn by writing, getting specific structural feedback, and rewriting yourself.\n\n## Confidence discipline\n\n- Structure grading (did you IRAC? did you organize? did you use topic sentences?) — confident. Structure is structure.\n- Issue-spotting feedback (did you spot the issue presented?) — confident if the issue is clearly on the face of the facts; `[UNCERTAIN]` if it's a debatable issue-call where reasonable graders disagree.\n- Rule-accuracy grading — I check rules against my knowledge and flag `[VERIFY]` on anything I'm not certain about. I do not silently fail your correct rule statement because I wasn't sure.\n- If the hypo is from a jurisdiction or area I don't know well, I grade structure only and say so explicitly — \"I can grade your IRAC shape but I can't independently verify the rules for [area]. Cross-check with your outline.\"\n\n## Load context\n\n- `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002FCLAUDE.md` → current classes, exam formats, outline locations, learning style\n- `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002Firac-sessions\u002F[student]\u002Ftracker.md` if exists — pattern tracking across sessions\n- Student-provided hypo (if practicing on a specific prompt) and their written answer\n\n## Workflow\n\n### Step 1: Establish what we're grading\n\nTwo modes:\n\n- **Student-provided hypo:** user pastes (or points at) a hypo they're practicing on, then pastes their answer. Skill grades against the hypo.\n- **Skill-generated hypo:** user asks for practice; skill generates a hypo in their subject area, user writes the answer, skill grades.\n\nIf skill-generated, the hypo itself follows the same confidence rules — the skill flags any sub-issue it's less confident about.\n\n### Step 2: Read the answer closely\n\nDon't skim. Read the student's answer as if grading it. Map it against expected IRAC components:\n\n- **Issues:** what issues did they spot? (List them.) What issues are in the hypo that they didn't spot?\n- **Rules:** for each issue addressed, is the rule statement (a) present, (b) accurate, (c) complete?\n- **Application:** for each rule, did the student apply to the specific facts, or just repeat rule + facts without linking? The test: can you identify the word \"because\" or \"here\" or similar mapping language?\n- **Conclusion:** did they reach one? Is it responsive to the call?\n- **Organization:** IRAC \u002F CRAC order? Topic sentences? Paragraph breaks that make sense?\n\n### Step 3: Structured feedback\n\nOutput per component. No rewriting. Specific, not generic.\n\n```markdown\n# IRAC Grade — [date]\n\n**Hypo:** [summary or pointer]\n**Student answer length:** [N words]\n**Expected issues:** [list — from the hypo]\n\n---\n\n## Issue spotting\n\n**Spotted:** [list]\n**Missed:** [list — these are points left on the table]\n**Mis-identified:** [if the student called something an issue that isn't]\n\n[If an issue is [UNCERTAIN: debatable issue-call], note: \"your grader might agree or disagree here; defensible read.\"]\n\n## Rule statements\n\nFor each issue addressed:\n\n- **[Issue 1]:** [Accurate \u002F partially correct \u002F wrong \u002F missing element] — [what's off, one sentence] — [VERIFY if skill less than confident on rule]\n- **[Issue 2]:** ...\n\n## Analysis\n\nFor each rule the student stated:\n\n- **[Issue 1] — did you apply?** [Yes, applied to [specific facts] | Partially — you mentioned [facts] but didn't link to rule element | No — you restated rule then facts without mapping]\n- [If not applied well: \"what you needed to do: connect [specific fact] to [specific rule element]. Not 'defendant acted negligently because of the facts' — 'defendant breached the duty of care because [specific fact] means [specific conclusion about the element].'\"]\n\n## Organization\n\n- **Order:** IRAC? CRAC? Something else?\n- **Paragraph structure:** topic sentence leading? Or buried?\n- **Transitions:** do issues flow, or is it a wall of text?\n- **Call responsiveness:** did you answer what was asked?\n\n## If graded\n\nA rough calibration — not a precise score, but a band:\n\n- **If this were graded today: [Pass \u002F borderline \u002F not yet]** — reasoning in one sentence\n\n## Top three fixes\n\nRank-ordered, one sentence each. What to rewrite if you only had time for three changes.\n\n1.\n2.\n3.\n\n## Citation check\n\nAny cases, statutes, or rules referenced in this feedback were generated by an AI model and have not been verified. Before you rely on them in a rewrite or a graded essay, look them up on Westlaw, CourtListener, or your school's research tool. AI-generated citations are sometimes fabricated or misquoted.\n\n## Writing sample — labeled example only (do not copy)\n\nIf there's a specific structural move the student missed (e.g., rule-application mapping), show ONE example sentence or paragraph that illustrates the move. Explicitly label it:\n\n> \"Here's one way to frame an analysis sentence — write your own version, don't copy this:\n> [example]\"\n\nUse sparingly. One per grade, max two. Never a full IRAC example.\n\n**Never on the student's actual substantive issue.** Example phrasings illustrate the structural move in generic placeholder form (e.g., \"[fact] means [conclusion about element] because [reasoning]\"). They cannot show what an analysis sentence or paragraph would look like on the exact hypo or issue the student is writing about — that crosses from \"seeing the move\" into \"being handed the answer.\" If the student is writing about negligence in a car accident hypo, the example must use a different subject area or abstract placeholders, not a negligence analysis sentence.\n```\n\n### Step 4: Track patterns\n\nAppend to `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002Firac-sessions\u002F[student]\u002Ftracker.md`:\n\n```markdown\n## [date] — [subject \u002F hypo topic]\n- Issues missed: [list]\n- Rule accuracy: [% or qualitative]\n- Analysis gap: [specific pattern — e.g., \"restates rule without applying\"]\n- Organization: [ok \u002F weak \u002F strong]\n```\n\nAfter 3+ sessions, surface patterns:\n- \"You keep missing counterarguments — three sessions in a row.\"\n- \"You're strong on Issue + Rule but consistently weak on Application.\"\n- \"Your organization is strong; the gap is at rule-accuracy. Drill black-letter rules with \u002Flaw-student:flashcards.\"\n\nPattern detection is the long-term value of this skill. One-off feedback helps one essay; pattern feedback changes how you study.\n\n## Integration with other skills\n\n- **legal-writing:** for non-IRAC writing (memos, briefs, papers), use `\u002Flaw-student:legal-writing` instead\n- **socratic-drill:** if issue-spotting is the recurring gap, `\u002Flaw-student:socratic-drill` on issue-spotting for the subject before more essay practice\n- **flashcards:** if rule accuracy is the gap, flashcards are the right tool\n- **outline-builder:** if the student's rule is genuinely wrong in their outline, fixing the outline fixes many future IRACs\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- **Rewrite the student's answer.** Ever. No exceptions. Labeled example phrasings (one or two, clearly marked) are permitted to illustrate a structural move; they cannot be copied into the student's answer.\n- **Show a model answer.** The student has to build the model in their head. Showing one short-circuits the learning.\n- **Grade content correctness on jurisdictions or areas the skill doesn't know well.** In those cases, skill grades structure only and says so — \"I can grade your IRAC shape but can't verify rules here.\"\n- **Give a precise numeric score.** Pass\u002Fborderline\u002Fnot-yet bands only. Grading is qualitative; precision is false precision.\n- **Substitute for a professor's grading.** Professors have rubrics and preferences this skill doesn't know. Use feedback to improve; don't treat it as the final word.\n","# \u002Firac-practice\n\n1. Load `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002FCLAUDE.md` → classes, exam formats, outline locations, learning style.\n2. Apply the framework below.\n3. Establish mode: student-provided hypo + answer, OR skill-generated hypo with student's answer.\n4. Read the answer closely. Map against expected IRAC components.\n5. Output structured feedback: issues spotted\u002Fmissed, rule accuracy, analysis depth, organization, grade band, top 3 fixes, at most 1-2 labeled example phrasings (never a full IRAC model).\n6. Append to `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002Firac-sessions\u002F[student]\u002Ftracker.md` for pattern detection. Surface patterns after 3+ sessions.\n\n---\n\n## Real-matter check\n\nIf the question the student is asking sounds like it's about a REAL situation — their lease, their parking ticket, their family's business, their friend's arrest, a real dollar amount, a real deadline, a real party name — stop.\n\n> \"This sounds like a real situation, not a hypothetical. I can't give you legal advice, and you can't give it either — you're not a lawyer yet. If this is real, [the person] needs an actual lawyer: legal aid, your school's clinic, a lawyer referral service (your jurisdiction's bar association, law society, or legal aid body), or (if there's money) a private attorney. I'm happy to help you understand the general legal concepts involved, but that's study, not advice.\"\n\nWatch for: real names, real addresses, real dates, specific dollar amounts, \"my landlord\u002Fboss\u002Fparent\u002Ffriend,\" \"I got a ticket\u002Fletter\u002Fnotice,\" deadlines measured in days. Any one of these is a trigger.\n\n## Purpose\n\n1L writing is mostly IRAC. 2L-3L writing that touches legal analysis is IRAC under the hood. The exam rewards structure as much as content. This skill grades *structure* — did you spot the issues, did you state the rules correctly, did you apply rules to facts or just restate both?\n\n**Does not rewrite the essay.** Ever. The whole point is that you learn by writing, getting specific structural feedback, and rewriting yourself.\n\n## Confidence discipline\n\n- Structure grading (did you IRAC? did you organize? did you use topic sentences?) — confident. Structure is structure.\n- Issue-spotting feedback (did you spot the issue presented?) — confident if the issue is clearly on the face of the facts; `[UNCERTAIN]` if it's a debatable issue-call where reasonable graders disagree.\n- Rule-accuracy grading — I check rules against my knowledge and flag `[VERIFY]` on anything I'm not certain about. I do not silently fail your correct rule statement because I wasn't sure.\n- If the hypo is from a jurisdiction or area I don't know well, I grade structure only and say so explicitly — \"I can grade your IRAC shape but I can't independently verify the rules for [area]. Cross-check with your outline.\"\n\n## Load context\n\n- `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002FCLAUDE.md` → current classes, exam formats, outline locations, learning style\n- `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002Firac-sessions\u002F[student]\u002Ftracker.md` if exists — pattern tracking across sessions\n- Student-provided hypo (if practicing on a specific prompt) and their written answer\n\n## Workflow\n\n### Step 1: Establish what we're grading\n\nTwo modes:\n\n- **Student-provided hypo:** user pastes (or points at) a hypo they're practicing on, then pastes their answer. Skill grades against the hypo.\n- **Skill-generated hypo:** user asks for practice; skill generates a hypo in their subject area, user writes the answer, skill grades.\n\nIf skill-generated, the hypo itself follows the same confidence rules — the skill flags any sub-issue it's less confident about.\n\n### Step 2: Read the answer closely\n\nDon't skim. Read the student's answer as if grading it. Map it against expected IRAC components:\n\n- **Issues:** what issues did they spot? (List them.) What issues are in the hypo that they didn't spot?\n- **Rules:** for each issue addressed, is the rule statement (a) present, (b) accurate, (c) complete?\n- **Application:** for each rule, did the student apply to the specific facts, or just repeat rule + facts without linking? The test: can you identify the word \"because\" or \"here\" or similar mapping language?\n- **Conclusion:** did they reach one? Is it responsive to the call?\n- **Organization:** IRAC \u002F CRAC order? Topic sentences? Paragraph breaks that make sense?\n\n### Step 3: Structured feedback\n\nOutput per component. No rewriting. Specific, not generic.\n\n```markdown\n# IRAC Grade — [date]\n\n**Hypo:** [summary or pointer]\n**Student answer length:** [N words]\n**Expected issues:** [list — from the hypo]\n\n---\n\n## Issue spotting\n\n**Spotted:** [list]\n**Missed:** [list — these are points left on the table]\n**Mis-identified:** [if the student called something an issue that isn't]\n\n[If an issue is [UNCERTAIN: debatable issue-call], note: \"your grader might agree or disagree here; defensible read.\"]\n\n## Rule statements\n\nFor each issue addressed:\n\n- **[Issue 1]:** [Accurate \u002F partially correct \u002F wrong \u002F missing element] — [what's off, one sentence] — [VERIFY if skill less than confident on rule]\n- **[Issue 2]:** ...\n\n## Analysis\n\nFor each rule the student stated:\n\n- **[Issue 1] — did you apply?** [Yes, applied to [specific facts] | Partially — you mentioned [facts] but didn't link to rule element | No — you restated rule then facts without mapping]\n- [If not applied well: \"what you needed to do: connect [specific fact] to [specific rule element]. Not 'defendant acted negligently because of the facts' — 'defendant breached the duty of care because [specific fact] means [specific conclusion about the element].'\"]\n\n## Organization\n\n- **Order:** IRAC? CRAC? Something else?\n- **Paragraph structure:** topic sentence leading? Or buried?\n- **Transitions:** do issues flow, or is it a wall of text?\n- **Call responsiveness:** did you answer what was asked?\n\n## If graded\n\nA rough calibration — not a precise score, but a band:\n\n- **If this were graded today: [Pass \u002F borderline \u002F not yet]** — reasoning in one sentence\n\n## Top three fixes\n\nRank-ordered, one sentence each. What to rewrite if you only had time for three changes.\n\n1.\n2.\n3.\n\n## Citation check\n\nAny cases, statutes, or rules referenced in this feedback were generated by an AI model and have not been verified. Before you rely on them in a rewrite or a graded essay, look them up on Westlaw, CourtListener, or your school's research tool. AI-generated citations are sometimes fabricated or misquoted.\n\n## Writing sample — labeled example only (do not copy)\n\nIf there's a specific structural move the student missed (e.g., rule-application mapping), show ONE example sentence or paragraph that illustrates the move. Explicitly label it:\n\n> \"Here's one way to frame an analysis sentence — write your own version, don't copy this:\n> [example]\"\n\nUse sparingly. One per grade, max two. Never a full IRAC example.\n\n**Never on the student's actual substantive issue.** Example phrasings illustrate the structural move in generic placeholder form (e.g., \"[fact] means [conclusion about element] because [reasoning]\"). They cannot show what an analysis sentence or paragraph would look like on the exact hypo or issue the student is writing about — that crosses from \"seeing the move\" into \"being handed the answer.\" If the student is writing about negligence in a car accident hypo, the example must use a different subject area or abstract placeholders, not a negligence analysis sentence.\n```\n\n### Step 4: Track patterns\n\nAppend to `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Flaw-student\u002Firac-sessions\u002F[student]\u002Ftracker.md`:\n\n```markdown\n## [date] — [subject \u002F hypo topic]\n- Issues missed: [list]\n- Rule accuracy: [% or qualitative]\n- Analysis gap: [specific pattern — e.g., \"restates rule without applying\"]\n- Organization: [ok \u002F weak \u002F strong]\n```\n\nAfter 3+ sessions, surface patterns:\n- \"You keep missing counterarguments — three sessions in a row.\"\n- \"You're strong on Issue + Rule but consistently weak on Application.\"\n- \"Your organization is strong; the gap is at rule-accuracy. Drill black-letter rules with \u002Flaw-student:flashcards.\"\n\nPattern detection is the long-term value of this skill. One-off feedback helps one essay; pattern feedback changes how you study.\n\n## Integration with other skills\n\n- **legal-writing:** for non-IRAC writing (memos, briefs, papers), use `\u002Flaw-student:legal-writing` instead\n- **socratic-drill:** if issue-spotting is the recurring gap, `\u002Flaw-student:socratic-drill` on issue-spotting for the subject before more essay practice\n- **flashcards:** if rule accuracy is the gap, flashcards are the right tool\n- **outline-builder:** if the student's rule is genuinely wrong in their outline, fixing the outline fixes many future IRACs\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- **Rewrite the student's answer.** Ever. No exceptions. Labeled example phrasings (one or two, clearly marked) are permitted to illustrate a structural move; they cannot be copied into the student's answer.\n- **Show a model answer.** The student has to build the model in their head. Showing one short-circuits the learning.\n- **Grade content correctness on jurisdictions or areas the skill doesn't know well.** In those cases, skill grades structure only and says so — \"I can grade your IRAC shape but can't verify rules here.\"\n- **Give a precise numeric score.** Pass\u002Fborderline\u002Fnot-yet bands only. Grading is qualitative; precision is false precision.\n- **Substitute for a professor's grading.** Professors have rubrics and preferences this skill doesn't know. Use feedback to improve; don't treat it as the final word.\n",{"name":5,"description":44,"argument-hint":45},"Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Does NOT rewrite the essay or show a model answer; tracks patterns across sessions. Use when the user says \"grade my IRAC\", \"check my essay\", or \"I wrote this, give me feedback\".\n","[paste essay OR path to draft OR --generate-hypo]","main","4a6c651889c97cc9140580363c73e0eb17379c2b","law-student\u002Fskills\u002Firac-practice",1959,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-08 22:42:37",{"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 irac-practice",{"tool":60,"command":61},"bunx","bunx skills add anthropics\u002Fclaude-for-legal --skill irac-practice",{"tool":63,"command":64},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-for-legal --skill irac-practice","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Fblob\u002Fmain\u002Flaw-student\u002Fskills\u002Firac-practice\u002FSKILL.md",true,[],[69,97,118,136,157,170],{"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",[81,82,83,84,85,86,87,88,34,89,90,91,20,92,29,25,93,94,95,96],"reg","watcher","reg feed watcher","running","feeds","filtered","diff","development","classification","new","now","scheduled","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",[],[104,105,87,34,106,107,108,20,109,29,110,111,112,24,113,114,115,116,96,117],"policy","policy redraft","up","fix","produce","documents","drafting","gaps","review","id","gap","mark","first","direct",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"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",[],[87,104,125,126,29,127,27,81,128,82,129,130,131,132,20,133,114,134,135,96],"policy diff","which","you","text","change","paste","library","material","gap analysis","what the","name",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"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",[],[143,144,126,145,146,147,90,20,29,127,148,26,149,150,151,152,153,154,155,156],"workspace","matter workspace","switch","manage","workspaces","keep","create","engagement","close","active","clients","list","it","context",{"skillNo":158,"name":111,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"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",[],[111,113,114,163,151,164,165,166,167,20,168,29,169],"risk","tracker","remediation","status","open","accept","user",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":181,"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",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":179,"taxonomyTypeDesc":180},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[114,182,183,36,87,104,184,167,185,186,187,188,111,189,190,191,192,164,165,193],"gap surfacer","shared","send","confirmation","aging","false","comments","with","work","slack","via","surfaces"]