[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-policy-starter":3,"mdc--hombgp-key":34,"related-repo-anthropic-policy-starter":1647,"related-org-anthropic-policy-starter":1745},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"policy-starter","draft AI usage policies","Draft a firm AI usage policy from published model policies, adapted to your practice profile — a research-and-synthesis tool whose output is a draft for attorney review and adoption, not a finished policy. Use when user says \"draft an AI policy\", \"we need an AI policy\", \"build an AI usage policy\", \"our firm needs a GenAI policy\", or similar requests to generate a first-cut internal AI policy.\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],{"name":14,"slug":15,"type":16},"Technical Writing","technical-writing","tag",{"name":18,"slug":19,"type":16},"Policy","policy",{"name":21,"slug":22,"type":16},"Legal","legal",8721,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","2026-05-14T06:02:22.024772",null,1642,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"A suite of plugins for legal workflows","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Ftree\u002FHEAD\u002Fai-governance-legal\u002Fskills\u002Fpolicy-starter","---\nname: policy-starter\ndescription: >\n  Draft a firm AI usage policy from published model policies, adapted to your\n  practice profile — a research-and-synthesis tool whose output is a draft for\n  attorney review and adoption, not a finished policy. Use when user says \"draft\n  an AI policy\", \"we need an AI policy\", \"build an AI usage policy\", \"our firm\n  needs a GenAI policy\", or similar requests to generate a first-cut internal\n  AI policy.\nargument-hint: \"[optional — scope hint, e.g. 'firm-wide', 'legal team only', 'update existing']\"\n---\n\n# \u002Fpolicy-starter\n\n1. Read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002FCLAUDE.md`. If the practice profile is unpopulated, stop and direct to `\u002Fai-governance-legal:cold-start-interview`.\n2. Use the framework below.\n3. Run the scope interview — which sections does the policy need to cover, who's the audience, what's the deployment context. Do not skip to drafting.\n4. Web search for the current published model policies and guidance relevant to the deployment context (ABA, state bars, ILTA, CLOC, NIST, peer-firm \u002F peer-company policies, current state AI laws, EU AI Act, sector regulators as applicable).\n5. Draft the selected sections, sourced from the model policies, with `[review]` flags on every choice point and `[review]` open questions at the bottom of each section.\n6. Output with the draft header (\"DRAFT FOR INTERNAL LEGAL REVIEW — NOT FOR DISTRIBUTION\"), the sources block, the reviewer note, and the adoption checklist.\n7. Close with the next-steps decision tree.\n\n```\n\u002Fai-governance-legal:policy-starter\n\u002Fai-governance-legal:policy-starter \"we need an AI policy for our 30-lawyer firm\"\n\u002Fai-governance-legal:policy-starter \"update our existing policy for the 2026 state AI laws\"\n```\n\n---\n\n## Matter context\n\n**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: \"Which matter is this for? Run `\u002Fai-governance-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\u002Fai-governance-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Purpose\n\nA lot of firms and in-house teams don't have a written AI usage policy yet, or\nare running on a 2024-vintage one that doesn't mention the state AI laws, the EU\nAI Act implementing acts, the 2025 COPPA amendments, or what they actually ended\nup doing with Copilot and Claude for Work. This skill produces a **draft** policy\nto bring to the decision-maker — GC, managing partner, executive committee,\nboard, head of IT, head of HR — not a finished policy to circulate.\n\nThe discipline of this skill:\n\n1. **Source from published model policies, not from invention.** Search for and\n   read the ABA AI Toolkit, state bar guidance, ILTA's model policy, CLOC's\n   templates, and peer-firm \u002F peer-company policies that are public. Cite what\n   each source says and adapt it — don't generate policy language out of thin\n   air.\n2. **Decision-tree the scope before drafting.** A policy that tries to cover\n   everything covers nothing. Ask the user what sections the policy needs. Let\n   them pick. Then build each picked section with `[review]` flags on every\n   choice point.\n3. **Flag every judgment call.** The output is a draft the attorney reviews and\n   adopts; every threshold, every named tool, every disclosure trigger, every\n   enforcement consequence is a `[review]` line.\n4. **Header signals the scope of the audience.** This output may be read beyond\n   legal — by HR, IT, all staff. The header is adapted accordingly.\n\nThis skill does NOT finalize, distribute, publish, or even recommend a specific\nposition on the hard calls. It produces a draft and surfaces the choices.\n\n## Read `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002FCLAUDE.md` first\n\nBefore drafting, always read the practice profile. The sections that drive the\ndraft:\n\n- `## Company profile` — AI role (Builder \u002F Deployer \u002F Both), regulatory footprint,\n  external commitments, practice setting\n- `## Use case registry` — what's already approved, conditional, or a red line\n- `## AI policy commitments` — what a prior or current policy already says\n- `## Vendor AI governance` — what the team already requires from vendors\n- `## Governance team and escalation` — who approves, who escalates\n- `## Who's using this` — Role (lawyer \u002F non-lawyer) governs the header and the\n  \"adopt this\" framing\n\nIf `## AI policy commitments` is populated, this is an UPDATE, not a new draft —\ntreat the existing policy as the base and propose changes. If it's empty, this\nis a first-cut draft.\n\n## Scope interview (do this BEFORE drafting)\n\nAsk the user which sections the policy should cover. Present as a checklist —\nthe user picks, you build. Do not pre-decide.\n\n> **What should the AI policy cover? Pick the sections you want in the draft:**\n> 1. **Scope** — who the policy applies to (all staff, certain roles, contractors), what tools it covers (GenAI only, all AI, specific vendors), what data is in\u002Fout of scope.\n> 2. **Permitted and prohibited uses** — the approved categories, the red lines, the \"ask first\" cases.\n> 3. **Approval and review** — who approves a new tool, who approves a new use case, how the review request is filed, what the SLA is.\n> 4. **Disclosure** — to clients (for firms), to courts, to counterparties, to employees, to end users of an AI feature.\n> 5. **Data handling** — what confidential\u002Fclient\u002Fprivileged data can go where, data residency, vendor retention terms, training-on-data posture.\n> 6. **Training and certification** — who has to take training, on what cadence, consequences for non-completion.\n> 7. **Incidents and reporting** — what counts as an AI incident, how to report, who handles.\n> 8. **Enforcement** — what happens when the policy is violated, link to disciplinary framework.\n> 9. **Review cadence and ownership** — how often the policy gets updated, who owns updates, how changes are communicated.\n> 10. **Glossary** — defined terms (GenAI, approved tool, high-risk use, consequential decision, confidential data, etc.).\n>\n> Default starter pack for a firm \u002F in-house legal team that's never had a policy: 1, 2, 3, 4, 5, 9. Skip the rest for v1.\n\nAfter the user picks, ask the second question:\n\n> **Two more inputs before I draft:**\n> - **Audience** — who's reading this? (All staff \u002F legal team only \u002F attorneys plus staff \u002F client-facing version also needed) This drives tone and the glossary.\n> - **Deployment context** — (a) law firm, (b) in-house legal at a company (policy covers legal or company-wide?), (c) legal aid \u002F clinic, (d) government. This drives which model policies I search.\n\n## Source the model policies\n\nBefore drafting, run web searches for the most recent published model AI\npolicies and guidance.\n\n**Derive the model policy sources from the practice profile's `## Regulatory footprint`.** Don't hardcode US sources for a global user.\n\n| Jurisdiction | Model policy sources |\n|---|---|\n| US | ABA Formal Opinion 512, state bar guidance (CA, FL, NY, TX all have published AI guidance), ILTA model policy, CLOC templates, peer firm published AI policies |\n| UK | Solicitors Regulation Authority risk outlook, Law Society AI principles, ICO AI guidance, Bar Council guidance |\n| EU | EU AI Act compliance framework (Article 4 AI literacy, Article 17 quality management), national DPA AI guidance (CNIL, DSB, Garante, AEPD), EDPB guidelines, EU institutions' AI policies |\n| Australia | Law Council of Australia AI guidelines, OAIC AI guidance, state law society guidance, Australian AI Ethics Framework |\n| Singapore | PDPC Model AI Governance Framework, MinLaw guidance, MAS AI fairness principles (for financial services) |\n| Canada | Law Society of Ontario\u002FBC\u002FAlberta AI guidance, OPC AI guidance, TBS Directive on Automated Decision-Making |\n| Multi-jurisdiction | Use all applicable, and note where they diverge (e.g., EU requires human oversight documentation US doesn't; Australia focuses on voluntary ethics frameworks; Singapore focuses on sectoral regulation) |\n\nIf the practice profile's footprint is empty or `[PLACEHOLDER]`, ask: \"What jurisdiction(s) does your organization operate in? I'll draft from the model policies that match your regulatory environment and professional responsibility framework, not a US-centric template.\"\n\nFor each source the draft uses, **record it in a \"Sources\" block at the top of\nthe output** with: name, URL, date accessed, and what the draft took from it.\n\nIf a web search can't be run, note in the reviewer note: \"Could not run web\nsearch — draft sourced from training knowledge alone, verify against current\nversions of the cited sources before adopting.\" The verification log applies.\n\n## The draft\n\nOutput follows a consistent structure. **Every choice point gets a `[review]`\nflag.** The user has to decide; the skill presents options.\n\n### Header\n\n```\nDRAFT FOR INTERNAL LEGAL REVIEW — NOT FOR DISTRIBUTION\nPrepared for: [firm \u002F company name from practice profile]\nDate: [today's date]\nPrepared by: ai-governance-legal policy-starter skill, adapted from published model policies\nNot for adoption, distribution, posting, or reliance until reviewed, adapted, and approved by [attorney \u002F GC \u002F managing partner \u002F executive committee per the governance team section of the practice profile].\n```\n\nWhen the Role in `## Who's using this` is Non-lawyer: add a second line under\nthe header — \"If you are not a licensed attorney, solicitor, barrister, or other\nauthorised legal professional in your jurisdiction, bring this draft to your\nattorney contact ([name from practice profile]) before using any of it. This is\na starting draft for their review, not a policy you can adopt.\"\n\n### Sources block (at the top, under the header)\n\nA table of the model policies \u002F guidance \u002F regulations the draft drew from:\n\n| Source | URL | Accessed | What the draft took from it |\n|---|---|---|---|\n| ABA Formal Op. 512 | [url] | [date] | Disclosure and competence framing |\n| ILTA Model AI Policy v.[X] | [url] | [date] | Approval workflow, data handling |\n| [State] Bar Op. [X] | [url] | [date] | Disclosure to clients |\n| [peer firm] published AI policy | [url] | [date] | Scope language |\n| Colorado SB 24-205 | [url] | [date] | High-risk AI definition |\n| EU AI Act, Art. [X] | [url] | [date] | Vendor flow-down |\n\n### Executive summary\n\nThree paragraphs max. What the policy does, who it binds, what the reader has\nto do before it takes effect.\n\n### The sections\n\nOnly the sections the user picked, in the order above. For each:\n\n- A **header and scope** sentence.\n- The **substantive rules**, adapted from the cited model policies. Every\n  specific threshold, number, named tool, named vendor, or escalation contact\n  is `[review]`. Example: \"Confidential client data may not be entered into\n  [general-purpose consumer AI tools] `[review — list tools, or reference the\n  approved-tools list]`. Use of such data in [approved firm-licensed tools]\n  `[review — list tools]` is permitted subject to the data handling section.\"\n- **Source attribution** inline where a rule is adapted from a specific source.\n  Example: \"Attorneys must verify the accuracy of all AI-generated work product\n  before using it in representation of a client `[ABA Formal Op. 512]`.\"\n- **Open questions** at the bottom of each section — 2-3 decisions the attorney\n  needs to make before the section is ready. These are distinct from inline\n  `[review]` flags — these are the \"we don't have a position here yet\" items,\n  not the \"fill in the specifics\" items.\n\n### Adoption checklist\n\nAt the end of the draft, a checklist of the things that have to happen before\nthe policy is adopted. Don't invent these — pull from the practice profile's\ngovernance team and escalation section. Typical items:\n\n- [ ] Review by GC \u002F managing partner `[review — name]`\n- [ ] Review by IT \u002F security `[review — name]`\n- [ ] Review by HR (for enforcement \u002F training sections) `[review — name]`\n- [ ] Board \u002F executive committee approval (if required) `[review — confirm whether required]`\n- [ ] Training materials drafted\n- [ ] Announcement drafted\n- [ ] Effective date set `[review]`\n- [ ] Review cadence calendared `[review — annual is typical]`\n- [ ] Add policy to the `## AI policy commitments` section of the practice\n      profile once adopted\n\n### Reviewer note\n\nThe standard reviewer note above the header, per the `## Outputs` section of\nthe practice profile. Use the block format:\n\n> **⚠️ Reviewer note**\n> - **Sources:** web search ✓ \u002F not connected — cites from training knowledge\n> - **Read:** practice profile · [N] published model policies\n> - **Flagged for your judgment:** [N] `[review]` items inline · [N] open questions per section\n> - **Currency:** searched for developments since [date]\n> - **Before relying:** this is a DRAFT — bring to [approver from practice profile], don't distribute until adopted\n\n## Don'ts\n\n- **Don't invent policy language.** Every substantive rule in the draft must be\n  traceable to a cited source or flagged `[review — adapted, no direct source]`.\n- **Don't pick the hard calls for the attorney.** \"Should paralegals be\n  permitted to use AI for first-draft work?\" is a `[review]`, not a recommended\n  position.\n- **Don't produce a finished-looking policy.** The header, the reviewer note,\n  and the `[review]` flags throughout are the signal that this is a draft. Do\n  not soften them.\n- **Don't skip the scope interview.** If the user says \"just draft a full\n  policy,\" push back: \"A policy that tries to cover everything covers nothing.\n  Which sections do you want? Here's the checklist.\" One round of negotiation\n  is fine — two is also fine. Drafting without scope is the failure mode.\n- **Don't generate section content the user didn't ask for.** If they picked 1,\n  2, 3, 4, 5, 9, do those. Don't add section 6 because \"a real policy needs\n  training.\"\n- **Don't recommend a specific vendor, tool, or consequence.** Flag those\n  `[review]` with context on what a typical decision would be, not what the\n  user's should be.\n- **Don't promise legal sufficiency.** The draft is a starting point for\n  attorney review, not a tested policy.\n\n## Handoffs\n\nAfter the draft is produced, close with the decision tree from the practice\nprofile. The most common next steps:\n\n1. **Tune the draft** — the user walks through the `[review]` flags and resolves\n   them with the attorney; the skill re-runs with the decisions baked in.\n2. **Stakeholder summary** — produce a one-page version for the board or\n   executive committee explaining what the policy does and doesn't do.\n3. **Training materials** — once the policy is adopted, `\u002Fai-governance-legal:aia-generation` can be used to produce per-use-case training notes.\n4. **Vendor sweep** — once the policy is adopted, `\u002Fai-governance-legal:vendor-ai-review` should be run against the vendors the policy references to check conformance.\n5. **Gap check against new regulation** — pair with `\u002Fai-governance-legal:reg-gap-analysis` to test the draft against a specific regulation or guidance before adoption.\n\n## Output scope reminder\n\nThe document this skill produces reaches HR, IT, and the broader business — not\njust legal. Keep the language plain enough for non-lawyers to follow. The legal\nprecision is in the `[review]` flags and the sources, not in jargon.\n",{"data":35,"body":37},{"name":4,"description":6,"argument-hint":36},"[optional — scope hint, e.g. 'firm-wide', 'legal team only', 'update existing']",{"type":38,"children":39},"root",[40,48,120,132,136,143,225,228,234,246,251,308,313,325,330,400,412,418,423,543,548,582,588,593,610,729,742,754,759,765,784,791,800,820,826,831,1050,1056,1061,1067,1072,1169,1175,1180,1310,1316,1329,1428,1434,1535,1541,1546,1629,1635],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":47},"text","\u002Fpolicy-starter",{"type":41,"tag":49,"props":50,"children":51},"ol",{},[52,75,80,85,90,110,115],{"type":41,"tag":53,"props":54,"children":55},"li",{},[56,58,65,67,73],{"type":46,"value":57},"Read ",{"type":41,"tag":59,"props":60,"children":62},"code",{"className":61},[],[63],{"type":46,"value":64},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002FCLAUDE.md",{"type":46,"value":66},". If the practice profile is unpopulated, stop and direct to ",{"type":41,"tag":59,"props":68,"children":70},{"className":69},[],[71],{"type":46,"value":72},"\u002Fai-governance-legal:cold-start-interview",{"type":46,"value":74},".",{"type":41,"tag":53,"props":76,"children":77},{},[78],{"type":46,"value":79},"Use the framework below.",{"type":41,"tag":53,"props":81,"children":82},{},[83],{"type":46,"value":84},"Run the scope interview — which sections does the policy need to cover, who's the audience, what's the deployment context. Do not skip to drafting.",{"type":41,"tag":53,"props":86,"children":87},{},[88],{"type":46,"value":89},"Web search for the current published model policies and guidance relevant to the deployment context (ABA, state bars, ILTA, CLOC, NIST, peer-firm \u002F peer-company policies, current state AI laws, EU AI Act, sector regulators as applicable).",{"type":41,"tag":53,"props":91,"children":92},{},[93,95,101,103,108],{"type":46,"value":94},"Draft the selected sections, sourced from the model policies, with ",{"type":41,"tag":59,"props":96,"children":98},{"className":97},[],[99],{"type":46,"value":100},"[review]",{"type":46,"value":102}," flags on every choice point and ",{"type":41,"tag":59,"props":104,"children":106},{"className":105},[],[107],{"type":46,"value":100},{"type":46,"value":109}," open questions at the bottom of each section.",{"type":41,"tag":53,"props":111,"children":112},{},[113],{"type":46,"value":114},"Output with the draft header (\"DRAFT FOR INTERNAL LEGAL REVIEW — NOT FOR DISTRIBUTION\"), the sources block, the reviewer note, and the adoption checklist.",{"type":41,"tag":53,"props":116,"children":117},{},[118],{"type":46,"value":119},"Close with the next-steps decision tree.",{"type":41,"tag":121,"props":122,"children":126},"pre",{"className":123,"code":125,"language":46},[124],"language-text","\u002Fai-governance-legal:policy-starter\n\u002Fai-governance-legal:policy-starter \"we need an AI policy for our 30-lawyer firm\"\n\u002Fai-governance-legal:policy-starter \"update our existing policy for the 2026 state AI laws\"\n",[127],{"type":41,"tag":59,"props":128,"children":130},{"__ignoreMap":129},"",[131],{"type":46,"value":125},{"type":41,"tag":133,"props":134,"children":135},"hr",{},[],{"type":41,"tag":137,"props":138,"children":140},"h2",{"id":139},"matter-context",[141],{"type":46,"value":142},"Matter context",{"type":41,"tag":144,"props":145,"children":146},"p",{},[147,153,155,161,163,169,171,177,179,185,187,193,195,201,203,209,211,217,218,224],{"type":41,"tag":148,"props":149,"children":150},"strong",{},[151],{"type":46,"value":152},"Matter context.",{"type":46,"value":154}," Check ",{"type":41,"tag":59,"props":156,"children":158},{"className":157},[],[159],{"type":46,"value":160},"## Matter workspaces",{"type":46,"value":162}," in the practice-level CLAUDE.md. If ",{"type":41,"tag":59,"props":164,"children":166},{"className":165},[],[167],{"type":46,"value":168},"Enabled",{"type":46,"value":170}," is ",{"type":41,"tag":59,"props":172,"children":174},{"className":173},[],[175],{"type":46,"value":176},"✗",{"type":46,"value":178}," (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":41,"tag":59,"props":180,"children":182},{"className":181},[],[183],{"type":46,"value":184},"\u002Fai-governance-legal:matter-workspace switch \u003Cslug>",{"type":46,"value":186}," or say ",{"type":41,"tag":59,"props":188,"children":190},{"className":189},[],[191],{"type":46,"value":192},"practice-level",{"type":46,"value":194},".\" Load the active matter's ",{"type":41,"tag":59,"props":196,"children":198},{"className":197},[],[199],{"type":46,"value":200},"matter.md",{"type":46,"value":202}," for matter-specific context and overrides. Write outputs to the matter folder at ",{"type":41,"tag":59,"props":204,"children":206},{"className":205},[],[207],{"type":46,"value":208},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F",{"type":46,"value":210},". Never read another matter's files unless ",{"type":41,"tag":59,"props":212,"children":214},{"className":213},[],[215],{"type":46,"value":216},"Cross-matter context",{"type":46,"value":170},{"type":41,"tag":59,"props":219,"children":221},{"className":220},[],[222],{"type":46,"value":223},"on",{"type":46,"value":74},{"type":41,"tag":133,"props":226,"children":227},{},[],{"type":41,"tag":137,"props":229,"children":231},{"id":230},"purpose",[232],{"type":46,"value":233},"Purpose",{"type":41,"tag":144,"props":235,"children":236},{},[237,239,244],{"type":46,"value":238},"A lot of firms and in-house teams don't have a written AI usage policy yet, or\nare running on a 2024-vintage one that doesn't mention the state AI laws, the EU\nAI Act implementing acts, the 2025 COPPA amendments, or what they actually ended\nup doing with Copilot and Claude for Work. This skill produces a ",{"type":41,"tag":148,"props":240,"children":241},{},[242],{"type":46,"value":243},"draft",{"type":46,"value":245}," policy\nto bring to the decision-maker — GC, managing partner, executive committee,\nboard, head of IT, head of HR — not a finished policy to circulate.",{"type":41,"tag":144,"props":247,"children":248},{},[249],{"type":46,"value":250},"The discipline of this skill:",{"type":41,"tag":49,"props":252,"children":253},{},[254,264,281,298],{"type":41,"tag":53,"props":255,"children":256},{},[257,262],{"type":41,"tag":148,"props":258,"children":259},{},[260],{"type":46,"value":261},"Source from published model policies, not from invention.",{"type":46,"value":263}," Search for and\nread the ABA AI Toolkit, state bar guidance, ILTA's model policy, CLOC's\ntemplates, and peer-firm \u002F peer-company policies that are public. Cite what\neach source says and adapt it — don't generate policy language out of thin\nair.",{"type":41,"tag":53,"props":265,"children":266},{},[267,272,274,279],{"type":41,"tag":148,"props":268,"children":269},{},[270],{"type":46,"value":271},"Decision-tree the scope before drafting.",{"type":46,"value":273}," A policy that tries to cover\neverything covers nothing. Ask the user what sections the policy needs. Let\nthem pick. Then build each picked section with ",{"type":41,"tag":59,"props":275,"children":277},{"className":276},[],[278],{"type":46,"value":100},{"type":46,"value":280}," flags on every\nchoice point.",{"type":41,"tag":53,"props":282,"children":283},{},[284,289,291,296],{"type":41,"tag":148,"props":285,"children":286},{},[287],{"type":46,"value":288},"Flag every judgment call.",{"type":46,"value":290}," The output is a draft the attorney reviews and\nadopts; every threshold, every named tool, every disclosure trigger, every\nenforcement consequence is a ",{"type":41,"tag":59,"props":292,"children":294},{"className":293},[],[295],{"type":46,"value":100},{"type":46,"value":297}," line.",{"type":41,"tag":53,"props":299,"children":300},{},[301,306],{"type":41,"tag":148,"props":302,"children":303},{},[304],{"type":46,"value":305},"Header signals the scope of the audience.",{"type":46,"value":307}," This output may be read beyond\nlegal — by HR, IT, all staff. The header is adapted accordingly.",{"type":41,"tag":144,"props":309,"children":310},{},[311],{"type":46,"value":312},"This skill does NOT finalize, distribute, publish, or even recommend a specific\nposition on the hard calls. It produces a draft and surfaces the choices.",{"type":41,"tag":137,"props":314,"children":316},{"id":315},"read-claudepluginsconfigclaude-for-legalai-governance-legalclaudemd-first",[317,318,323],{"type":46,"value":57},{"type":41,"tag":59,"props":319,"children":321},{"className":320},[],[322],{"type":46,"value":64},{"type":46,"value":324}," first",{"type":41,"tag":144,"props":326,"children":327},{},[328],{"type":46,"value":329},"Before drafting, always read the practice profile. The sections that drive the\ndraft:",{"type":41,"tag":331,"props":332,"children":333},"ul",{},[334,345,356,367,378,389],{"type":41,"tag":53,"props":335,"children":336},{},[337,343],{"type":41,"tag":59,"props":338,"children":340},{"className":339},[],[341],{"type":46,"value":342},"## Company profile",{"type":46,"value":344}," — AI role (Builder \u002F Deployer \u002F Both), regulatory footprint,\nexternal commitments, practice setting",{"type":41,"tag":53,"props":346,"children":347},{},[348,354],{"type":41,"tag":59,"props":349,"children":351},{"className":350},[],[352],{"type":46,"value":353},"## Use case registry",{"type":46,"value":355}," — what's already approved, conditional, or a red line",{"type":41,"tag":53,"props":357,"children":358},{},[359,365],{"type":41,"tag":59,"props":360,"children":362},{"className":361},[],[363],{"type":46,"value":364},"## AI policy commitments",{"type":46,"value":366}," — what a prior or current policy already says",{"type":41,"tag":53,"props":368,"children":369},{},[370,376],{"type":41,"tag":59,"props":371,"children":373},{"className":372},[],[374],{"type":46,"value":375},"## Vendor AI governance",{"type":46,"value":377}," — what the team already requires from vendors",{"type":41,"tag":53,"props":379,"children":380},{},[381,387],{"type":41,"tag":59,"props":382,"children":384},{"className":383},[],[385],{"type":46,"value":386},"## Governance team and escalation",{"type":46,"value":388}," — who approves, who escalates",{"type":41,"tag":53,"props":390,"children":391},{},[392,398],{"type":41,"tag":59,"props":393,"children":395},{"className":394},[],[396],{"type":46,"value":397},"## Who's using this",{"type":46,"value":399}," — Role (lawyer \u002F non-lawyer) governs the header and the\n\"adopt this\" framing",{"type":41,"tag":144,"props":401,"children":402},{},[403,405,410],{"type":46,"value":404},"If ",{"type":41,"tag":59,"props":406,"children":408},{"className":407},[],[409],{"type":46,"value":364},{"type":46,"value":411}," is populated, this is an UPDATE, not a new draft —\ntreat the existing policy as the base and propose changes. If it's empty, this\nis a first-cut draft.",{"type":41,"tag":137,"props":413,"children":415},{"id":414},"scope-interview-do-this-before-drafting",[416],{"type":46,"value":417},"Scope interview (do this BEFORE drafting)",{"type":41,"tag":144,"props":419,"children":420},{},[421],{"type":46,"value":422},"Ask the user which sections the policy should cover. Present as a checklist —\nthe user picks, you build. Do not pre-decide.",{"type":41,"tag":424,"props":425,"children":426},"blockquote",{},[427,435,538],{"type":41,"tag":144,"props":428,"children":429},{},[430],{"type":41,"tag":148,"props":431,"children":432},{},[433],{"type":46,"value":434},"What should the AI policy cover? Pick the sections you want in the draft:",{"type":41,"tag":49,"props":436,"children":437},{},[438,448,458,468,478,488,498,508,518,528],{"type":41,"tag":53,"props":439,"children":440},{},[441,446],{"type":41,"tag":148,"props":442,"children":443},{},[444],{"type":46,"value":445},"Scope",{"type":46,"value":447}," — who the policy applies to (all staff, certain roles, contractors), what tools it covers (GenAI only, all AI, specific vendors), what data is in\u002Fout of scope.",{"type":41,"tag":53,"props":449,"children":450},{},[451,456],{"type":41,"tag":148,"props":452,"children":453},{},[454],{"type":46,"value":455},"Permitted and prohibited uses",{"type":46,"value":457}," — the approved categories, the red lines, the \"ask first\" cases.",{"type":41,"tag":53,"props":459,"children":460},{},[461,466],{"type":41,"tag":148,"props":462,"children":463},{},[464],{"type":46,"value":465},"Approval and review",{"type":46,"value":467}," — who approves a new tool, who approves a new use case, how the review request is filed, what the SLA is.",{"type":41,"tag":53,"props":469,"children":470},{},[471,476],{"type":41,"tag":148,"props":472,"children":473},{},[474],{"type":46,"value":475},"Disclosure",{"type":46,"value":477}," — to clients (for firms), to courts, to counterparties, to employees, to end users of an AI feature.",{"type":41,"tag":53,"props":479,"children":480},{},[481,486],{"type":41,"tag":148,"props":482,"children":483},{},[484],{"type":46,"value":485},"Data handling",{"type":46,"value":487}," — what confidential\u002Fclient\u002Fprivileged data can go where, data residency, vendor retention terms, training-on-data posture.",{"type":41,"tag":53,"props":489,"children":490},{},[491,496],{"type":41,"tag":148,"props":492,"children":493},{},[494],{"type":46,"value":495},"Training and certification",{"type":46,"value":497}," — who has to take training, on what cadence, consequences for non-completion.",{"type":41,"tag":53,"props":499,"children":500},{},[501,506],{"type":41,"tag":148,"props":502,"children":503},{},[504],{"type":46,"value":505},"Incidents and reporting",{"type":46,"value":507}," — what counts as an AI incident, how to report, who handles.",{"type":41,"tag":53,"props":509,"children":510},{},[511,516],{"type":41,"tag":148,"props":512,"children":513},{},[514],{"type":46,"value":515},"Enforcement",{"type":46,"value":517}," — what happens when the policy is violated, link to disciplinary framework.",{"type":41,"tag":53,"props":519,"children":520},{},[521,526],{"type":41,"tag":148,"props":522,"children":523},{},[524],{"type":46,"value":525},"Review cadence and ownership",{"type":46,"value":527}," — how often the policy gets updated, who owns updates, how changes are communicated.",{"type":41,"tag":53,"props":529,"children":530},{},[531,536],{"type":41,"tag":148,"props":532,"children":533},{},[534],{"type":46,"value":535},"Glossary",{"type":46,"value":537}," — defined terms (GenAI, approved tool, high-risk use, consequential decision, confidential data, etc.).",{"type":41,"tag":144,"props":539,"children":540},{},[541],{"type":46,"value":542},"Default starter pack for a firm \u002F in-house legal team that's never had a policy: 1, 2, 3, 4, 5, 9. Skip the rest for v1.",{"type":41,"tag":144,"props":544,"children":545},{},[546],{"type":46,"value":547},"After the user picks, ask the second question:",{"type":41,"tag":424,"props":549,"children":550},{},[551,559],{"type":41,"tag":144,"props":552,"children":553},{},[554],{"type":41,"tag":148,"props":555,"children":556},{},[557],{"type":46,"value":558},"Two more inputs before I draft:",{"type":41,"tag":331,"props":560,"children":561},{},[562,572],{"type":41,"tag":53,"props":563,"children":564},{},[565,570],{"type":41,"tag":148,"props":566,"children":567},{},[568],{"type":46,"value":569},"Audience",{"type":46,"value":571}," — who's reading this? (All staff \u002F legal team only \u002F attorneys plus staff \u002F client-facing version also needed) This drives tone and the glossary.",{"type":41,"tag":53,"props":573,"children":574},{},[575,580],{"type":41,"tag":148,"props":576,"children":577},{},[578],{"type":46,"value":579},"Deployment context",{"type":46,"value":581}," — (a) law firm, (b) in-house legal at a company (policy covers legal or company-wide?), (c) legal aid \u002F clinic, (d) government. This drives which model policies I search.",{"type":41,"tag":137,"props":583,"children":585},{"id":584},"source-the-model-policies",[586],{"type":46,"value":587},"Source the model policies",{"type":41,"tag":144,"props":589,"children":590},{},[591],{"type":46,"value":592},"Before drafting, run web searches for the most recent published model AI\npolicies and guidance.",{"type":41,"tag":144,"props":594,"children":595},{},[596,608],{"type":41,"tag":148,"props":597,"children":598},{},[599,601,607],{"type":46,"value":600},"Derive the model policy sources from the practice profile's ",{"type":41,"tag":59,"props":602,"children":604},{"className":603},[],[605],{"type":46,"value":606},"## Regulatory footprint",{"type":46,"value":74},{"type":46,"value":609}," Don't hardcode US sources for a global user.",{"type":41,"tag":611,"props":612,"children":613},"table",{},[614,633],{"type":41,"tag":615,"props":616,"children":617},"thead",{},[618],{"type":41,"tag":619,"props":620,"children":621},"tr",{},[622,628],{"type":41,"tag":623,"props":624,"children":625},"th",{},[626],{"type":46,"value":627},"Jurisdiction",{"type":41,"tag":623,"props":629,"children":630},{},[631],{"type":46,"value":632},"Model policy sources",{"type":41,"tag":634,"props":635,"children":636},"tbody",{},[637,651,664,677,690,703,716],{"type":41,"tag":619,"props":638,"children":639},{},[640,646],{"type":41,"tag":641,"props":642,"children":643},"td",{},[644],{"type":46,"value":645},"US",{"type":41,"tag":641,"props":647,"children":648},{},[649],{"type":46,"value":650},"ABA Formal Opinion 512, state bar guidance (CA, FL, NY, TX all have published AI guidance), ILTA model policy, CLOC templates, peer firm published AI policies",{"type":41,"tag":619,"props":652,"children":653},{},[654,659],{"type":41,"tag":641,"props":655,"children":656},{},[657],{"type":46,"value":658},"UK",{"type":41,"tag":641,"props":660,"children":661},{},[662],{"type":46,"value":663},"Solicitors Regulation Authority risk outlook, Law Society AI principles, ICO AI guidance, Bar Council guidance",{"type":41,"tag":619,"props":665,"children":666},{},[667,672],{"type":41,"tag":641,"props":668,"children":669},{},[670],{"type":46,"value":671},"EU",{"type":41,"tag":641,"props":673,"children":674},{},[675],{"type":46,"value":676},"EU AI Act compliance framework (Article 4 AI literacy, Article 17 quality management), national DPA AI guidance (CNIL, DSB, Garante, AEPD), EDPB guidelines, EU institutions' AI policies",{"type":41,"tag":619,"props":678,"children":679},{},[680,685],{"type":41,"tag":641,"props":681,"children":682},{},[683],{"type":46,"value":684},"Australia",{"type":41,"tag":641,"props":686,"children":687},{},[688],{"type":46,"value":689},"Law Council of Australia AI guidelines, OAIC AI guidance, state law society guidance, Australian AI Ethics Framework",{"type":41,"tag":619,"props":691,"children":692},{},[693,698],{"type":41,"tag":641,"props":694,"children":695},{},[696],{"type":46,"value":697},"Singapore",{"type":41,"tag":641,"props":699,"children":700},{},[701],{"type":46,"value":702},"PDPC Model AI Governance Framework, MinLaw guidance, MAS AI fairness principles (for financial services)",{"type":41,"tag":619,"props":704,"children":705},{},[706,711],{"type":41,"tag":641,"props":707,"children":708},{},[709],{"type":46,"value":710},"Canada",{"type":41,"tag":641,"props":712,"children":713},{},[714],{"type":46,"value":715},"Law Society of Ontario\u002FBC\u002FAlberta AI guidance, OPC AI guidance, TBS Directive on Automated Decision-Making",{"type":41,"tag":619,"props":717,"children":718},{},[719,724],{"type":41,"tag":641,"props":720,"children":721},{},[722],{"type":46,"value":723},"Multi-jurisdiction",{"type":41,"tag":641,"props":725,"children":726},{},[727],{"type":46,"value":728},"Use all applicable, and note where they diverge (e.g., EU requires human oversight documentation US doesn't; Australia focuses on voluntary ethics frameworks; Singapore focuses on sectoral regulation)",{"type":41,"tag":144,"props":730,"children":731},{},[732,734,740],{"type":46,"value":733},"If the practice profile's footprint is empty or ",{"type":41,"tag":59,"props":735,"children":737},{"className":736},[],[738],{"type":46,"value":739},"[PLACEHOLDER]",{"type":46,"value":741},", ask: \"What jurisdiction(s) does your organization operate in? I'll draft from the model policies that match your regulatory environment and professional responsibility framework, not a US-centric template.\"",{"type":41,"tag":144,"props":743,"children":744},{},[745,747,752],{"type":46,"value":746},"For each source the draft uses, ",{"type":41,"tag":148,"props":748,"children":749},{},[750],{"type":46,"value":751},"record it in a \"Sources\" block at the top of\nthe output",{"type":46,"value":753}," with: name, URL, date accessed, and what the draft took from it.",{"type":41,"tag":144,"props":755,"children":756},{},[757],{"type":46,"value":758},"If a web search can't be run, note in the reviewer note: \"Could not run web\nsearch — draft sourced from training knowledge alone, verify against current\nversions of the cited sources before adopting.\" The verification log applies.",{"type":41,"tag":137,"props":760,"children":762},{"id":761},"the-draft",[763],{"type":46,"value":764},"The draft",{"type":41,"tag":144,"props":766,"children":767},{},[768,770,782],{"type":46,"value":769},"Output follows a consistent structure. ",{"type":41,"tag":148,"props":771,"children":772},{},[773,775,780],{"type":46,"value":774},"Every choice point gets a ",{"type":41,"tag":59,"props":776,"children":778},{"className":777},[],[779],{"type":46,"value":100},{"type":46,"value":781},"\nflag.",{"type":46,"value":783}," The user has to decide; the skill presents options.",{"type":41,"tag":785,"props":786,"children":788},"h3",{"id":787},"header",[789],{"type":46,"value":790},"Header",{"type":41,"tag":121,"props":792,"children":795},{"className":793,"code":794,"language":46},[124],"DRAFT FOR INTERNAL LEGAL REVIEW — NOT FOR DISTRIBUTION\nPrepared for: [firm \u002F company name from practice profile]\nDate: [today's date]\nPrepared by: ai-governance-legal policy-starter skill, adapted from published model policies\nNot for adoption, distribution, posting, or reliance until reviewed, adapted, and approved by [attorney \u002F GC \u002F managing partner \u002F executive committee per the governance team section of the practice profile].\n",[796],{"type":41,"tag":59,"props":797,"children":798},{"__ignoreMap":129},[799],{"type":46,"value":794},{"type":41,"tag":144,"props":801,"children":802},{},[803,805,810,812,818],{"type":46,"value":804},"When the Role in ",{"type":41,"tag":59,"props":806,"children":808},{"className":807},[],[809],{"type":46,"value":397},{"type":46,"value":811}," is Non-lawyer: add a second line under\nthe header — \"If you are not a licensed attorney, solicitor, barrister, or other\nauthorised legal professional in your jurisdiction, bring this draft to your\nattorney contact (",{"type":41,"tag":813,"props":814,"children":815},"span",{},[816],{"type":46,"value":817},"name from practice profile",{"type":46,"value":819},") before using any of it. This is\na starting draft for their review, not a policy you can adopt.\"",{"type":41,"tag":785,"props":821,"children":823},{"id":822},"sources-block-at-the-top-under-the-header",[824],{"type":46,"value":825},"Sources block (at the top, under the header)",{"type":41,"tag":144,"props":827,"children":828},{},[829],{"type":46,"value":830},"A table of the model policies \u002F guidance \u002F regulations the draft drew from:",{"type":41,"tag":611,"props":832,"children":833},{},[834,860],{"type":41,"tag":615,"props":835,"children":836},{},[837],{"type":41,"tag":619,"props":838,"children":839},{},[840,845,850,855],{"type":41,"tag":623,"props":841,"children":842},{},[843],{"type":46,"value":844},"Source",{"type":41,"tag":623,"props":846,"children":847},{},[848],{"type":46,"value":849},"URL",{"type":41,"tag":623,"props":851,"children":852},{},[853],{"type":46,"value":854},"Accessed",{"type":41,"tag":623,"props":856,"children":857},{},[858],{"type":46,"value":859},"What the draft took from it",{"type":41,"tag":634,"props":861,"children":862},{},[863,892,924,960,992,1019],{"type":41,"tag":619,"props":864,"children":865},{},[866,871,879,887],{"type":41,"tag":641,"props":867,"children":868},{},[869],{"type":46,"value":870},"ABA Formal Op. 512",{"type":41,"tag":641,"props":872,"children":873},{},[874],{"type":41,"tag":813,"props":875,"children":876},{},[877],{"type":46,"value":878},"url",{"type":41,"tag":641,"props":880,"children":881},{},[882],{"type":41,"tag":813,"props":883,"children":884},{},[885],{"type":46,"value":886},"date",{"type":41,"tag":641,"props":888,"children":889},{},[890],{"type":46,"value":891},"Disclosure and competence framing",{"type":41,"tag":619,"props":893,"children":894},{},[895,905,912,919],{"type":41,"tag":641,"props":896,"children":897},{},[898,900],{"type":46,"value":899},"ILTA Model AI Policy v.",{"type":41,"tag":813,"props":901,"children":902},{},[903],{"type":46,"value":904},"X",{"type":41,"tag":641,"props":906,"children":907},{},[908],{"type":41,"tag":813,"props":909,"children":910},{},[911],{"type":46,"value":878},{"type":41,"tag":641,"props":913,"children":914},{},[915],{"type":41,"tag":813,"props":916,"children":917},{},[918],{"type":46,"value":886},{"type":41,"tag":641,"props":920,"children":921},{},[922],{"type":46,"value":923},"Approval workflow, data handling",{"type":41,"tag":619,"props":925,"children":926},{},[927,941,948,955],{"type":41,"tag":641,"props":928,"children":929},{},[930,935,937],{"type":41,"tag":813,"props":931,"children":932},{},[933],{"type":46,"value":934},"State",{"type":46,"value":936}," Bar Op. ",{"type":41,"tag":813,"props":938,"children":939},{},[940],{"type":46,"value":904},{"type":41,"tag":641,"props":942,"children":943},{},[944],{"type":41,"tag":813,"props":945,"children":946},{},[947],{"type":46,"value":878},{"type":41,"tag":641,"props":949,"children":950},{},[951],{"type":41,"tag":813,"props":952,"children":953},{},[954],{"type":46,"value":886},{"type":41,"tag":641,"props":956,"children":957},{},[958],{"type":46,"value":959},"Disclosure to clients",{"type":41,"tag":619,"props":961,"children":962},{},[963,973,980,987],{"type":41,"tag":641,"props":964,"children":965},{},[966,971],{"type":41,"tag":813,"props":967,"children":968},{},[969],{"type":46,"value":970},"peer firm",{"type":46,"value":972}," published AI policy",{"type":41,"tag":641,"props":974,"children":975},{},[976],{"type":41,"tag":813,"props":977,"children":978},{},[979],{"type":46,"value":878},{"type":41,"tag":641,"props":981,"children":982},{},[983],{"type":41,"tag":813,"props":984,"children":985},{},[986],{"type":46,"value":886},{"type":41,"tag":641,"props":988,"children":989},{},[990],{"type":46,"value":991},"Scope language",{"type":41,"tag":619,"props":993,"children":994},{},[995,1000,1007,1014],{"type":41,"tag":641,"props":996,"children":997},{},[998],{"type":46,"value":999},"Colorado SB 24-205",{"type":41,"tag":641,"props":1001,"children":1002},{},[1003],{"type":41,"tag":813,"props":1004,"children":1005},{},[1006],{"type":46,"value":878},{"type":41,"tag":641,"props":1008,"children":1009},{},[1010],{"type":41,"tag":813,"props":1011,"children":1012},{},[1013],{"type":46,"value":886},{"type":41,"tag":641,"props":1015,"children":1016},{},[1017],{"type":46,"value":1018},"High-risk AI definition",{"type":41,"tag":619,"props":1020,"children":1021},{},[1022,1031,1038,1045],{"type":41,"tag":641,"props":1023,"children":1024},{},[1025,1027],{"type":46,"value":1026},"EU AI Act, Art. ",{"type":41,"tag":813,"props":1028,"children":1029},{},[1030],{"type":46,"value":904},{"type":41,"tag":641,"props":1032,"children":1033},{},[1034],{"type":41,"tag":813,"props":1035,"children":1036},{},[1037],{"type":46,"value":878},{"type":41,"tag":641,"props":1039,"children":1040},{},[1041],{"type":41,"tag":813,"props":1042,"children":1043},{},[1044],{"type":46,"value":886},{"type":41,"tag":641,"props":1046,"children":1047},{},[1048],{"type":46,"value":1049},"Vendor flow-down",{"type":41,"tag":785,"props":1051,"children":1053},{"id":1052},"executive-summary",[1054],{"type":46,"value":1055},"Executive summary",{"type":41,"tag":144,"props":1057,"children":1058},{},[1059],{"type":46,"value":1060},"Three paragraphs max. What the policy does, who it binds, what the reader has\nto do before it takes effect.",{"type":41,"tag":785,"props":1062,"children":1064},{"id":1063},"the-sections",[1065],{"type":46,"value":1066},"The sections",{"type":41,"tag":144,"props":1068,"children":1069},{},[1070],{"type":46,"value":1071},"Only the sections the user picked, in the order above. For each:",{"type":41,"tag":331,"props":1073,"children":1074},{},[1075,1087,1134,1152],{"type":41,"tag":53,"props":1076,"children":1077},{},[1078,1080,1085],{"type":46,"value":1079},"A ",{"type":41,"tag":148,"props":1081,"children":1082},{},[1083],{"type":46,"value":1084},"header and scope",{"type":46,"value":1086}," sentence.",{"type":41,"tag":53,"props":1088,"children":1089},{},[1090,1092,1097,1099,1104,1106,1111,1113,1119,1121,1126,1132],{"type":46,"value":1091},"The ",{"type":41,"tag":148,"props":1093,"children":1094},{},[1095],{"type":46,"value":1096},"substantive rules",{"type":46,"value":1098},", adapted from the cited model policies. Every\nspecific threshold, number, named tool, named vendor, or escalation contact\nis ",{"type":41,"tag":59,"props":1100,"children":1102},{"className":1101},[],[1103],{"type":46,"value":100},{"type":46,"value":1105},". Example: \"Confidential client data may not be entered into\n",{"type":41,"tag":813,"props":1107,"children":1108},{},[1109],{"type":46,"value":1110},"general-purpose consumer AI tools",{"type":46,"value":1112}," ",{"type":41,"tag":59,"props":1114,"children":1116},{"className":1115},[],[1117],{"type":46,"value":1118},"[review — list tools, or reference the approved-tools list]",{"type":46,"value":1120},". Use of such data in ",{"type":41,"tag":813,"props":1122,"children":1123},{},[1124],{"type":46,"value":1125},"approved firm-licensed tools",{"type":41,"tag":59,"props":1127,"children":1129},{"className":1128},[],[1130],{"type":46,"value":1131},"[review — list tools]",{"type":46,"value":1133}," is permitted subject to the data handling section.\"",{"type":41,"tag":53,"props":1135,"children":1136},{},[1137,1142,1144,1150],{"type":41,"tag":148,"props":1138,"children":1139},{},[1140],{"type":46,"value":1141},"Source attribution",{"type":46,"value":1143}," inline where a rule is adapted from a specific source.\nExample: \"Attorneys must verify the accuracy of all AI-generated work product\nbefore using it in representation of a client ",{"type":41,"tag":59,"props":1145,"children":1147},{"className":1146},[],[1148],{"type":46,"value":1149},"[ABA Formal Op. 512]",{"type":46,"value":1151},".\"",{"type":41,"tag":53,"props":1153,"children":1154},{},[1155,1160,1162,1167],{"type":41,"tag":148,"props":1156,"children":1157},{},[1158],{"type":46,"value":1159},"Open questions",{"type":46,"value":1161}," at the bottom of each section — 2-3 decisions the attorney\nneeds to make before the section is ready. These are distinct from inline\n",{"type":41,"tag":59,"props":1163,"children":1165},{"className":1164},[],[1166],{"type":46,"value":100},{"type":46,"value":1168}," flags — these are the \"we don't have a position here yet\" items,\nnot the \"fill in the specifics\" items.",{"type":41,"tag":785,"props":1170,"children":1172},{"id":1171},"adoption-checklist",[1173],{"type":46,"value":1174},"Adoption checklist",{"type":41,"tag":144,"props":1176,"children":1177},{},[1178],{"type":46,"value":1179},"At the end of the draft, a checklist of the things that have to happen before\nthe policy is adopted. Don't invent these — pull from the practice profile's\ngovernance team and escalation section. Typical items:",{"type":41,"tag":331,"props":1181,"children":1184},{"className":1182},[1183],"contains-task-list",[1185,1204,1218,1232,1247,1256,1265,1279,1294],{"type":41,"tag":53,"props":1186,"children":1189},{"className":1187},[1188],"task-list-item",[1190,1196,1198],{"type":41,"tag":1191,"props":1192,"children":1195},"input",{"disabled":1193,"type":1194},true,"checkbox",[],{"type":46,"value":1197}," Review by GC \u002F managing partner ",{"type":41,"tag":59,"props":1199,"children":1201},{"className":1200},[],[1202],{"type":46,"value":1203},"[review — name]",{"type":41,"tag":53,"props":1205,"children":1207},{"className":1206},[1188],[1208,1211,1213],{"type":41,"tag":1191,"props":1209,"children":1210},{"disabled":1193,"type":1194},[],{"type":46,"value":1212}," Review by IT \u002F security ",{"type":41,"tag":59,"props":1214,"children":1216},{"className":1215},[],[1217],{"type":46,"value":1203},{"type":41,"tag":53,"props":1219,"children":1221},{"className":1220},[1188],[1222,1225,1227],{"type":41,"tag":1191,"props":1223,"children":1224},{"disabled":1193,"type":1194},[],{"type":46,"value":1226}," Review by HR (for enforcement \u002F training sections) ",{"type":41,"tag":59,"props":1228,"children":1230},{"className":1229},[],[1231],{"type":46,"value":1203},{"type":41,"tag":53,"props":1233,"children":1235},{"className":1234},[1188],[1236,1239,1241],{"type":41,"tag":1191,"props":1237,"children":1238},{"disabled":1193,"type":1194},[],{"type":46,"value":1240}," Board \u002F executive committee approval (if required) ",{"type":41,"tag":59,"props":1242,"children":1244},{"className":1243},[],[1245],{"type":46,"value":1246},"[review — confirm whether required]",{"type":41,"tag":53,"props":1248,"children":1250},{"className":1249},[1188],[1251,1254],{"type":41,"tag":1191,"props":1252,"children":1253},{"disabled":1193,"type":1194},[],{"type":46,"value":1255}," Training materials drafted",{"type":41,"tag":53,"props":1257,"children":1259},{"className":1258},[1188],[1260,1263],{"type":41,"tag":1191,"props":1261,"children":1262},{"disabled":1193,"type":1194},[],{"type":46,"value":1264}," Announcement drafted",{"type":41,"tag":53,"props":1266,"children":1268},{"className":1267},[1188],[1269,1272,1274],{"type":41,"tag":1191,"props":1270,"children":1271},{"disabled":1193,"type":1194},[],{"type":46,"value":1273}," Effective date set ",{"type":41,"tag":59,"props":1275,"children":1277},{"className":1276},[],[1278],{"type":46,"value":100},{"type":41,"tag":53,"props":1280,"children":1282},{"className":1281},[1188],[1283,1286,1288],{"type":41,"tag":1191,"props":1284,"children":1285},{"disabled":1193,"type":1194},[],{"type":46,"value":1287}," Review cadence calendared ",{"type":41,"tag":59,"props":1289,"children":1291},{"className":1290},[],[1292],{"type":46,"value":1293},"[review — annual is typical]",{"type":41,"tag":53,"props":1295,"children":1297},{"className":1296},[1188],[1298,1301,1303,1308],{"type":41,"tag":1191,"props":1299,"children":1300},{"disabled":1193,"type":1194},[],{"type":46,"value":1302}," Add policy to the ",{"type":41,"tag":59,"props":1304,"children":1306},{"className":1305},[],[1307],{"type":46,"value":364},{"type":46,"value":1309}," section of the practice\nprofile once adopted",{"type":41,"tag":785,"props":1311,"children":1313},{"id":1312},"reviewer-note",[1314],{"type":46,"value":1315},"Reviewer note",{"type":41,"tag":144,"props":1317,"children":1318},{},[1319,1321,1327],{"type":46,"value":1320},"The standard reviewer note above the header, per the ",{"type":41,"tag":59,"props":1322,"children":1324},{"className":1323},[],[1325],{"type":46,"value":1326},"## Outputs",{"type":46,"value":1328}," section of\nthe practice profile. Use the block format:",{"type":41,"tag":424,"props":1330,"children":1331},{},[1332,1340],{"type":41,"tag":144,"props":1333,"children":1334},{},[1335],{"type":41,"tag":148,"props":1336,"children":1337},{},[1338],{"type":46,"value":1339},"⚠️ Reviewer note",{"type":41,"tag":331,"props":1341,"children":1342},{},[1343,1353,1370,1397,1411],{"type":41,"tag":53,"props":1344,"children":1345},{},[1346,1351],{"type":41,"tag":148,"props":1347,"children":1348},{},[1349],{"type":46,"value":1350},"Sources:",{"type":46,"value":1352}," web search ✓ \u002F not connected — cites from training knowledge",{"type":41,"tag":53,"props":1354,"children":1355},{},[1356,1361,1363,1368],{"type":41,"tag":148,"props":1357,"children":1358},{},[1359],{"type":46,"value":1360},"Read:",{"type":46,"value":1362}," practice profile · ",{"type":41,"tag":813,"props":1364,"children":1365},{},[1366],{"type":46,"value":1367},"N",{"type":46,"value":1369}," published model policies",{"type":41,"tag":53,"props":1371,"children":1372},{},[1373,1378,1379,1383,1384,1389,1391,1395],{"type":41,"tag":148,"props":1374,"children":1375},{},[1376],{"type":46,"value":1377},"Flagged for your judgment:",{"type":46,"value":1112},{"type":41,"tag":813,"props":1380,"children":1381},{},[1382],{"type":46,"value":1367},{"type":46,"value":1112},{"type":41,"tag":59,"props":1385,"children":1387},{"className":1386},[],[1388],{"type":46,"value":100},{"type":46,"value":1390}," items inline · ",{"type":41,"tag":813,"props":1392,"children":1393},{},[1394],{"type":46,"value":1367},{"type":46,"value":1396}," open questions per section",{"type":41,"tag":53,"props":1398,"children":1399},{},[1400,1405,1407],{"type":41,"tag":148,"props":1401,"children":1402},{},[1403],{"type":46,"value":1404},"Currency:",{"type":46,"value":1406}," searched for developments since ",{"type":41,"tag":813,"props":1408,"children":1409},{},[1410],{"type":46,"value":886},{"type":41,"tag":53,"props":1412,"children":1413},{},[1414,1419,1421,1426],{"type":41,"tag":148,"props":1415,"children":1416},{},[1417],{"type":46,"value":1418},"Before relying:",{"type":46,"value":1420}," this is a DRAFT — bring to ",{"type":41,"tag":813,"props":1422,"children":1423},{},[1424],{"type":46,"value":1425},"approver from practice profile",{"type":46,"value":1427},", don't distribute until adopted",{"type":41,"tag":137,"props":1429,"children":1431},{"id":1430},"donts",[1432],{"type":46,"value":1433},"Don'ts",{"type":41,"tag":331,"props":1435,"children":1436},{},[1437,1454,1471,1488,1498,1508,1525],{"type":41,"tag":53,"props":1438,"children":1439},{},[1440,1445,1447,1453],{"type":41,"tag":148,"props":1441,"children":1442},{},[1443],{"type":46,"value":1444},"Don't invent policy language.",{"type":46,"value":1446}," Every substantive rule in the draft must be\ntraceable to a cited source or flagged ",{"type":41,"tag":59,"props":1448,"children":1450},{"className":1449},[],[1451],{"type":46,"value":1452},"[review — adapted, no direct source]",{"type":46,"value":74},{"type":41,"tag":53,"props":1455,"children":1456},{},[1457,1462,1464,1469],{"type":41,"tag":148,"props":1458,"children":1459},{},[1460],{"type":46,"value":1461},"Don't pick the hard calls for the attorney.",{"type":46,"value":1463}," \"Should paralegals be\npermitted to use AI for first-draft work?\" is a ",{"type":41,"tag":59,"props":1465,"children":1467},{"className":1466},[],[1468],{"type":46,"value":100},{"type":46,"value":1470},", not a recommended\nposition.",{"type":41,"tag":53,"props":1472,"children":1473},{},[1474,1479,1481,1486],{"type":41,"tag":148,"props":1475,"children":1476},{},[1477],{"type":46,"value":1478},"Don't produce a finished-looking policy.",{"type":46,"value":1480}," The header, the reviewer note,\nand the ",{"type":41,"tag":59,"props":1482,"children":1484},{"className":1483},[],[1485],{"type":46,"value":100},{"type":46,"value":1487}," flags throughout are the signal that this is a draft. Do\nnot soften them.",{"type":41,"tag":53,"props":1489,"children":1490},{},[1491,1496],{"type":41,"tag":148,"props":1492,"children":1493},{},[1494],{"type":46,"value":1495},"Don't skip the scope interview.",{"type":46,"value":1497}," If the user says \"just draft a full\npolicy,\" push back: \"A policy that tries to cover everything covers nothing.\nWhich sections do you want? Here's the checklist.\" One round of negotiation\nis fine — two is also fine. Drafting without scope is the failure mode.",{"type":41,"tag":53,"props":1499,"children":1500},{},[1501,1506],{"type":41,"tag":148,"props":1502,"children":1503},{},[1504],{"type":46,"value":1505},"Don't generate section content the user didn't ask for.",{"type":46,"value":1507}," If they picked 1,\n2, 3, 4, 5, 9, do those. Don't add section 6 because \"a real policy needs\ntraining.\"",{"type":41,"tag":53,"props":1509,"children":1510},{},[1511,1516,1518,1523],{"type":41,"tag":148,"props":1512,"children":1513},{},[1514],{"type":46,"value":1515},"Don't recommend a specific vendor, tool, or consequence.",{"type":46,"value":1517}," Flag those\n",{"type":41,"tag":59,"props":1519,"children":1521},{"className":1520},[],[1522],{"type":46,"value":100},{"type":46,"value":1524}," with context on what a typical decision would be, not what the\nuser's should be.",{"type":41,"tag":53,"props":1526,"children":1527},{},[1528,1533],{"type":41,"tag":148,"props":1529,"children":1530},{},[1531],{"type":46,"value":1532},"Don't promise legal sufficiency.",{"type":46,"value":1534}," The draft is a starting point for\nattorney review, not a tested policy.",{"type":41,"tag":137,"props":1536,"children":1538},{"id":1537},"handoffs",[1539],{"type":46,"value":1540},"Handoffs",{"type":41,"tag":144,"props":1542,"children":1543},{},[1544],{"type":46,"value":1545},"After the draft is produced, close with the decision tree from the practice\nprofile. The most common next steps:",{"type":41,"tag":49,"props":1547,"children":1548},{},[1549,1566,1576,1594,1611],{"type":41,"tag":53,"props":1550,"children":1551},{},[1552,1557,1559,1564],{"type":41,"tag":148,"props":1553,"children":1554},{},[1555],{"type":46,"value":1556},"Tune the draft",{"type":46,"value":1558}," — the user walks through the ",{"type":41,"tag":59,"props":1560,"children":1562},{"className":1561},[],[1563],{"type":46,"value":100},{"type":46,"value":1565}," flags and resolves\nthem with the attorney; the skill re-runs with the decisions baked in.",{"type":41,"tag":53,"props":1567,"children":1568},{},[1569,1574],{"type":41,"tag":148,"props":1570,"children":1571},{},[1572],{"type":46,"value":1573},"Stakeholder summary",{"type":46,"value":1575}," — produce a one-page version for the board or\nexecutive committee explaining what the policy does and doesn't do.",{"type":41,"tag":53,"props":1577,"children":1578},{},[1579,1584,1586,1592],{"type":41,"tag":148,"props":1580,"children":1581},{},[1582],{"type":46,"value":1583},"Training materials",{"type":46,"value":1585}," — once the policy is adopted, ",{"type":41,"tag":59,"props":1587,"children":1589},{"className":1588},[],[1590],{"type":46,"value":1591},"\u002Fai-governance-legal:aia-generation",{"type":46,"value":1593}," can be used to produce per-use-case training notes.",{"type":41,"tag":53,"props":1595,"children":1596},{},[1597,1602,1603,1609],{"type":41,"tag":148,"props":1598,"children":1599},{},[1600],{"type":46,"value":1601},"Vendor sweep",{"type":46,"value":1585},{"type":41,"tag":59,"props":1604,"children":1606},{"className":1605},[],[1607],{"type":46,"value":1608},"\u002Fai-governance-legal:vendor-ai-review",{"type":46,"value":1610}," should be run against the vendors the policy references to check conformance.",{"type":41,"tag":53,"props":1612,"children":1613},{},[1614,1619,1621,1627],{"type":41,"tag":148,"props":1615,"children":1616},{},[1617],{"type":46,"value":1618},"Gap check against new regulation",{"type":46,"value":1620}," — pair with ",{"type":41,"tag":59,"props":1622,"children":1624},{"className":1623},[],[1625],{"type":46,"value":1626},"\u002Fai-governance-legal:reg-gap-analysis",{"type":46,"value":1628}," to test the draft against a specific regulation or guidance before adoption.",{"type":41,"tag":137,"props":1630,"children":1632},{"id":1631},"output-scope-reminder",[1633],{"type":46,"value":1634},"Output scope reminder",{"type":41,"tag":144,"props":1636,"children":1637},{},[1638,1640,1645],{"type":46,"value":1639},"The document this skill produces reaches HR, IT, and the broader business — not\njust legal. Keep the language plain enough for non-lawyers to follow. The legal\nprecision is in the ",{"type":41,"tag":59,"props":1641,"children":1643},{"className":1642},[],[1644],{"type":46,"value":100},{"type":46,"value":1646}," flags and the sources, not in jargon.",{"items":1648,"total":1744},[1649,1663,1680,1695,1707,1718,1729],{"slug":1650,"name":1650,"fn":1651,"description":1652,"org":1653,"tags":1654,"stars":23,"repoUrl":24,"updatedAt":1662},"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},[1655,1658,1661],{"name":1656,"slug":1657,"type":16},"Compliance","compliance",{"name":1659,"slug":1660,"type":16},"Governance","governance",{"name":21,"slug":22,"type":16},"2026-05-14T06:02:19.677579",{"slug":1664,"name":1664,"fn":1665,"description":1666,"org":1667,"tags":1668,"stars":23,"repoUrl":24,"updatedAt":1679},"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},[1669,1672,1675,1676],{"name":1670,"slug":1671,"type":16},"Automation","automation",{"name":1673,"slug":1674,"type":16},"Contracts","contracts",{"name":21,"slug":22,"type":16},{"name":1677,"slug":1678,"type":16},"QA","qa","2026-05-14T06:01:31.00555",{"slug":1681,"name":1681,"fn":1682,"description":1683,"org":1684,"tags":1685,"stars":23,"repoUrl":24,"updatedAt":1694},"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},[1686,1687,1688,1691],{"name":21,"slug":22,"type":16},{"name":18,"slug":19,"type":16},{"name":1689,"slug":1690,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1692,"slug":1693,"type":16},"Risk Assessment","risk-assessment","2026-05-13T06:03:19.61029",{"slug":1696,"name":1696,"fn":1697,"description":1698,"org":1699,"tags":1700,"stars":23,"repoUrl":24,"updatedAt":1706},"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},[1701,1702,1705],{"name":1673,"slug":1674,"type":16},{"name":1703,"slug":1704,"type":16},"Documents","documents",{"name":21,"slug":22,"type":16},"2026-05-13T06:03:34.070339",{"slug":1708,"name":1708,"fn":1709,"description":1710,"org":1711,"tags":1712,"stars":23,"repoUrl":24,"updatedAt":1717},"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},[1713,1714],{"name":1670,"slug":1671,"type":16},{"name":1715,"slug":1716,"type":16},"Plugin Development","plugin-development","2026-05-13T06:02:55.642269",{"slug":1719,"name":1719,"fn":1720,"description":1721,"org":1722,"tags":1723,"stars":23,"repoUrl":24,"updatedAt":1728},"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},[1724,1727],{"name":1725,"slug":1726,"type":16},"Education","education",{"name":21,"slug":22,"type":16},"2026-07-24T05:41:43.01243",{"slug":1730,"name":1730,"fn":1731,"description":1732,"org":1733,"tags":1734,"stars":23,"repoUrl":24,"updatedAt":1743},"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},[1735,1738,1739,1740],{"name":1736,"slug":1737,"type":16},"Documentation","documentation",{"name":1659,"slug":1660,"type":16},{"name":21,"slug":22,"type":16},{"name":1741,"slug":1742,"type":16},"Meetings","meetings","2026-05-14T06:01:29.792942",118,{"items":1746,"total":1927},[1747,1768,1782,1794,1813,1822,1841,1861,1875,1890,1898,1911],{"slug":1748,"name":1748,"fn":1749,"description":1750,"org":1751,"tags":1752,"stars":1765,"repoUrl":1766,"updatedAt":1767},"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},[1753,1756,1759,1762],{"name":1754,"slug":1755,"type":16},"Creative","creative",{"name":1757,"slug":1758,"type":16},"Design","design",{"name":1760,"slug":1761,"type":16},"Generative Art","generative-art",{"name":1763,"slug":1764,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1769,"name":1769,"fn":1770,"description":1771,"org":1772,"tags":1773,"stars":1765,"repoUrl":1766,"updatedAt":1781},"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},[1774,1777,1778],{"name":1775,"slug":1776,"type":16},"Branding","branding",{"name":1757,"slug":1758,"type":16},{"name":1779,"slug":1780,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1783,"name":1783,"fn":1784,"description":1785,"org":1786,"tags":1787,"stars":1765,"repoUrl":1766,"updatedAt":1793},"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},[1788,1789,1790],{"name":1754,"slug":1755,"type":16},{"name":1757,"slug":1758,"type":16},{"name":1791,"slug":1792,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1795,"name":1795,"fn":1796,"description":1797,"org":1798,"tags":1799,"stars":1765,"repoUrl":1766,"updatedAt":1812},"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},[1800,1803,1804,1807,1809],{"name":1801,"slug":1802,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1805,"slug":1806,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1808,"slug":1795,"type":16},"Claude API",{"name":1810,"slug":1811,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1814,"name":1814,"fn":1815,"description":1816,"org":1817,"tags":1818,"stars":1765,"repoUrl":1766,"updatedAt":1821},"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},[1819,1820],{"name":1736,"slug":1737,"type":16},{"name":14,"slug":15,"type":16},"2026-04-06T17:56:14.18897",{"slug":1823,"name":1823,"fn":1824,"description":1825,"org":1826,"tags":1827,"stars":1765,"repoUrl":1766,"updatedAt":1840},"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},[1828,1829,1831,1834,1837],{"name":1703,"slug":1704,"type":16},{"name":1830,"slug":1823,"type":16},"DOCX",{"name":1832,"slug":1833,"type":16},"Office","office",{"name":1835,"slug":1836,"type":16},"Templates","templates",{"name":1838,"slug":1839,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1842,"name":1842,"fn":1843,"description":1844,"org":1845,"tags":1846,"stars":1765,"repoUrl":1766,"updatedAt":1860},"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},[1847,1848,1851,1854,1857],{"name":1757,"slug":1758,"type":16},{"name":1849,"slug":1850,"type":16},"Frontend","frontend",{"name":1852,"slug":1853,"type":16},"React","react",{"name":1855,"slug":1856,"type":16},"Tailwind CSS","tailwind-css",{"name":1858,"slug":1859,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1862,"name":1862,"fn":1863,"description":1864,"org":1865,"tags":1866,"stars":1765,"repoUrl":1766,"updatedAt":1874},"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},[1867,1870,1871],{"name":1868,"slug":1869,"type":16},"Communications","communications",{"name":1835,"slug":1836,"type":16},{"name":1872,"slug":1873,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1876,"name":1876,"fn":1877,"description":1878,"org":1879,"tags":1880,"stars":1765,"repoUrl":1766,"updatedAt":1889},"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},[1881,1882,1885,1886],{"name":1801,"slug":1802,"type":16},{"name":1883,"slug":1884,"type":16},"API Development","api-development",{"name":1810,"slug":1811,"type":16},{"name":1887,"slug":1888,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1792,"name":1792,"fn":1891,"description":1892,"org":1893,"tags":1894,"stars":1765,"repoUrl":1766,"updatedAt":1897},"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},[1895,1896],{"name":1703,"slug":1704,"type":16},{"name":1791,"slug":1792,"type":16},"2026-04-06T17:56:02.483316",{"slug":1899,"name":1899,"fn":1900,"description":1901,"org":1902,"tags":1903,"stars":1765,"repoUrl":1766,"updatedAt":1910},"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},[1904,1907],{"name":1905,"slug":1906,"type":16},"PowerPoint","powerpoint",{"name":1908,"slug":1909,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1912,"name":1912,"fn":1913,"description":1914,"org":1915,"tags":1916,"stars":1765,"repoUrl":1766,"updatedAt":1926},"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},[1917,1918,1919,1922,1925],{"name":1801,"slug":1802,"type":16},{"name":1736,"slug":1737,"type":16},{"name":1920,"slug":1921,"type":16},"Evals","evals",{"name":1923,"slug":1924,"type":16},"Performance","performance",{"name":14,"slug":15,"type":16},"2026-04-19T06:45:40.804",490]