[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-feature-risk-assessment":3,"mdc-c2mdf6-key":37,"related-org-anthropic-feature-risk-assessment":1276,"related-repo-anthropic-feature-risk-assessment":1465},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"feature-risk-assessment","perform structured feature risk assessments","Deeper risk assessment for a single feature or product area when the launch review found something that needs more than a line item. Structured analysis: what could go wrong, how likely, how bad, what mitigates it. Use when user says \"deep dive on this risk\", \"risk assessment for [feature]\", \"what could go wrong with\", or when launch-review flags a novel issue.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20,23],{"name":14,"slug":15,"type":16},"Compliance","compliance","tag",{"name":18,"slug":19,"type":16},"Product Management","product-management",{"name":21,"slug":22,"type":16},"Legal","legal",{"name":24,"slug":25,"type":16},"Risk Assessment","risk-assessment",8721,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","2026-05-13T06:04:26.958143",null,1642,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"A suite of plugins for legal workflows","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Ftree\u002FHEAD\u002Fproduct-legal\u002Fskills\u002Ffeature-risk-assessment","---\nname: feature-risk-assessment\ndescription: >\n  Deeper risk assessment for a single feature or product area when the launch\n  review found something that needs more than a line item. Structured analysis:\n  what could go wrong, how likely, how bad, what mitigates it. Use when user\n  says \"deep dive on this risk\", \"risk assessment for [feature]\", \"what could\n  go wrong with\", or when launch-review flags a novel issue.\n---\n\n# Feature Risk Assessment\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 `\u002Fproduct-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\u002Fproduct-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Purpose\n\nThe launch review is broad. This is deep. When a single issue needs more than a table row — a novel AI feature, a children's product, something a regulator is actively looking at — this skill produces a standalone assessment.\n\nNot every launch needs one. Most don't. This is for the 10% where \"PIA done, shipped\" isn't the right level of scrutiny.\n\n## When to run this\n\n- Launch review found a pattern that's **not in the calibration table** (novel)\n- Launch review found something in the **\"usually blocks\"** category\n- GC or leadership asked \"what's the risk here\" and wants more than a one-liner\n- The feature is in an area with **active regulatory attention** (AI, children, biometric, health)\n- Someone outside legal is worried and a structured answer would help\n\nIf none of the above, the launch review is enough. Don't generate paperwork for its own sake.\n\n## Structure\n\n### 1. What we're assessing\n\nOne paragraph. What the feature does, what's new about it, why it got escalated to a full assessment.\n\n### 2. The risks\n\nFor each distinct risk (aim for 2-5, not 15):\n\n```markdown\n### Risk [N]: [Short name]\n\n**Scenario:** [What would have to happen for this to go wrong. Be specific —\nnot \"data breach\" but \"the recommendation algo surfaces a user's sensitive\ncategory interest to someone who shouldn't see it because X.\"]\n\n**Who gets hurt:** [Users? The company? A third party? Specific.]\n\n**How likely:** [Low \u002F Medium \u002F High — with a reason. \"Low — would require\nboth X and Y to fail simultaneously.\" Not just a vibes rating.]\n\n**How bad if it happens:** [Low \u002F Medium \u002F High — with a reason. \"High —\nregulatory fine + class action exposure + press\" vs. \"Low — one angry\ntweet, no actual harm.\"]\n\n**Existing mitigations:** [What already reduces the likelihood or impact]\n\n**Gap:** [What's missing, if anything]\n\n**Residual risk:** [After existing mitigations — is this acceptable or does\nit need more?]\n```\n\n### 3. Regulatory landscape (if relevant)\n\nOnly include if a regulator is actively interested in this space. If so:\n\n- Which regulator, what they've said\u002Fdone recently\n- How this feature would look to them\n- Whether we'd rather they hear about it from us or from a headline\n\n### 4. Precedent (if any)\n\nHas another company done something similar? What happened?\n\n- If nothing bad happened → useful, not dispositive\n- If something bad happened → what was different about their situation, does it apply here\n\nDon't overweight precedent. Regulators change priorities; one company getting away with something doesn't mean the next one will.\n\n### 5. Options\n\nPresent 2-3 realistic paths:\n\n```markdown\n| Option | Description | Risk reduction | Cost |\n|---|---|---|---|\n| A: Ship as designed | [current plan] | None | None |\n| B: Ship with [mitigation] | [change] | [how much] | [eng effort, timeline, UX] |\n| C: Don't ship [component] | [scope cut] | [how much] | [product impact] |\n```\n\n### 6. Recommendation\n\nPick one. Explain why. Acknowledge what you're trading off.\n\n```markdown\n**Recommended: Option [X]**\n\n[Why. What risk remains. Why that's acceptable. Who accepts it.]\n\n**If the answer is \"not my call\":** [Who decides, what they need to know]\n```\n\n## Calibration check\n\nBefore finalizing, check against `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md` → Risk calibration:\n\n- Is this risk assessment calibrated to *this company*, or is it generic?\n- A risk that's \"High\" at a company under a consent decree might be \"Medium\" at one that isn't\n- The assessment should reflect the actual regulatory posture, litigation history, and risk appetite captured in the practice profile\n\n## Handoffs\n\n- **To AI governance:** If the deep-dive was triggered by an AI feature — which\n  it often is — run `\u002Fai-governance-legal:aia-generation [feature]` in parallel or\n  immediately after. The feature risk assessment frames the decision; the AIA\n  documents the AI system specifically in the format AI governance needs. They're\n  not duplicates: the FRA is a product-legal decision doc; the AIA is the\n  governance record.\n- **To privacy:** If the feature involves new data collection or processing,\n  run `\u002Fprivacy-legal:pia-generation [feature]`. The FRA's risk section\n  will likely overlap with the PIA's — flag that overlap so work isn't duplicated,\n  but both docs need to exist.\n- **To AI governance vendor review:** If the feature uses a new AI vendor,\n  run `\u002Fai-governance-legal:vendor-ai-review [vendor agreement]` if not already done\n  during the launch review.\n\n## Output format\n\nStandalone doc, 2-4 pages. Prepend the work-product header from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md` `## Outputs` (it differs by user role — see `## Who's using this`).\n\nNot a slide deck, not a memo to file — a decision document someone reads and then decides.\n\nSave where `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md` → Launch review process says review docs go. If the doc is going to be shared with anyone outside the privileged loop (e.g., posted to a broadly-shared ticket), drop the work-product header only for that externally-facing copy and keep the privileged original in the matter file.\n\n## Citation check\n\nIf the assessment cites cases, statutes, regulations, or enforcement actions — in the Regulatory landscape or Precedent sections especially — those citations were generated by an AI model and have not been verified against a primary source. Before the decision document goes to a decisionmaker, verify each citation against a legal research tool (Westlaw, CourtListener, or your firm's research platform) for accuracy, good law status, and current enforcement posture. A risk assessment built on a fabricated enforcement action is worse than no assessment.\n\n> **No silent supplement.** If a research query to the configured legal research tool returns few or no results for the regime or precedent the assessment needs, 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 [regime \u002F precedent]. 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 the issuing authority before relying, or (4) flag as unverified and stop. Which would you like?\" A lawyer decides whether to accept lower-confidence sources.\n>\n> **Source attribution.** Tag every citation in the Regulatory landscape and Precedent sections with where it came from: `[Westlaw]`, `[CourtListener]`, `[regulator site]`, 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 from the feature team. Citations tagged `verify` carry higher fabrication risk and should be checked first. Never strip or collapse the tags — the decisionmaker needs to see which citations to verify first.\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- It doesn't assess every feature. Most features get a launch review and that's it.\n- It doesn't make the decision. It frames the decision. Someone with authority picks an option.\n- It doesn't do quantitative risk modeling. If the company has a formal risk framework with numbers, use that — this is qualitative.\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,50,57,141,145,151,156,161,167,218,223,229,236,241,247,252,572,578,583,601,607,612,625,630,636,641,864,870,875,952,958,971,997,1003,1060,1066,1094,1099,1111,1117,1122,1228,1234,1246,1252,1270],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","Feature Risk Assessment",{"type":43,"tag":51,"props":52,"children":54},"h2",{"id":53},"matter-context",[55],{"type":48,"value":56},"Matter context",{"type":43,"tag":58,"props":59,"children":60},"p",{},[61,67,69,76,78,84,86,92,94,100,102,108,110,116,118,124,126,132,133,139],{"type":43,"tag":62,"props":63,"children":64},"strong",{},[65],{"type":48,"value":66},"Matter context.",{"type":48,"value":68}," Check ",{"type":43,"tag":70,"props":71,"children":73},"code",{"className":72},[],[74],{"type":48,"value":75},"## Matter workspaces",{"type":48,"value":77}," in the practice-level CLAUDE.md. If ",{"type":43,"tag":70,"props":79,"children":81},{"className":80},[],[82],{"type":48,"value":83},"Enabled",{"type":48,"value":85}," is ",{"type":43,"tag":70,"props":87,"children":89},{"className":88},[],[90],{"type":48,"value":91},"✗",{"type":48,"value":93}," (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 ",{"type":43,"tag":70,"props":95,"children":97},{"className":96},[],[98],{"type":48,"value":99},"\u002Fproduct-legal:matter-workspace switch \u003Cslug>",{"type":48,"value":101}," or say ",{"type":43,"tag":70,"props":103,"children":105},{"className":104},[],[106],{"type":48,"value":107},"practice-level",{"type":48,"value":109},".\" Load the active matter's ",{"type":43,"tag":70,"props":111,"children":113},{"className":112},[],[114],{"type":48,"value":115},"matter.md",{"type":48,"value":117}," for matter-specific context and overrides. Write outputs to the matter folder at ",{"type":43,"tag":70,"props":119,"children":121},{"className":120},[],[122],{"type":48,"value":123},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F",{"type":48,"value":125},". Never read another matter's files unless ",{"type":43,"tag":70,"props":127,"children":129},{"className":128},[],[130],{"type":48,"value":131},"Cross-matter context",{"type":48,"value":85},{"type":43,"tag":70,"props":134,"children":136},{"className":135},[],[137],{"type":48,"value":138},"on",{"type":48,"value":140},".",{"type":43,"tag":142,"props":143,"children":144},"hr",{},[],{"type":43,"tag":51,"props":146,"children":148},{"id":147},"purpose",[149],{"type":48,"value":150},"Purpose",{"type":43,"tag":58,"props":152,"children":153},{},[154],{"type":48,"value":155},"The launch review is broad. This is deep. When a single issue needs more than a table row — a novel AI feature, a children's product, something a regulator is actively looking at — this skill produces a standalone assessment.",{"type":43,"tag":58,"props":157,"children":158},{},[159],{"type":48,"value":160},"Not every launch needs one. Most don't. This is for the 10% where \"PIA done, shipped\" isn't the right level of scrutiny.",{"type":43,"tag":51,"props":162,"children":164},{"id":163},"when-to-run-this",[165],{"type":48,"value":166},"When to run this",{"type":43,"tag":168,"props":169,"children":170},"ul",{},[171,184,196,201,213],{"type":43,"tag":172,"props":173,"children":174},"li",{},[175,177,182],{"type":48,"value":176},"Launch review found a pattern that's ",{"type":43,"tag":62,"props":178,"children":179},{},[180],{"type":48,"value":181},"not in the calibration table",{"type":48,"value":183}," (novel)",{"type":43,"tag":172,"props":185,"children":186},{},[187,189,194],{"type":48,"value":188},"Launch review found something in the ",{"type":43,"tag":62,"props":190,"children":191},{},[192],{"type":48,"value":193},"\"usually blocks\"",{"type":48,"value":195}," category",{"type":43,"tag":172,"props":197,"children":198},{},[199],{"type":48,"value":200},"GC or leadership asked \"what's the risk here\" and wants more than a one-liner",{"type":43,"tag":172,"props":202,"children":203},{},[204,206,211],{"type":48,"value":205},"The feature is in an area with ",{"type":43,"tag":62,"props":207,"children":208},{},[209],{"type":48,"value":210},"active regulatory attention",{"type":48,"value":212}," (AI, children, biometric, health)",{"type":43,"tag":172,"props":214,"children":215},{},[216],{"type":48,"value":217},"Someone outside legal is worried and a structured answer would help",{"type":43,"tag":58,"props":219,"children":220},{},[221],{"type":48,"value":222},"If none of the above, the launch review is enough. Don't generate paperwork for its own sake.",{"type":43,"tag":51,"props":224,"children":226},{"id":225},"structure",[227],{"type":48,"value":228},"Structure",{"type":43,"tag":230,"props":231,"children":233},"h3",{"id":232},"_1-what-were-assessing",[234],{"type":48,"value":235},"1. What we're assessing",{"type":43,"tag":58,"props":237,"children":238},{},[239],{"type":48,"value":240},"One paragraph. What the feature does, what's new about it, why it got escalated to a full assessment.",{"type":43,"tag":230,"props":242,"children":244},{"id":243},"_2-the-risks",[245],{"type":48,"value":246},"2. The risks",{"type":43,"tag":58,"props":248,"children":249},{},[250],{"type":48,"value":251},"For each distinct risk (aim for 2-5, not 15):",{"type":43,"tag":253,"props":254,"children":259},"pre",{"className":255,"code":256,"language":257,"meta":258,"style":258},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","### Risk [N]: [Short name]\n\n**Scenario:** [What would have to happen for this to go wrong. Be specific —\nnot \"data breach\" but \"the recommendation algo surfaces a user's sensitive\ncategory interest to someone who shouldn't see it because X.\"]\n\n**Who gets hurt:** [Users? The company? A third party? Specific.]\n\n**How likely:** [Low \u002F Medium \u002F High — with a reason. \"Low — would require\nboth X and Y to fail simultaneously.\" Not just a vibes rating.]\n\n**How bad if it happens:** [Low \u002F Medium \u002F High — with a reason. \"High —\nregulatory fine + class action exposure + press\" vs. \"Low — one angry\ntweet, no actual harm.\"]\n\n**Existing mitigations:** [What already reduces the likelihood or impact]\n\n**Gap:** [What's missing, if anything]\n\n**Residual risk:** [After existing mitigations — is this acceptable or does\nit need more?]\n","markdown","",[260],{"type":43,"tag":70,"props":261,"children":262},{"__ignoreMap":258},[263,302,312,338,347,356,364,386,394,416,425,433,455,464,473,481,503,511,533,541,563],{"type":43,"tag":264,"props":265,"children":268},"span",{"class":266,"line":267},"line",1,[269,275,281,286,292,297],{"type":43,"tag":264,"props":270,"children":272},{"style":271},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[273],{"type":48,"value":274},"### ",{"type":43,"tag":264,"props":276,"children":278},{"style":277},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[279],{"type":48,"value":280},"Risk ",{"type":43,"tag":264,"props":282,"children":283},{"style":271},[284],{"type":48,"value":285},"[",{"type":43,"tag":264,"props":287,"children":289},{"style":288},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[290],{"type":48,"value":291},"N",{"type":43,"tag":264,"props":293,"children":294},{"style":271},[295],{"type":48,"value":296},"]",{"type":43,"tag":264,"props":298,"children":299},{"style":277},[300],{"type":48,"value":301},": [Short name]\n",{"type":43,"tag":264,"props":303,"children":305},{"class":266,"line":304},2,[306],{"type":43,"tag":264,"props":307,"children":309},{"emptyLinePlaceholder":308},true,[310],{"type":48,"value":311},"\n",{"type":43,"tag":264,"props":313,"children":315},{"class":266,"line":314},3,[316,322,328,332],{"type":43,"tag":264,"props":317,"children":319},{"style":318},"--shiki-light:#39ADB5;--shiki-light-font-weight:bold;--shiki-default:#89DDFF;--shiki-default-font-weight:bold;--shiki-dark:#89DDFF;--shiki-dark-font-weight:bold",[320],{"type":48,"value":321},"**",{"type":43,"tag":264,"props":323,"children":325},{"style":324},"--shiki-light:#E53935;--shiki-light-font-weight:bold;--shiki-default:#F07178;--shiki-default-font-weight:bold;--shiki-dark:#F07178;--shiki-dark-font-weight:bold",[326],{"type":48,"value":327},"Scenario:",{"type":43,"tag":264,"props":329,"children":330},{"style":318},[331],{"type":48,"value":321},{"type":43,"tag":264,"props":333,"children":335},{"style":334},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[336],{"type":48,"value":337}," [What would have to happen for this to go wrong. Be specific —\n",{"type":43,"tag":264,"props":339,"children":341},{"class":266,"line":340},4,[342],{"type":43,"tag":264,"props":343,"children":344},{"style":334},[345],{"type":48,"value":346},"not \"data breach\" but \"the recommendation algo surfaces a user's sensitive\n",{"type":43,"tag":264,"props":348,"children":350},{"class":266,"line":349},5,[351],{"type":43,"tag":264,"props":352,"children":353},{"style":334},[354],{"type":48,"value":355},"category interest to someone who shouldn't see it because X.\"]\n",{"type":43,"tag":264,"props":357,"children":359},{"class":266,"line":358},6,[360],{"type":43,"tag":264,"props":361,"children":362},{"emptyLinePlaceholder":308},[363],{"type":48,"value":311},{"type":43,"tag":264,"props":365,"children":367},{"class":266,"line":366},7,[368,372,377,381],{"type":43,"tag":264,"props":369,"children":370},{"style":318},[371],{"type":48,"value":321},{"type":43,"tag":264,"props":373,"children":374},{"style":324},[375],{"type":48,"value":376},"Who gets hurt:",{"type":43,"tag":264,"props":378,"children":379},{"style":318},[380],{"type":48,"value":321},{"type":43,"tag":264,"props":382,"children":383},{"style":334},[384],{"type":48,"value":385}," [Users? The company? A third party? Specific.]\n",{"type":43,"tag":264,"props":387,"children":389},{"class":266,"line":388},8,[390],{"type":43,"tag":264,"props":391,"children":392},{"emptyLinePlaceholder":308},[393],{"type":48,"value":311},{"type":43,"tag":264,"props":395,"children":397},{"class":266,"line":396},9,[398,402,407,411],{"type":43,"tag":264,"props":399,"children":400},{"style":318},[401],{"type":48,"value":321},{"type":43,"tag":264,"props":403,"children":404},{"style":324},[405],{"type":48,"value":406},"How likely:",{"type":43,"tag":264,"props":408,"children":409},{"style":318},[410],{"type":48,"value":321},{"type":43,"tag":264,"props":412,"children":413},{"style":334},[414],{"type":48,"value":415}," [Low \u002F Medium \u002F High — with a reason. \"Low — would require\n",{"type":43,"tag":264,"props":417,"children":419},{"class":266,"line":418},10,[420],{"type":43,"tag":264,"props":421,"children":422},{"style":334},[423],{"type":48,"value":424},"both X and Y to fail simultaneously.\" Not just a vibes rating.]\n",{"type":43,"tag":264,"props":426,"children":428},{"class":266,"line":427},11,[429],{"type":43,"tag":264,"props":430,"children":431},{"emptyLinePlaceholder":308},[432],{"type":48,"value":311},{"type":43,"tag":264,"props":434,"children":436},{"class":266,"line":435},12,[437,441,446,450],{"type":43,"tag":264,"props":438,"children":439},{"style":318},[440],{"type":48,"value":321},{"type":43,"tag":264,"props":442,"children":443},{"style":324},[444],{"type":48,"value":445},"How bad if it happens:",{"type":43,"tag":264,"props":447,"children":448},{"style":318},[449],{"type":48,"value":321},{"type":43,"tag":264,"props":451,"children":452},{"style":334},[453],{"type":48,"value":454}," [Low \u002F Medium \u002F High — with a reason. \"High —\n",{"type":43,"tag":264,"props":456,"children":458},{"class":266,"line":457},13,[459],{"type":43,"tag":264,"props":460,"children":461},{"style":334},[462],{"type":48,"value":463},"regulatory fine + class action exposure + press\" vs. \"Low — one angry\n",{"type":43,"tag":264,"props":465,"children":467},{"class":266,"line":466},14,[468],{"type":43,"tag":264,"props":469,"children":470},{"style":334},[471],{"type":48,"value":472},"tweet, no actual harm.\"]\n",{"type":43,"tag":264,"props":474,"children":476},{"class":266,"line":475},15,[477],{"type":43,"tag":264,"props":478,"children":479},{"emptyLinePlaceholder":308},[480],{"type":48,"value":311},{"type":43,"tag":264,"props":482,"children":484},{"class":266,"line":483},16,[485,489,494,498],{"type":43,"tag":264,"props":486,"children":487},{"style":318},[488],{"type":48,"value":321},{"type":43,"tag":264,"props":490,"children":491},{"style":324},[492],{"type":48,"value":493},"Existing mitigations:",{"type":43,"tag":264,"props":495,"children":496},{"style":318},[497],{"type":48,"value":321},{"type":43,"tag":264,"props":499,"children":500},{"style":334},[501],{"type":48,"value":502}," [What already reduces the likelihood or impact]\n",{"type":43,"tag":264,"props":504,"children":506},{"class":266,"line":505},17,[507],{"type":43,"tag":264,"props":508,"children":509},{"emptyLinePlaceholder":308},[510],{"type":48,"value":311},{"type":43,"tag":264,"props":512,"children":514},{"class":266,"line":513},18,[515,519,524,528],{"type":43,"tag":264,"props":516,"children":517},{"style":318},[518],{"type":48,"value":321},{"type":43,"tag":264,"props":520,"children":521},{"style":324},[522],{"type":48,"value":523},"Gap:",{"type":43,"tag":264,"props":525,"children":526},{"style":318},[527],{"type":48,"value":321},{"type":43,"tag":264,"props":529,"children":530},{"style":334},[531],{"type":48,"value":532}," [What's missing, if anything]\n",{"type":43,"tag":264,"props":534,"children":536},{"class":266,"line":535},19,[537],{"type":43,"tag":264,"props":538,"children":539},{"emptyLinePlaceholder":308},[540],{"type":48,"value":311},{"type":43,"tag":264,"props":542,"children":544},{"class":266,"line":543},20,[545,549,554,558],{"type":43,"tag":264,"props":546,"children":547},{"style":318},[548],{"type":48,"value":321},{"type":43,"tag":264,"props":550,"children":551},{"style":324},[552],{"type":48,"value":553},"Residual risk:",{"type":43,"tag":264,"props":555,"children":556},{"style":318},[557],{"type":48,"value":321},{"type":43,"tag":264,"props":559,"children":560},{"style":334},[561],{"type":48,"value":562}," [After existing mitigations — is this acceptable or does\n",{"type":43,"tag":264,"props":564,"children":566},{"class":266,"line":565},21,[567],{"type":43,"tag":264,"props":568,"children":569},{"style":334},[570],{"type":48,"value":571},"it need more?]\n",{"type":43,"tag":230,"props":573,"children":575},{"id":574},"_3-regulatory-landscape-if-relevant",[576],{"type":48,"value":577},"3. Regulatory landscape (if relevant)",{"type":43,"tag":58,"props":579,"children":580},{},[581],{"type":48,"value":582},"Only include if a regulator is actively interested in this space. If so:",{"type":43,"tag":168,"props":584,"children":585},{},[586,591,596],{"type":43,"tag":172,"props":587,"children":588},{},[589],{"type":48,"value":590},"Which regulator, what they've said\u002Fdone recently",{"type":43,"tag":172,"props":592,"children":593},{},[594],{"type":48,"value":595},"How this feature would look to them",{"type":43,"tag":172,"props":597,"children":598},{},[599],{"type":48,"value":600},"Whether we'd rather they hear about it from us or from a headline",{"type":43,"tag":230,"props":602,"children":604},{"id":603},"_4-precedent-if-any",[605],{"type":48,"value":606},"4. Precedent (if any)",{"type":43,"tag":58,"props":608,"children":609},{},[610],{"type":48,"value":611},"Has another company done something similar? What happened?",{"type":43,"tag":168,"props":613,"children":614},{},[615,620],{"type":43,"tag":172,"props":616,"children":617},{},[618],{"type":48,"value":619},"If nothing bad happened → useful, not dispositive",{"type":43,"tag":172,"props":621,"children":622},{},[623],{"type":48,"value":624},"If something bad happened → what was different about their situation, does it apply here",{"type":43,"tag":58,"props":626,"children":627},{},[628],{"type":48,"value":629},"Don't overweight precedent. Regulators change priorities; one company getting away with something doesn't mean the next one will.",{"type":43,"tag":230,"props":631,"children":633},{"id":632},"_5-options",[634],{"type":48,"value":635},"5. Options",{"type":43,"tag":58,"props":637,"children":638},{},[639],{"type":48,"value":640},"Present 2-3 realistic paths:",{"type":43,"tag":253,"props":642,"children":644},{"className":255,"code":643,"language":257,"meta":258,"style":258},"| Option | Description | Risk reduction | Cost |\n|---|---|---|---|\n| A: Ship as designed | [current plan] | None | None |\n| B: Ship with [mitigation] | [change] | [how much] | [eng effort, timeline, UX] |\n| C: Don't ship [component] | [scope cut] | [how much] | [product impact] |\n",[645],{"type":43,"tag":70,"props":646,"children":647},{"__ignoreMap":258},[648,693,701,743,809],{"type":43,"tag":264,"props":649,"children":650},{"class":266,"line":267},[651,656,661,665,670,674,679,683,688],{"type":43,"tag":264,"props":652,"children":653},{"style":271},[654],{"type":48,"value":655},"|",{"type":43,"tag":264,"props":657,"children":658},{"style":334},[659],{"type":48,"value":660}," Option ",{"type":43,"tag":264,"props":662,"children":663},{"style":271},[664],{"type":48,"value":655},{"type":43,"tag":264,"props":666,"children":667},{"style":334},[668],{"type":48,"value":669}," Description ",{"type":43,"tag":264,"props":671,"children":672},{"style":271},[673],{"type":48,"value":655},{"type":43,"tag":264,"props":675,"children":676},{"style":334},[677],{"type":48,"value":678}," Risk reduction ",{"type":43,"tag":264,"props":680,"children":681},{"style":271},[682],{"type":48,"value":655},{"type":43,"tag":264,"props":684,"children":685},{"style":334},[686],{"type":48,"value":687}," Cost ",{"type":43,"tag":264,"props":689,"children":690},{"style":271},[691],{"type":48,"value":692},"|\n",{"type":43,"tag":264,"props":694,"children":695},{"class":266,"line":304},[696],{"type":43,"tag":264,"props":697,"children":698},{"style":271},[699],{"type":48,"value":700},"|---|---|---|---|\n",{"type":43,"tag":264,"props":702,"children":703},{"class":266,"line":314},[704,708,713,717,722,726,731,735,739],{"type":43,"tag":264,"props":705,"children":706},{"style":271},[707],{"type":48,"value":655},{"type":43,"tag":264,"props":709,"children":710},{"style":334},[711],{"type":48,"value":712}," A: Ship as designed ",{"type":43,"tag":264,"props":714,"children":715},{"style":271},[716],{"type":48,"value":655},{"type":43,"tag":264,"props":718,"children":719},{"style":334},[720],{"type":48,"value":721}," [current plan] ",{"type":43,"tag":264,"props":723,"children":724},{"style":271},[725],{"type":48,"value":655},{"type":43,"tag":264,"props":727,"children":728},{"style":334},[729],{"type":48,"value":730}," None ",{"type":43,"tag":264,"props":732,"children":733},{"style":271},[734],{"type":48,"value":655},{"type":43,"tag":264,"props":736,"children":737},{"style":334},[738],{"type":48,"value":730},{"type":43,"tag":264,"props":740,"children":741},{"style":271},[742],{"type":48,"value":692},{"type":43,"tag":264,"props":744,"children":745},{"class":266,"line":340},[746,750,755,759,764,768,773,778,783,787,791,796,800,805],{"type":43,"tag":264,"props":747,"children":748},{"style":271},[749],{"type":48,"value":655},{"type":43,"tag":264,"props":751,"children":752},{"style":334},[753],{"type":48,"value":754}," B: Ship with ",{"type":43,"tag":264,"props":756,"children":757},{"style":271},[758],{"type":48,"value":285},{"type":43,"tag":264,"props":760,"children":761},{"style":288},[762],{"type":48,"value":763},"mitigation",{"type":43,"tag":264,"props":765,"children":766},{"style":271},[767],{"type":48,"value":296},{"type":43,"tag":264,"props":769,"children":770},{"style":271},[771],{"type":48,"value":772}," |",{"type":43,"tag":264,"props":774,"children":775},{"style":271},[776],{"type":48,"value":777}," [",{"type":43,"tag":264,"props":779,"children":780},{"style":288},[781],{"type":48,"value":782},"change",{"type":43,"tag":264,"props":784,"children":785},{"style":271},[786],{"type":48,"value":296},{"type":43,"tag":264,"props":788,"children":789},{"style":271},[790],{"type":48,"value":772},{"type":43,"tag":264,"props":792,"children":793},{"style":334},[794],{"type":48,"value":795}," [how much] ",{"type":43,"tag":264,"props":797,"children":798},{"style":271},[799],{"type":48,"value":655},{"type":43,"tag":264,"props":801,"children":802},{"style":334},[803],{"type":48,"value":804}," [eng effort, timeline, UX] ",{"type":43,"tag":264,"props":806,"children":807},{"style":271},[808],{"type":48,"value":692},{"type":43,"tag":264,"props":810,"children":811},{"class":266,"line":349},[812,816,821,825,830,834,838,843,847,851,855,860],{"type":43,"tag":264,"props":813,"children":814},{"style":271},[815],{"type":48,"value":655},{"type":43,"tag":264,"props":817,"children":818},{"style":334},[819],{"type":48,"value":820}," C: Don't ship ",{"type":43,"tag":264,"props":822,"children":823},{"style":271},[824],{"type":48,"value":285},{"type":43,"tag":264,"props":826,"children":827},{"style":288},[828],{"type":48,"value":829},"component",{"type":43,"tag":264,"props":831,"children":832},{"style":271},[833],{"type":48,"value":296},{"type":43,"tag":264,"props":835,"children":836},{"style":271},[837],{"type":48,"value":772},{"type":43,"tag":264,"props":839,"children":840},{"style":334},[841],{"type":48,"value":842}," [scope cut] ",{"type":43,"tag":264,"props":844,"children":845},{"style":271},[846],{"type":48,"value":655},{"type":43,"tag":264,"props":848,"children":849},{"style":334},[850],{"type":48,"value":795},{"type":43,"tag":264,"props":852,"children":853},{"style":271},[854],{"type":48,"value":655},{"type":43,"tag":264,"props":856,"children":857},{"style":334},[858],{"type":48,"value":859}," [product impact] ",{"type":43,"tag":264,"props":861,"children":862},{"style":271},[863],{"type":48,"value":692},{"type":43,"tag":230,"props":865,"children":867},{"id":866},"_6-recommendation",[868],{"type":48,"value":869},"6. Recommendation",{"type":43,"tag":58,"props":871,"children":872},{},[873],{"type":48,"value":874},"Pick one. Explain why. Acknowledge what you're trading off.",{"type":43,"tag":253,"props":876,"children":878},{"className":255,"code":877,"language":257,"meta":258,"style":258},"**Recommended: Option [X]**\n\n[Why. What risk remains. Why that's acceptable. Who accepts it.]\n\n**If the answer is \"not my call\":** [Who decides, what they need to know]\n",[879],{"type":43,"tag":70,"props":880,"children":881},{"__ignoreMap":258},[882,909,916,924,931],{"type":43,"tag":264,"props":883,"children":884},{"class":266,"line":267},[885,889,894,898,904],{"type":43,"tag":264,"props":886,"children":887},{"style":318},[888],{"type":48,"value":321},{"type":43,"tag":264,"props":890,"children":891},{"style":324},[892],{"type":48,"value":893},"Recommended: Option ",{"type":43,"tag":264,"props":895,"children":896},{"style":318},[897],{"type":48,"value":285},{"type":43,"tag":264,"props":899,"children":901},{"style":900},"--shiki-light:#91B859;--shiki-light-font-weight:bold;--shiki-default:#C3E88D;--shiki-default-font-weight:bold;--shiki-dark:#C3E88D;--shiki-dark-font-weight:bold",[902],{"type":48,"value":903},"X",{"type":43,"tag":264,"props":905,"children":906},{"style":318},[907],{"type":48,"value":908},"]**\n",{"type":43,"tag":264,"props":910,"children":911},{"class":266,"line":304},[912],{"type":43,"tag":264,"props":913,"children":914},{"emptyLinePlaceholder":308},[915],{"type":48,"value":311},{"type":43,"tag":264,"props":917,"children":918},{"class":266,"line":314},[919],{"type":43,"tag":264,"props":920,"children":921},{"style":334},[922],{"type":48,"value":923},"[Why. What risk remains. Why that's acceptable. Who accepts it.]\n",{"type":43,"tag":264,"props":925,"children":926},{"class":266,"line":340},[927],{"type":43,"tag":264,"props":928,"children":929},{"emptyLinePlaceholder":308},[930],{"type":48,"value":311},{"type":43,"tag":264,"props":932,"children":933},{"class":266,"line":349},[934,938,943,947],{"type":43,"tag":264,"props":935,"children":936},{"style":318},[937],{"type":48,"value":321},{"type":43,"tag":264,"props":939,"children":940},{"style":324},[941],{"type":48,"value":942},"If the answer is \"not my call\":",{"type":43,"tag":264,"props":944,"children":945},{"style":318},[946],{"type":48,"value":321},{"type":43,"tag":264,"props":948,"children":949},{"style":334},[950],{"type":48,"value":951}," [Who decides, what they need to know]\n",{"type":43,"tag":51,"props":953,"children":955},{"id":954},"calibration-check",[956],{"type":48,"value":957},"Calibration check",{"type":43,"tag":58,"props":959,"children":960},{},[961,963,969],{"type":48,"value":962},"Before finalizing, check against ",{"type":43,"tag":70,"props":964,"children":966},{"className":965},[],[967],{"type":48,"value":968},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md",{"type":48,"value":970}," → Risk calibration:",{"type":43,"tag":168,"props":972,"children":973},{},[974,987,992],{"type":43,"tag":172,"props":975,"children":976},{},[977,979,985],{"type":48,"value":978},"Is this risk assessment calibrated to ",{"type":43,"tag":980,"props":981,"children":982},"em",{},[983],{"type":48,"value":984},"this company",{"type":48,"value":986},", or is it generic?",{"type":43,"tag":172,"props":988,"children":989},{},[990],{"type":48,"value":991},"A risk that's \"High\" at a company under a consent decree might be \"Medium\" at one that isn't",{"type":43,"tag":172,"props":993,"children":994},{},[995],{"type":48,"value":996},"The assessment should reflect the actual regulatory posture, litigation history, and risk appetite captured in the practice profile",{"type":43,"tag":51,"props":998,"children":1000},{"id":999},"handoffs",[1001],{"type":48,"value":1002},"Handoffs",{"type":43,"tag":168,"props":1004,"children":1005},{},[1006,1024,1042],{"type":43,"tag":172,"props":1007,"children":1008},{},[1009,1014,1016,1022],{"type":43,"tag":62,"props":1010,"children":1011},{},[1012],{"type":48,"value":1013},"To AI governance:",{"type":48,"value":1015}," If the deep-dive was triggered by an AI feature — which\nit often is — run ",{"type":43,"tag":70,"props":1017,"children":1019},{"className":1018},[],[1020],{"type":48,"value":1021},"\u002Fai-governance-legal:aia-generation [feature]",{"type":48,"value":1023}," in parallel or\nimmediately after. The feature risk assessment frames the decision; the AIA\ndocuments the AI system specifically in the format AI governance needs. They're\nnot duplicates: the FRA is a product-legal decision doc; the AIA is the\ngovernance record.",{"type":43,"tag":172,"props":1025,"children":1026},{},[1027,1032,1034,1040],{"type":43,"tag":62,"props":1028,"children":1029},{},[1030],{"type":48,"value":1031},"To privacy:",{"type":48,"value":1033}," If the feature involves new data collection or processing,\nrun ",{"type":43,"tag":70,"props":1035,"children":1037},{"className":1036},[],[1038],{"type":48,"value":1039},"\u002Fprivacy-legal:pia-generation [feature]",{"type":48,"value":1041},". The FRA's risk section\nwill likely overlap with the PIA's — flag that overlap so work isn't duplicated,\nbut both docs need to exist.",{"type":43,"tag":172,"props":1043,"children":1044},{},[1045,1050,1052,1058],{"type":43,"tag":62,"props":1046,"children":1047},{},[1048],{"type":48,"value":1049},"To AI governance vendor review:",{"type":48,"value":1051}," If the feature uses a new AI vendor,\nrun ",{"type":43,"tag":70,"props":1053,"children":1055},{"className":1054},[],[1056],{"type":48,"value":1057},"\u002Fai-governance-legal:vendor-ai-review [vendor agreement]",{"type":48,"value":1059}," if not already done\nduring the launch review.",{"type":43,"tag":51,"props":1061,"children":1063},{"id":1062},"output-format",[1064],{"type":48,"value":1065},"Output format",{"type":43,"tag":58,"props":1067,"children":1068},{},[1069,1071,1076,1078,1084,1086,1092],{"type":48,"value":1070},"Standalone doc, 2-4 pages. Prepend the work-product header from ",{"type":43,"tag":70,"props":1072,"children":1074},{"className":1073},[],[1075],{"type":48,"value":968},{"type":48,"value":1077}," ",{"type":43,"tag":70,"props":1079,"children":1081},{"className":1080},[],[1082],{"type":48,"value":1083},"## Outputs",{"type":48,"value":1085}," (it differs by user role — see ",{"type":43,"tag":70,"props":1087,"children":1089},{"className":1088},[],[1090],{"type":48,"value":1091},"## Who's using this",{"type":48,"value":1093},").",{"type":43,"tag":58,"props":1095,"children":1096},{},[1097],{"type":48,"value":1098},"Not a slide deck, not a memo to file — a decision document someone reads and then decides.",{"type":43,"tag":58,"props":1100,"children":1101},{},[1102,1104,1109],{"type":48,"value":1103},"Save where ",{"type":43,"tag":70,"props":1105,"children":1107},{"className":1106},[],[1108],{"type":48,"value":968},{"type":48,"value":1110}," → Launch review process says review docs go. If the doc is going to be shared with anyone outside the privileged loop (e.g., posted to a broadly-shared ticket), drop the work-product header only for that externally-facing copy and keep the privileged original in the matter file.",{"type":43,"tag":51,"props":1112,"children":1114},{"id":1113},"citation-check",[1115],{"type":48,"value":1116},"Citation check",{"type":43,"tag":58,"props":1118,"children":1119},{},[1120],{"type":48,"value":1121},"If the assessment cites cases, statutes, regulations, or enforcement actions — in the Regulatory landscape or Precedent sections especially — those citations were generated by an AI model and have not been verified against a primary source. Before the decision document goes to a decisionmaker, verify each citation against a legal research tool (Westlaw, CourtListener, or your firm's research platform) for accuracy, good law status, and current enforcement posture. A risk assessment built on a fabricated enforcement action is worse than no assessment.",{"type":43,"tag":1123,"props":1124,"children":1125},"blockquote",{},[1126,1164],{"type":43,"tag":58,"props":1127,"children":1128},{},[1129,1134,1136,1140,1142,1147,1149,1154,1156,1162],{"type":43,"tag":62,"props":1130,"children":1131},{},[1132],{"type":48,"value":1133},"No silent supplement.",{"type":48,"value":1135}," If a research query to the configured legal research tool returns few or no results for the regime or precedent the assessment needs, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: \"The search returned ",{"type":43,"tag":264,"props":1137,"children":1138},{},[1139],{"type":48,"value":291},{"type":48,"value":1141}," results from ",{"type":43,"tag":264,"props":1143,"children":1144},{},[1145],{"type":48,"value":1146},"tool",{"type":48,"value":1148},". Coverage appears thin for ",{"type":43,"tag":264,"props":1150,"children":1151},{},[1152],{"type":48,"value":1153},"regime \u002F precedent",{"type":48,"value":1155},". Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged ",{"type":43,"tag":70,"props":1157,"children":1159},{"className":1158},[],[1160],{"type":48,"value":1161},"[web search — verify]",{"type":48,"value":1163}," and should be checked against the issuing authority before relying, or (4) flag as unverified and stop. Which would you like?\" A lawyer decides whether to accept lower-confidence sources.",{"type":43,"tag":58,"props":1165,"children":1166},{},[1167,1172,1174,1180,1182,1188,1189,1195,1197,1202,1204,1210,1212,1218,1220,1226],{"type":43,"tag":62,"props":1168,"children":1169},{},[1170],{"type":48,"value":1171},"Source attribution.",{"type":48,"value":1173}," Tag every citation in the Regulatory landscape and Precedent sections with where it came from: ",{"type":43,"tag":70,"props":1175,"children":1177},{"className":1176},[],[1178],{"type":48,"value":1179},"[Westlaw]",{"type":48,"value":1181},", ",{"type":43,"tag":70,"props":1183,"children":1185},{"className":1184},[],[1186],{"type":48,"value":1187},"[CourtListener]",{"type":48,"value":1181},{"type":43,"tag":70,"props":1190,"children":1192},{"className":1191},[],[1193],{"type":48,"value":1194},"[regulator site]",{"type":48,"value":1196},", or the MCP tool name for citations retrieved from a legal research connector; ",{"type":43,"tag":70,"props":1198,"children":1200},{"className":1199},[],[1201],{"type":48,"value":1161},{"type":48,"value":1203}," for web-search citations; ",{"type":43,"tag":70,"props":1205,"children":1207},{"className":1206},[],[1208],{"type":48,"value":1209},"[model knowledge — verify]",{"type":48,"value":1211}," for citations recalled from training data; ",{"type":43,"tag":70,"props":1213,"children":1215},{"className":1214},[],[1216],{"type":48,"value":1217},"[user provided]",{"type":48,"value":1219}," for citations from the feature team. Citations tagged ",{"type":43,"tag":70,"props":1221,"children":1223},{"className":1222},[],[1224],{"type":48,"value":1225},"verify",{"type":48,"value":1227}," carry higher fabrication risk and should be checked first. Never strip or collapse the tags — the decisionmaker needs to see which citations to verify first.",{"type":43,"tag":51,"props":1229,"children":1231},{"id":1230},"close-with-the-next-steps-decision-tree",[1232],{"type":48,"value":1233},"Close with the next-steps decision tree",{"type":43,"tag":58,"props":1235,"children":1236},{},[1237,1239,1244],{"type":48,"value":1238},"End with the next-steps decision tree per CLAUDE.md ",{"type":43,"tag":70,"props":1240,"children":1242},{"className":1241},[],[1243],{"type":48,"value":1083},{"type":48,"value":1245},". 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.",{"type":43,"tag":51,"props":1247,"children":1249},{"id":1248},"what-this-skill-does-not-do",[1250],{"type":48,"value":1251},"What this skill does not do",{"type":43,"tag":168,"props":1253,"children":1254},{},[1255,1260,1265],{"type":43,"tag":172,"props":1256,"children":1257},{},[1258],{"type":48,"value":1259},"It doesn't assess every feature. Most features get a launch review and that's it.",{"type":43,"tag":172,"props":1261,"children":1262},{},[1263],{"type":48,"value":1264},"It doesn't make the decision. It frames the decision. Someone with authority picks an option.",{"type":43,"tag":172,"props":1266,"children":1267},{},[1268],{"type":48,"value":1269},"It doesn't do quantitative risk modeling. If the company has a formal risk framework with numbers, use that — this is qualitative.",{"type":43,"tag":1271,"props":1272,"children":1273},"style",{},[1274],{"type":48,"value":1275},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1277,"total":1464},[1278,1299,1313,1325,1344,1357,1378,1398,1412,1427,1435,1448],{"slug":1279,"name":1279,"fn":1280,"description":1281,"org":1282,"tags":1283,"stars":1296,"repoUrl":1297,"updatedAt":1298},"algorithmic-art","create algorithmic art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1284,1287,1290,1293],{"name":1285,"slug":1286,"type":16},"Creative","creative",{"name":1288,"slug":1289,"type":16},"Design","design",{"name":1291,"slug":1292,"type":16},"Generative Art","generative-art",{"name":1294,"slug":1295,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1300,"name":1300,"fn":1301,"description":1302,"org":1303,"tags":1304,"stars":1296,"repoUrl":1297,"updatedAt":1312},"brand-guidelines","apply Anthropic brand colors and typography","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1305,1308,1309],{"name":1306,"slug":1307,"type":16},"Branding","branding",{"name":1288,"slug":1289,"type":16},{"name":1310,"slug":1311,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1314,"name":1314,"fn":1315,"description":1316,"org":1317,"tags":1318,"stars":1296,"repoUrl":1297,"updatedAt":1324},"canvas-design","create posters and visual art as PNG or PDF","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1319,1320,1321],{"name":1285,"slug":1286,"type":16},{"name":1288,"slug":1289,"type":16},{"name":1322,"slug":1323,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1326,"name":1326,"fn":1327,"description":1328,"org":1329,"tags":1330,"stars":1296,"repoUrl":1297,"updatedAt":1343},"claude-api","build apps with the Claude API","Reference for the Claude API \u002F Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.\nTRIGGER — read BEFORE opening the target file; don't skip because it \"looks like a one-liner\" — whenever: the prompt names Claude\u002FAnthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing\u002Fmodel choice\u002Flimits\u002Fcaching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent\u002FMCP\u002Ftool-definition\u002Fmulti-agent\u002FRAG\u002FLLM-judge\u002Fcomputer-use; generate\u002Fsummarize\u002Fextract\u002Fclassify\u002Frewrite\u002Fconverse over NL; debugging refusals\u002Fcutoffs\u002Fstreaming\u002Ftool-calls\u002Ftokens).\nSKIP only when another provider is being worked on (overrides all triggers): OpenAI\u002FGPT\u002FGemini\u002FLlama\u002FMistral\u002FCohere\u002FOllama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1331,1334,1335,1338,1340],{"name":1332,"slug":1333,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1336,"slug":1337,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1339,"slug":1326,"type":16},"Claude API",{"name":1341,"slug":1342,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1345,"name":1345,"fn":1346,"description":1347,"org":1348,"tags":1349,"stars":1296,"repoUrl":1297,"updatedAt":1356},"doc-coauthoring","co-author documentation and technical specs","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1350,1353],{"name":1351,"slug":1352,"type":16},"Documentation","documentation",{"name":1354,"slug":1355,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1358,"name":1358,"fn":1359,"description":1360,"org":1361,"tags":1362,"stars":1296,"repoUrl":1297,"updatedAt":1377},"docx","create and edit Word documents","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1363,1366,1368,1371,1374],{"name":1364,"slug":1365,"type":16},"Documents","documents",{"name":1367,"slug":1358,"type":16},"DOCX",{"name":1369,"slug":1370,"type":16},"Office","office",{"name":1372,"slug":1373,"type":16},"Templates","templates",{"name":1375,"slug":1376,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1379,"name":1379,"fn":1380,"description":1381,"org":1382,"tags":1383,"stars":1296,"repoUrl":1297,"updatedAt":1397},"frontend-design","design production-grade frontend interfaces","Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1384,1385,1388,1391,1394],{"name":1288,"slug":1289,"type":16},{"name":1386,"slug":1387,"type":16},"Frontend","frontend",{"name":1389,"slug":1390,"type":16},"React","react",{"name":1392,"slug":1393,"type":16},"Tailwind CSS","tailwind-css",{"name":1395,"slug":1396,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1399,"name":1399,"fn":1400,"description":1401,"org":1402,"tags":1403,"stars":1296,"repoUrl":1297,"updatedAt":1411},"internal-comms","write internal company communications","A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1404,1407,1408],{"name":1405,"slug":1406,"type":16},"Communications","communications",{"name":1372,"slug":1373,"type":16},{"name":1409,"slug":1410,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1413,"name":1413,"fn":1414,"description":1415,"org":1416,"tags":1417,"stars":1296,"repoUrl":1297,"updatedAt":1426},"mcp-builder","build MCP servers","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node\u002FTypeScript (MCP SDK).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1418,1419,1422,1423],{"name":1332,"slug":1333,"type":16},{"name":1420,"slug":1421,"type":16},"API Development","api-development",{"name":1341,"slug":1342,"type":16},{"name":1424,"slug":1425,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1323,"name":1323,"fn":1428,"description":1429,"org":1430,"tags":1431,"stars":1296,"repoUrl":1297,"updatedAt":1434},"read edit and manipulate PDF files","Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text\u002Ftables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting\u002Fdecrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1432,1433],{"name":1364,"slug":1365,"type":16},{"name":1322,"slug":1323,"type":16},"2026-04-06T17:56:02.483316",{"slug":1436,"name":1436,"fn":1437,"description":1438,"org":1439,"tags":1440,"stars":1296,"repoUrl":1297,"updatedAt":1447},"pptx","create and edit PowerPoint presentations","Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1441,1444],{"name":1442,"slug":1443,"type":16},"PowerPoint","powerpoint",{"name":1445,"slug":1446,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1449,"name":1449,"fn":1450,"description":1451,"org":1452,"tags":1453,"stars":1296,"repoUrl":1297,"updatedAt":1463},"skill-creator","create and optimize agent skills","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1454,1455,1456,1459,1462],{"name":1332,"slug":1333,"type":16},{"name":1351,"slug":1352,"type":16},{"name":1457,"slug":1458,"type":16},"Evals","evals",{"name":1460,"slug":1461,"type":16},"Performance","performance",{"name":1354,"slug":1355,"type":16},"2026-04-19T06:45:40.804",490,{"items":1466,"total":1556},[1467,1479,1496,1511,1521,1532,1543],{"slug":1468,"name":1468,"fn":1469,"description":1470,"org":1471,"tags":1472,"stars":26,"repoUrl":27,"updatedAt":1478},"ai-inventory","track AI systems for EU AI Act","EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier (prohibited, high-risk, limited, minimal, GPAI, GPAI+systemic). Role and tier are assessed per system, not per company. Use when the user says \"ai inventory\", \"add an ai system\", \"what systems do we have\", \"classify this ai system\", \"eu ai act register\", or \"ai system registry\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1473,1474,1477],{"name":14,"slug":15,"type":16},{"name":1475,"slug":1476,"type":16},"Governance","governance",{"name":21,"slug":22,"type":16},"2026-05-14T06:02:19.677579",{"slug":1480,"name":1480,"fn":1481,"description":1482,"org":1483,"tags":1484,"stars":26,"repoUrl":27,"updatedAt":1495},"ai-tool-handoff","manage handoff to bulk legal review tools","Detects when Luminance, Kira, or a similar bulk-review tool is in use, hands off the high-volume clause extraction to it, and QAs its output per the trust level in `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`. Use when user says \"send to Luminance\", \"bulk review\", \"AI extraction\", or when diligence-issue-extraction hits a high-volume category.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1485,1488,1491,1492],{"name":1486,"slug":1487,"type":16},"Automation","automation",{"name":1489,"slug":1490,"type":16},"Contracts","contracts",{"name":21,"slug":22,"type":16},{"name":1493,"slug":1494,"type":16},"QA","qa","2026-05-14T06:01:31.00555",{"slug":1497,"name":1497,"fn":1498,"description":1499,"org":1500,"tags":1501,"stars":26,"repoUrl":27,"updatedAt":1510},"aia-generation","run AI impact assessments","Run an AI impact assessment — structured intake, risk analysis, regulatory classification per regime in scope, policy consistency diff, and recommendation with conditions. Uses the house-style structure learned from the seed impact assessment in `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002FCLAUDE.md`. Use when user says \"impact assessment for\", \"assess this AI use case\", \"run an AIA\", \"generate an AIA\", \"we need to document this AI system\", \"AI risk assessment for X\", or follows a conditional triage result.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1502,1503,1506,1509],{"name":21,"slug":22,"type":16},{"name":1504,"slug":1505,"type":16},"Policy","policy",{"name":1507,"slug":1508,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":24,"slug":25,"type":16},"2026-05-13T06:03:19.61029",{"slug":1512,"name":1512,"fn":1513,"description":1514,"org":1515,"tags":1516,"stars":26,"repoUrl":27,"updatedAt":1520},"amendment-history","trace contract amendment history","Trace how a contract has changed across its base agreement and all amendments — either a summary of all changes over time, or a provision trace for a specific clause. Use when the user says \"what changed in this contract over time\", \"show me the amendment history\", \"where's the latest [clause]\", \"how has [provision] evolved\", or uploads multiple versions of an agreement.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1517,1518,1519],{"name":1489,"slug":1490,"type":16},{"name":1364,"slug":1365,"type":16},{"name":21,"slug":22,"type":16},"2026-05-13T06:03:34.070339",{"slug":1522,"name":1522,"fn":1523,"description":1524,"org":1525,"tags":1526,"stars":26,"repoUrl":27,"updatedAt":1531},"auto-updater","check for community skill updates","Check installed community skills for updates. Shows a diff and requires explicit approval before applying. Use when the user says \"check for updates\", \"update my skills\", \"anything new for my installed skills\", or when invoked from the registry-sync agent.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1527,1528],{"name":1486,"slug":1487,"type":16},{"name":1529,"slug":1530,"type":16},"Plugin Development","plugin-development","2026-05-13T06:02:55.642269",{"slug":1533,"name":1533,"fn":1534,"description":1535,"org":1536,"tags":1537,"stars":26,"repoUrl":27,"updatedAt":1542},"bar-prep-questions","provide bar exam practice questions","Bar prep questions — MBE or essay, targeted at your weak subjects and bar jurisdiction. Tracks misses and comes back to patterns. Use when the user says \"bar prep\", \"MBE questions\", \"practice essay\", or \"test me for the bar\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1538,1541],{"name":1539,"slug":1540,"type":16},"Education","education",{"name":21,"slug":22,"type":16},"2026-07-24T05:41:43.01243",{"slug":1544,"name":1544,"fn":1545,"description":1546,"org":1547,"tags":1548,"stars":26,"repoUrl":27,"updatedAt":1555},"board-minutes","draft board and committee meeting minutes","Drafts board or committee meeting minutes in your house format. Auto-detects upcoming board and committee meetings from your calendar, asks for the agenda and any slides or pre-read materials, and produces a complete draft in the format learned from your seed minutes. Also handles written consents in lieu of meetings. Trigger: \"board minutes\", \"draft minutes\", \"upcoming board meeting\", \"committee minutes\", \"written consent\", or calendar detection of an upcoming board or committee event.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1549,1550,1551,1552],{"name":1351,"slug":1352,"type":16},{"name":1475,"slug":1476,"type":16},{"name":21,"slug":22,"type":16},{"name":1553,"slug":1554,"type":16},"Meetings","meetings","2026-05-14T06:01:29.792942",118]