[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-ai-tool-handoff":3,"mdc-nbhh9e-key":37,"related-org-anthropic-ai-tool-handoff":1313,"related-repo-anthropic-ai-tool-handoff":1502},{"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},"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},"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},"Contracts","contracts","tag",{"name":18,"slug":19,"type":16},"Automation","automation",{"name":21,"slug":22,"type":16},"QA","qa",{"name":24,"slug":25,"type":16},"Legal","legal",8721,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","2026-05-14T06:01:31.00555",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\u002Fcorporate-legal\u002Fskills\u002Fai-tool-handoff","---\nname: ai-tool-handoff\ndescription: >\n  Detects when Luminance, Kira, or a similar bulk-review tool is in use,\n  hands off the high-volume clause extraction to it, and QAs its output\n  per the trust level in `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`. Use when user says \"send to Luminance\",\n  \"bulk review\", \"AI extraction\", or when diligence-issue-extraction hits\n  a high-volume category.\n---\n\n# AI Tool Handoff\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 `\u002Fcorporate-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\u002Fcorporate-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Purpose\n\nLuminance and Kira are good at one thing: reading 500 contracts and finding every change-of-control clause. They're less good at judgment — deciding whether a particular CoC provision is actually triggered by this deal structure.\n\nThis skill hands off the bulk extraction to the right tool, then runs the QA layer on what comes back.\n\n**Before you hand off:** try `tabular-review` first (`\u002Fcorporate-legal:tabular-review`). For anything the user's environment can handle — a few hundred documents, a defined column schema — native tabular review is faster to set up, has no per-document cost, and keeps the work product local. Hand off to Luminance\u002FKira when the corpus is genuinely too large, the team already has a license and workflow, or the matter requires a tool with a validated provenance chain.\n\n## Load context\n\n`~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md` → AI-assisted review:\n- Tool in use (Luminance \u002F Kira \u002F none)\n- What it's used for (which clause types)\n- Trust level (use as-is \u002F spot-check \u002F full re-review)\n- Handoff process (who loads, who QAs)\n\nIf `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md` says no AI tool → this skill is a no-op. Everything goes through diligence-issue-extraction directly.\n\n## When to hand off\n\nHand off when all of:\n- Category has >50 documents (below that, faster to just read them)\n- Extraction target is a clause type the tool is good at (CoC, assignment, exclusivity, MFN, termination, auto-renewal)\n- Documents are reasonably uniform (all customer contracts on similar paper — not a mix of contracts, letters, and board minutes)\n\nDon't hand off:\n- Bespoke or heavily negotiated documents\n- Side letters and amendments (context-dependent, tools miss the interaction with the main agreement)\n- Anything where the question is \"what does this mean for the deal\" not \"does this clause exist\"\n\n## The handoff\n\n### Step 1: Prepare the batch\n\n- Identify documents for the batch (from VDR inventory)\n- Specify extraction targets per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md` (which clause types)\n- Note the materiality threshold so tool output can be filtered\n\n### Step 2: Load (or instruct the loader)\n\nPer `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md` — who loads. If it's you, generate the load instructions. If it's someone else, generate the request:\n\n```markdown\n## [Tool] Load Request — [Deal code] — [Category]\n\n**Documents:** [N] docs from VDR folder [path]\n**Load to:** [Tool workspace\u002Fmatter]\n**Extraction targets:**\n- Change of control \u002F assignment\n- Exclusivity\n- [etc. per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`]\n\n**Filter output:** Flag only where extraction target is present — no need for \"no CoC clause found\" for every doc.\n\n**Return by:** [date]\n```\n\n### Step 3: QA the output\n\nWhen the tool returns results, apply the trust level:\n\n**\"Use as-is\":** Ingest directly into diligence findings. (Only if `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md` says this — it's rare.)\n\n**\"Spot-check X%\":** Randomly sample X% of flagged documents. For each, read the actual clause and compare to the tool's extraction. If error rate is low, accept the batch. If errors found, widen the sample.\n\n**\"Full human review of flagged\":** Tool narrows the universe (500 docs → 80 with CoC clauses). Human reads all 80. Tool saved the time of reading the 420 clean ones.\n\n### Step 4: Judgment layer\n\nThe tool found the clauses. Now apply judgment:\n\nFor each flagged CoC provision: is it actually triggered by this deal?\n- Stock sale vs. asset sale vs. merger — different triggers\n- \"Change of control\" defined how in the contract — majority ownership? board control? something else?\n- Is there a carve-out for this type of transaction?\n\nThis is the part the tool can't do. Output goes to diligence findings in house format.\n\n## Output\n\n> The QA summary below is derived from VDR documents that are privileged, confidential, or both. It inherits the sources' privilege and confidentiality status — distribution beyond the privilege circle can waive privilege. Store with the matter's privileged files.\n\n```markdown\n## AI Tool Handoff Summary — [Category]\n\n**Tool:** [Luminance \u002F Kira]\n**Documents processed:** [N]\n**Extraction targets:** [clause types]\n\n### QA\n\n**Trust level:** [per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`]\n**Sample size:** [N] docs spot-checked\n**Error rate:** [X]% — [Accepted \u002F Widened sample \u002F Full re-review triggered]\n\n### Results\n\n| Clause type | Docs flagged | After judgment layer | Material |\n|---|---|---|---|\n| Change of control | [N] | [N actually triggered by deal structure] | [N above threshold] |\n| Assignment | [N] | [N] | [N] |\n\n**→ [N] findings added to diligence issues**\n**→ [N] consents added to closing checklist**\n```\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 run Luminance or Kira — it manages the handoff and QA. A human (or the tool's own interface) runs the extraction.\n- It doesn't replace the tool's output with its own judgment entirely — if `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md` says spot-check 10%, check 10%, not 100%.\n- It doesn't decide the trust level — that's in `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`, set at cold-start based on the team's experience with the tool.\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,50,57,141,145,151,156,161,187,193,204,229,241,247,252,270,275,293,299,306,331,337,349,632,638,643,660,670,680,686,691,696,714,719,725,734,1250,1256,1269,1275,1307],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","AI Tool Handoff",{"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},"\u002Fcorporate-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\u002Fcorporate-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},"Luminance and Kira are good at one thing: reading 500 contracts and finding every change-of-control clause. They're less good at judgment — deciding whether a particular CoC provision is actually triggered by this deal structure.",{"type":43,"tag":58,"props":157,"children":158},{},[159],{"type":48,"value":160},"This skill hands off the bulk extraction to the right tool, then runs the QA layer on what comes back.",{"type":43,"tag":58,"props":162,"children":163},{},[164,169,171,177,179,185],{"type":43,"tag":62,"props":165,"children":166},{},[167],{"type":48,"value":168},"Before you hand off:",{"type":48,"value":170}," try ",{"type":43,"tag":70,"props":172,"children":174},{"className":173},[],[175],{"type":48,"value":176},"tabular-review",{"type":48,"value":178}," first (",{"type":43,"tag":70,"props":180,"children":182},{"className":181},[],[183],{"type":48,"value":184},"\u002Fcorporate-legal:tabular-review",{"type":48,"value":186},"). For anything the user's environment can handle — a few hundred documents, a defined column schema — native tabular review is faster to set up, has no per-document cost, and keeps the work product local. Hand off to Luminance\u002FKira when the corpus is genuinely too large, the team already has a license and workflow, or the matter requires a tool with a validated provenance chain.",{"type":43,"tag":51,"props":188,"children":190},{"id":189},"load-context",[191],{"type":48,"value":192},"Load context",{"type":43,"tag":58,"props":194,"children":195},{},[196,202],{"type":43,"tag":70,"props":197,"children":199},{"className":198},[],[200],{"type":48,"value":201},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md",{"type":48,"value":203}," → AI-assisted review:",{"type":43,"tag":205,"props":206,"children":207},"ul",{},[208,214,219,224],{"type":43,"tag":209,"props":210,"children":211},"li",{},[212],{"type":48,"value":213},"Tool in use (Luminance \u002F Kira \u002F none)",{"type":43,"tag":209,"props":215,"children":216},{},[217],{"type":48,"value":218},"What it's used for (which clause types)",{"type":43,"tag":209,"props":220,"children":221},{},[222],{"type":48,"value":223},"Trust level (use as-is \u002F spot-check \u002F full re-review)",{"type":43,"tag":209,"props":225,"children":226},{},[227],{"type":48,"value":228},"Handoff process (who loads, who QAs)",{"type":43,"tag":58,"props":230,"children":231},{},[232,234,239],{"type":48,"value":233},"If ",{"type":43,"tag":70,"props":235,"children":237},{"className":236},[],[238],{"type":48,"value":201},{"type":48,"value":240}," says no AI tool → this skill is a no-op. Everything goes through diligence-issue-extraction directly.",{"type":43,"tag":51,"props":242,"children":244},{"id":243},"when-to-hand-off",[245],{"type":48,"value":246},"When to hand off",{"type":43,"tag":58,"props":248,"children":249},{},[250],{"type":48,"value":251},"Hand off when all of:",{"type":43,"tag":205,"props":253,"children":254},{},[255,260,265],{"type":43,"tag":209,"props":256,"children":257},{},[258],{"type":48,"value":259},"Category has >50 documents (below that, faster to just read them)",{"type":43,"tag":209,"props":261,"children":262},{},[263],{"type":48,"value":264},"Extraction target is a clause type the tool is good at (CoC, assignment, exclusivity, MFN, termination, auto-renewal)",{"type":43,"tag":209,"props":266,"children":267},{},[268],{"type":48,"value":269},"Documents are reasonably uniform (all customer contracts on similar paper — not a mix of contracts, letters, and board minutes)",{"type":43,"tag":58,"props":271,"children":272},{},[273],{"type":48,"value":274},"Don't hand off:",{"type":43,"tag":205,"props":276,"children":277},{},[278,283,288],{"type":43,"tag":209,"props":279,"children":280},{},[281],{"type":48,"value":282},"Bespoke or heavily negotiated documents",{"type":43,"tag":209,"props":284,"children":285},{},[286],{"type":48,"value":287},"Side letters and amendments (context-dependent, tools miss the interaction with the main agreement)",{"type":43,"tag":209,"props":289,"children":290},{},[291],{"type":48,"value":292},"Anything where the question is \"what does this mean for the deal\" not \"does this clause exist\"",{"type":43,"tag":51,"props":294,"children":296},{"id":295},"the-handoff",[297],{"type":48,"value":298},"The handoff",{"type":43,"tag":300,"props":301,"children":303},"h3",{"id":302},"step-1-prepare-the-batch",[304],{"type":48,"value":305},"Step 1: Prepare the batch",{"type":43,"tag":205,"props":307,"children":308},{},[309,314,326],{"type":43,"tag":209,"props":310,"children":311},{},[312],{"type":48,"value":313},"Identify documents for the batch (from VDR inventory)",{"type":43,"tag":209,"props":315,"children":316},{},[317,319,324],{"type":48,"value":318},"Specify extraction targets per ",{"type":43,"tag":70,"props":320,"children":322},{"className":321},[],[323],{"type":48,"value":201},{"type":48,"value":325}," (which clause types)",{"type":43,"tag":209,"props":327,"children":328},{},[329],{"type":48,"value":330},"Note the materiality threshold so tool output can be filtered",{"type":43,"tag":300,"props":332,"children":334},{"id":333},"step-2-load-or-instruct-the-loader",[335],{"type":48,"value":336},"Step 2: Load (or instruct the loader)",{"type":43,"tag":58,"props":338,"children":339},{},[340,342,347],{"type":48,"value":341},"Per ",{"type":43,"tag":70,"props":343,"children":345},{"className":344},[],[346],{"type":48,"value":201},{"type":48,"value":348}," — who loads. If it's you, generate the load instructions. If it's someone else, generate the request:",{"type":43,"tag":350,"props":351,"children":356},"pre",{"className":352,"code":353,"language":354,"meta":355,"style":355},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","## [Tool] Load Request — [Deal code] — [Category]\n\n**Documents:** [N] docs from VDR folder [path]\n**Load to:** [Tool workspace\u002Fmatter]\n**Extraction targets:**\n- Change of control \u002F assignment\n- Exclusivity\n- [etc. per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`]\n\n**Filter output:** Flag only where extraction target is present — no need for \"no CoC clause found\" for every doc.\n\n**Return by:** [date]\n","markdown","",[357],{"type":43,"tag":70,"props":358,"children":359},{"__ignoreMap":355},[360,404,414,467,489,507,521,534,564,572,594,602],{"type":43,"tag":361,"props":362,"children":365},"span",{"class":363,"line":364},"line",1,[366,372,378,383,389,394,399],{"type":43,"tag":361,"props":367,"children":369},{"style":368},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[370],{"type":48,"value":371},"## [",{"type":43,"tag":361,"props":373,"children":375},{"style":374},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[376],{"type":48,"value":377},"Tool",{"type":43,"tag":361,"props":379,"children":380},{"style":368},[381],{"type":48,"value":382},"]",{"type":43,"tag":361,"props":384,"children":386},{"style":385},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[387],{"type":48,"value":388}," Load Request — [Deal code] — ",{"type":43,"tag":361,"props":390,"children":391},{"style":368},[392],{"type":48,"value":393},"[",{"type":43,"tag":361,"props":395,"children":396},{"style":374},[397],{"type":48,"value":398},"Category",{"type":43,"tag":361,"props":400,"children":401},{"style":368},[402],{"type":48,"value":403},"]\n",{"type":43,"tag":361,"props":405,"children":407},{"class":363,"line":406},2,[408],{"type":43,"tag":361,"props":409,"children":411},{"emptyLinePlaceholder":410},true,[412],{"type":48,"value":413},"\n",{"type":43,"tag":361,"props":415,"children":417},{"class":363,"line":416},3,[418,424,430,434,439,444,448,454,458,463],{"type":43,"tag":361,"props":419,"children":421},{"style":420},"--shiki-light:#39ADB5;--shiki-light-font-weight:bold;--shiki-default:#89DDFF;--shiki-default-font-weight:bold;--shiki-dark:#89DDFF;--shiki-dark-font-weight:bold",[422],{"type":48,"value":423},"**",{"type":43,"tag":361,"props":425,"children":427},{"style":426},"--shiki-light:#E53935;--shiki-light-font-weight:bold;--shiki-default:#F07178;--shiki-default-font-weight:bold;--shiki-dark:#F07178;--shiki-dark-font-weight:bold",[428],{"type":48,"value":429},"Documents:",{"type":43,"tag":361,"props":431,"children":432},{"style":420},[433],{"type":48,"value":423},{"type":43,"tag":361,"props":435,"children":436},{"style":368},[437],{"type":48,"value":438}," [",{"type":43,"tag":361,"props":440,"children":441},{"style":374},[442],{"type":48,"value":443},"N",{"type":43,"tag":361,"props":445,"children":446},{"style":368},[447],{"type":48,"value":382},{"type":43,"tag":361,"props":449,"children":451},{"style":450},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[452],{"type":48,"value":453}," docs from VDR folder ",{"type":43,"tag":361,"props":455,"children":456},{"style":368},[457],{"type":48,"value":393},{"type":43,"tag":361,"props":459,"children":460},{"style":374},[461],{"type":48,"value":462},"path",{"type":43,"tag":361,"props":464,"children":465},{"style":368},[466],{"type":48,"value":403},{"type":43,"tag":361,"props":468,"children":470},{"class":363,"line":469},4,[471,475,480,484],{"type":43,"tag":361,"props":472,"children":473},{"style":420},[474],{"type":48,"value":423},{"type":43,"tag":361,"props":476,"children":477},{"style":426},[478],{"type":48,"value":479},"Load to:",{"type":43,"tag":361,"props":481,"children":482},{"style":420},[483],{"type":48,"value":423},{"type":43,"tag":361,"props":485,"children":486},{"style":450},[487],{"type":48,"value":488}," [Tool workspace\u002Fmatter]\n",{"type":43,"tag":361,"props":490,"children":492},{"class":363,"line":491},5,[493,497,502],{"type":43,"tag":361,"props":494,"children":495},{"style":420},[496],{"type":48,"value":423},{"type":43,"tag":361,"props":498,"children":499},{"style":426},[500],{"type":48,"value":501},"Extraction targets:",{"type":43,"tag":361,"props":503,"children":504},{"style":420},[505],{"type":48,"value":506},"**\n",{"type":43,"tag":361,"props":508,"children":510},{"class":363,"line":509},6,[511,516],{"type":43,"tag":361,"props":512,"children":513},{"style":368},[514],{"type":48,"value":515},"-",{"type":43,"tag":361,"props":517,"children":518},{"style":450},[519],{"type":48,"value":520}," Change of control \u002F assignment\n",{"type":43,"tag":361,"props":522,"children":524},{"class":363,"line":523},7,[525,529],{"type":43,"tag":361,"props":526,"children":527},{"style":368},[528],{"type":48,"value":515},{"type":43,"tag":361,"props":530,"children":531},{"style":450},[532],{"type":48,"value":533}," Exclusivity\n",{"type":43,"tag":361,"props":535,"children":537},{"class":363,"line":536},8,[538,542,547,552,556,560],{"type":43,"tag":361,"props":539,"children":540},{"style":368},[541],{"type":48,"value":515},{"type":43,"tag":361,"props":543,"children":544},{"style":450},[545],{"type":48,"value":546}," [etc. per ",{"type":43,"tag":361,"props":548,"children":549},{"style":368},[550],{"type":48,"value":551},"`",{"type":43,"tag":361,"props":553,"children":554},{"style":374},[555],{"type":48,"value":201},{"type":43,"tag":361,"props":557,"children":558},{"style":368},[559],{"type":48,"value":551},{"type":43,"tag":361,"props":561,"children":562},{"style":450},[563],{"type":48,"value":403},{"type":43,"tag":361,"props":565,"children":567},{"class":363,"line":566},9,[568],{"type":43,"tag":361,"props":569,"children":570},{"emptyLinePlaceholder":410},[571],{"type":48,"value":413},{"type":43,"tag":361,"props":573,"children":575},{"class":363,"line":574},10,[576,580,585,589],{"type":43,"tag":361,"props":577,"children":578},{"style":420},[579],{"type":48,"value":423},{"type":43,"tag":361,"props":581,"children":582},{"style":426},[583],{"type":48,"value":584},"Filter output:",{"type":43,"tag":361,"props":586,"children":587},{"style":420},[588],{"type":48,"value":423},{"type":43,"tag":361,"props":590,"children":591},{"style":450},[592],{"type":48,"value":593}," Flag only where extraction target is present — no need for \"no CoC clause found\" for every doc.\n",{"type":43,"tag":361,"props":595,"children":597},{"class":363,"line":596},11,[598],{"type":43,"tag":361,"props":599,"children":600},{"emptyLinePlaceholder":410},[601],{"type":48,"value":413},{"type":43,"tag":361,"props":603,"children":605},{"class":363,"line":604},12,[606,610,615,619,623,628],{"type":43,"tag":361,"props":607,"children":608},{"style":420},[609],{"type":48,"value":423},{"type":43,"tag":361,"props":611,"children":612},{"style":426},[613],{"type":48,"value":614},"Return by:",{"type":43,"tag":361,"props":616,"children":617},{"style":420},[618],{"type":48,"value":423},{"type":43,"tag":361,"props":620,"children":621},{"style":368},[622],{"type":48,"value":438},{"type":43,"tag":361,"props":624,"children":625},{"style":374},[626],{"type":48,"value":627},"date",{"type":43,"tag":361,"props":629,"children":630},{"style":368},[631],{"type":48,"value":403},{"type":43,"tag":300,"props":633,"children":635},{"id":634},"step-3-qa-the-output",[636],{"type":48,"value":637},"Step 3: QA the output",{"type":43,"tag":58,"props":639,"children":640},{},[641],{"type":48,"value":642},"When the tool returns results, apply the trust level:",{"type":43,"tag":58,"props":644,"children":645},{},[646,651,653,658],{"type":43,"tag":62,"props":647,"children":648},{},[649],{"type":48,"value":650},"\"Use as-is\":",{"type":48,"value":652}," Ingest directly into diligence findings. (Only if ",{"type":43,"tag":70,"props":654,"children":656},{"className":655},[],[657],{"type":48,"value":201},{"type":48,"value":659}," says this — it's rare.)",{"type":43,"tag":58,"props":661,"children":662},{},[663,668],{"type":43,"tag":62,"props":664,"children":665},{},[666],{"type":48,"value":667},"\"Spot-check X%\":",{"type":48,"value":669}," Randomly sample X% of flagged documents. For each, read the actual clause and compare to the tool's extraction. If error rate is low, accept the batch. If errors found, widen the sample.",{"type":43,"tag":58,"props":671,"children":672},{},[673,678],{"type":43,"tag":62,"props":674,"children":675},{},[676],{"type":48,"value":677},"\"Full human review of flagged\":",{"type":48,"value":679}," Tool narrows the universe (500 docs → 80 with CoC clauses). Human reads all 80. Tool saved the time of reading the 420 clean ones.",{"type":43,"tag":300,"props":681,"children":683},{"id":682},"step-4-judgment-layer",[684],{"type":48,"value":685},"Step 4: Judgment layer",{"type":43,"tag":58,"props":687,"children":688},{},[689],{"type":48,"value":690},"The tool found the clauses. Now apply judgment:",{"type":43,"tag":58,"props":692,"children":693},{},[694],{"type":48,"value":695},"For each flagged CoC provision: is it actually triggered by this deal?",{"type":43,"tag":205,"props":697,"children":698},{},[699,704,709],{"type":43,"tag":209,"props":700,"children":701},{},[702],{"type":48,"value":703},"Stock sale vs. asset sale vs. merger — different triggers",{"type":43,"tag":209,"props":705,"children":706},{},[707],{"type":48,"value":708},"\"Change of control\" defined how in the contract — majority ownership? board control? something else?",{"type":43,"tag":209,"props":710,"children":711},{},[712],{"type":48,"value":713},"Is there a carve-out for this type of transaction?",{"type":43,"tag":58,"props":715,"children":716},{},[717],{"type":48,"value":718},"This is the part the tool can't do. Output goes to diligence findings in house format.",{"type":43,"tag":51,"props":720,"children":722},{"id":721},"output",[723],{"type":48,"value":724},"Output",{"type":43,"tag":726,"props":727,"children":728},"blockquote",{},[729],{"type":43,"tag":58,"props":730,"children":731},{},[732],{"type":48,"value":733},"The QA summary below is derived from VDR documents that are privileged, confidential, or both. It inherits the sources' privilege and confidentiality status — distribution beyond the privilege circle can waive privilege. Store with the matter's privileged files.",{"type":43,"tag":350,"props":735,"children":737},{"className":352,"code":736,"language":354,"meta":355,"style":355},"## AI Tool Handoff Summary — [Category]\n\n**Tool:** [Luminance \u002F Kira]\n**Documents processed:** [N]\n**Extraction targets:** [clause types]\n\n### QA\n\n**Trust level:** [per `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fcorporate-legal\u002FCLAUDE.md`]\n**Sample size:** [N] docs spot-checked\n**Error rate:** [X]% — [Accepted \u002F Widened sample \u002F Full re-review triggered]\n\n### Results\n\n| Clause type | Docs flagged | After judgment layer | Material |\n|---|---|---|---|\n| Change of control | [N] | [N actually triggered by deal structure] | [N above threshold] |\n| Assignment | [N] | [N] | [N] |\n\n**→ [N] findings added to diligence issues**\n**→ [N] consents added to closing checklist**\n",[738],{"type":43,"tag":70,"props":739,"children":740},{"__ignoreMap":355},[741,766,773,794,822,842,849,862,869,906,939,973,980,993,1001,1047,1056,1108,1174,1182,1217],{"type":43,"tag":361,"props":742,"children":743},{"class":363,"line":364},[744,749,754,758,762],{"type":43,"tag":361,"props":745,"children":746},{"style":368},[747],{"type":48,"value":748},"## ",{"type":43,"tag":361,"props":750,"children":751},{"style":385},[752],{"type":48,"value":753},"AI Tool Handoff Summary — ",{"type":43,"tag":361,"props":755,"children":756},{"style":368},[757],{"type":48,"value":393},{"type":43,"tag":361,"props":759,"children":760},{"style":374},[761],{"type":48,"value":398},{"type":43,"tag":361,"props":763,"children":764},{"style":368},[765],{"type":48,"value":403},{"type":43,"tag":361,"props":767,"children":768},{"class":363,"line":406},[769],{"type":43,"tag":361,"props":770,"children":771},{"emptyLinePlaceholder":410},[772],{"type":48,"value":413},{"type":43,"tag":361,"props":774,"children":775},{"class":363,"line":416},[776,780,785,789],{"type":43,"tag":361,"props":777,"children":778},{"style":420},[779],{"type":48,"value":423},{"type":43,"tag":361,"props":781,"children":782},{"style":426},[783],{"type":48,"value":784},"Tool:",{"type":43,"tag":361,"props":786,"children":787},{"style":420},[788],{"type":48,"value":423},{"type":43,"tag":361,"props":790,"children":791},{"style":450},[792],{"type":48,"value":793}," [Luminance \u002F Kira]\n",{"type":43,"tag":361,"props":795,"children":796},{"class":363,"line":469},[797,801,806,810,814,818],{"type":43,"tag":361,"props":798,"children":799},{"style":420},[800],{"type":48,"value":423},{"type":43,"tag":361,"props":802,"children":803},{"style":426},[804],{"type":48,"value":805},"Documents processed:",{"type":43,"tag":361,"props":807,"children":808},{"style":420},[809],{"type":48,"value":423},{"type":43,"tag":361,"props":811,"children":812},{"style":368},[813],{"type":48,"value":438},{"type":43,"tag":361,"props":815,"children":816},{"style":374},[817],{"type":48,"value":443},{"type":43,"tag":361,"props":819,"children":820},{"style":368},[821],{"type":48,"value":403},{"type":43,"tag":361,"props":823,"children":824},{"class":363,"line":491},[825,829,833,837],{"type":43,"tag":361,"props":826,"children":827},{"style":420},[828],{"type":48,"value":423},{"type":43,"tag":361,"props":830,"children":831},{"style":426},[832],{"type":48,"value":501},{"type":43,"tag":361,"props":834,"children":835},{"style":420},[836],{"type":48,"value":423},{"type":43,"tag":361,"props":838,"children":839},{"style":450},[840],{"type":48,"value":841}," [clause types]\n",{"type":43,"tag":361,"props":843,"children":844},{"class":363,"line":509},[845],{"type":43,"tag":361,"props":846,"children":847},{"emptyLinePlaceholder":410},[848],{"type":48,"value":413},{"type":43,"tag":361,"props":850,"children":851},{"class":363,"line":523},[852,857],{"type":43,"tag":361,"props":853,"children":854},{"style":368},[855],{"type":48,"value":856},"### ",{"type":43,"tag":361,"props":858,"children":859},{"style":385},[860],{"type":48,"value":861},"QA\n",{"type":43,"tag":361,"props":863,"children":864},{"class":363,"line":536},[865],{"type":43,"tag":361,"props":866,"children":867},{"emptyLinePlaceholder":410},[868],{"type":48,"value":413},{"type":43,"tag":361,"props":870,"children":871},{"class":363,"line":566},[872,876,881,885,890,894,898,902],{"type":43,"tag":361,"props":873,"children":874},{"style":420},[875],{"type":48,"value":423},{"type":43,"tag":361,"props":877,"children":878},{"style":426},[879],{"type":48,"value":880},"Trust level:",{"type":43,"tag":361,"props":882,"children":883},{"style":420},[884],{"type":48,"value":423},{"type":43,"tag":361,"props":886,"children":887},{"style":450},[888],{"type":48,"value":889}," [per ",{"type":43,"tag":361,"props":891,"children":892},{"style":368},[893],{"type":48,"value":551},{"type":43,"tag":361,"props":895,"children":896},{"style":374},[897],{"type":48,"value":201},{"type":43,"tag":361,"props":899,"children":900},{"style":368},[901],{"type":48,"value":551},{"type":43,"tag":361,"props":903,"children":904},{"style":450},[905],{"type":48,"value":403},{"type":43,"tag":361,"props":907,"children":908},{"class":363,"line":574},[909,913,918,922,926,930,934],{"type":43,"tag":361,"props":910,"children":911},{"style":420},[912],{"type":48,"value":423},{"type":43,"tag":361,"props":914,"children":915},{"style":426},[916],{"type":48,"value":917},"Sample size:",{"type":43,"tag":361,"props":919,"children":920},{"style":420},[921],{"type":48,"value":423},{"type":43,"tag":361,"props":923,"children":924},{"style":368},[925],{"type":48,"value":438},{"type":43,"tag":361,"props":927,"children":928},{"style":374},[929],{"type":48,"value":443},{"type":43,"tag":361,"props":931,"children":932},{"style":368},[933],{"type":48,"value":382},{"type":43,"tag":361,"props":935,"children":936},{"style":450},[937],{"type":48,"value":938}," docs spot-checked\n",{"type":43,"tag":361,"props":940,"children":941},{"class":363,"line":596},[942,946,951,955,959,964,968],{"type":43,"tag":361,"props":943,"children":944},{"style":420},[945],{"type":48,"value":423},{"type":43,"tag":361,"props":947,"children":948},{"style":426},[949],{"type":48,"value":950},"Error rate:",{"type":43,"tag":361,"props":952,"children":953},{"style":420},[954],{"type":48,"value":423},{"type":43,"tag":361,"props":956,"children":957},{"style":368},[958],{"type":48,"value":438},{"type":43,"tag":361,"props":960,"children":961},{"style":374},[962],{"type":48,"value":963},"X",{"type":43,"tag":361,"props":965,"children":966},{"style":368},[967],{"type":48,"value":382},{"type":43,"tag":361,"props":969,"children":970},{"style":450},[971],{"type":48,"value":972},"% — [Accepted \u002F Widened sample \u002F Full re-review triggered]\n",{"type":43,"tag":361,"props":974,"children":975},{"class":363,"line":604},[976],{"type":43,"tag":361,"props":977,"children":978},{"emptyLinePlaceholder":410},[979],{"type":48,"value":413},{"type":43,"tag":361,"props":981,"children":983},{"class":363,"line":982},13,[984,988],{"type":43,"tag":361,"props":985,"children":986},{"style":368},[987],{"type":48,"value":856},{"type":43,"tag":361,"props":989,"children":990},{"style":385},[991],{"type":48,"value":992},"Results\n",{"type":43,"tag":361,"props":994,"children":996},{"class":363,"line":995},14,[997],{"type":43,"tag":361,"props":998,"children":999},{"emptyLinePlaceholder":410},[1000],{"type":48,"value":413},{"type":43,"tag":361,"props":1002,"children":1004},{"class":363,"line":1003},15,[1005,1010,1015,1019,1024,1028,1033,1037,1042],{"type":43,"tag":361,"props":1006,"children":1007},{"style":368},[1008],{"type":48,"value":1009},"|",{"type":43,"tag":361,"props":1011,"children":1012},{"style":450},[1013],{"type":48,"value":1014}," Clause type ",{"type":43,"tag":361,"props":1016,"children":1017},{"style":368},[1018],{"type":48,"value":1009},{"type":43,"tag":361,"props":1020,"children":1021},{"style":450},[1022],{"type":48,"value":1023}," Docs flagged ",{"type":43,"tag":361,"props":1025,"children":1026},{"style":368},[1027],{"type":48,"value":1009},{"type":43,"tag":361,"props":1029,"children":1030},{"style":450},[1031],{"type":48,"value":1032}," After judgment layer ",{"type":43,"tag":361,"props":1034,"children":1035},{"style":368},[1036],{"type":48,"value":1009},{"type":43,"tag":361,"props":1038,"children":1039},{"style":450},[1040],{"type":48,"value":1041}," Material ",{"type":43,"tag":361,"props":1043,"children":1044},{"style":368},[1045],{"type":48,"value":1046},"|\n",{"type":43,"tag":361,"props":1048,"children":1050},{"class":363,"line":1049},16,[1051],{"type":43,"tag":361,"props":1052,"children":1053},{"style":368},[1054],{"type":48,"value":1055},"|---|---|---|---|\n",{"type":43,"tag":361,"props":1057,"children":1059},{"class":363,"line":1058},17,[1060,1064,1069,1073,1077,1081,1085,1090,1095,1099,1104],{"type":43,"tag":361,"props":1061,"children":1062},{"style":368},[1063],{"type":48,"value":1009},{"type":43,"tag":361,"props":1065,"children":1066},{"style":450},[1067],{"type":48,"value":1068}," Change of control ",{"type":43,"tag":361,"props":1070,"children":1071},{"style":368},[1072],{"type":48,"value":1009},{"type":43,"tag":361,"props":1074,"children":1075},{"style":368},[1076],{"type":48,"value":438},{"type":43,"tag":361,"props":1078,"children":1079},{"style":374},[1080],{"type":48,"value":443},{"type":43,"tag":361,"props":1082,"children":1083},{"style":368},[1084],{"type":48,"value":382},{"type":43,"tag":361,"props":1086,"children":1087},{"style":368},[1088],{"type":48,"value":1089}," |",{"type":43,"tag":361,"props":1091,"children":1092},{"style":450},[1093],{"type":48,"value":1094}," [N actually triggered by deal structure] ",{"type":43,"tag":361,"props":1096,"children":1097},{"style":368},[1098],{"type":48,"value":1009},{"type":43,"tag":361,"props":1100,"children":1101},{"style":450},[1102],{"type":48,"value":1103}," [N above threshold] ",{"type":43,"tag":361,"props":1105,"children":1106},{"style":368},[1107],{"type":48,"value":1046},{"type":43,"tag":361,"props":1109,"children":1111},{"class":363,"line":1110},18,[1112,1116,1121,1125,1129,1133,1137,1141,1145,1149,1153,1157,1161,1165,1169],{"type":43,"tag":361,"props":1113,"children":1114},{"style":368},[1115],{"type":48,"value":1009},{"type":43,"tag":361,"props":1117,"children":1118},{"style":450},[1119],{"type":48,"value":1120}," Assignment ",{"type":43,"tag":361,"props":1122,"children":1123},{"style":368},[1124],{"type":48,"value":1009},{"type":43,"tag":361,"props":1126,"children":1127},{"style":368},[1128],{"type":48,"value":438},{"type":43,"tag":361,"props":1130,"children":1131},{"style":374},[1132],{"type":48,"value":443},{"type":43,"tag":361,"props":1134,"children":1135},{"style":368},[1136],{"type":48,"value":382},{"type":43,"tag":361,"props":1138,"children":1139},{"style":368},[1140],{"type":48,"value":1089},{"type":43,"tag":361,"props":1142,"children":1143},{"style":368},[1144],{"type":48,"value":438},{"type":43,"tag":361,"props":1146,"children":1147},{"style":374},[1148],{"type":48,"value":443},{"type":43,"tag":361,"props":1150,"children":1151},{"style":368},[1152],{"type":48,"value":382},{"type":43,"tag":361,"props":1154,"children":1155},{"style":368},[1156],{"type":48,"value":1089},{"type":43,"tag":361,"props":1158,"children":1159},{"style":368},[1160],{"type":48,"value":438},{"type":43,"tag":361,"props":1162,"children":1163},{"style":374},[1164],{"type":48,"value":443},{"type":43,"tag":361,"props":1166,"children":1167},{"style":368},[1168],{"type":48,"value":382},{"type":43,"tag":361,"props":1170,"children":1171},{"style":368},[1172],{"type":48,"value":1173}," |\n",{"type":43,"tag":361,"props":1175,"children":1177},{"class":363,"line":1176},19,[1178],{"type":43,"tag":361,"props":1179,"children":1180},{"emptyLinePlaceholder":410},[1181],{"type":48,"value":413},{"type":43,"tag":361,"props":1183,"children":1185},{"class":363,"line":1184},20,[1186,1190,1195,1199,1204,1208,1213],{"type":43,"tag":361,"props":1187,"children":1188},{"style":420},[1189],{"type":48,"value":423},{"type":43,"tag":361,"props":1191,"children":1192},{"style":426},[1193],{"type":48,"value":1194},"→ ",{"type":43,"tag":361,"props":1196,"children":1197},{"style":420},[1198],{"type":48,"value":393},{"type":43,"tag":361,"props":1200,"children":1202},{"style":1201},"--shiki-light:#91B859;--shiki-light-font-weight:bold;--shiki-default:#C3E88D;--shiki-default-font-weight:bold;--shiki-dark:#C3E88D;--shiki-dark-font-weight:bold",[1203],{"type":48,"value":443},{"type":43,"tag":361,"props":1205,"children":1206},{"style":420},[1207],{"type":48,"value":382},{"type":43,"tag":361,"props":1209,"children":1210},{"style":426},[1211],{"type":48,"value":1212}," findings added to diligence issues",{"type":43,"tag":361,"props":1214,"children":1215},{"style":420},[1216],{"type":48,"value":506},{"type":43,"tag":361,"props":1218,"children":1220},{"class":363,"line":1219},21,[1221,1225,1229,1233,1237,1241,1246],{"type":43,"tag":361,"props":1222,"children":1223},{"style":420},[1224],{"type":48,"value":423},{"type":43,"tag":361,"props":1226,"children":1227},{"style":426},[1228],{"type":48,"value":1194},{"type":43,"tag":361,"props":1230,"children":1231},{"style":420},[1232],{"type":48,"value":393},{"type":43,"tag":361,"props":1234,"children":1235},{"style":1201},[1236],{"type":48,"value":443},{"type":43,"tag":361,"props":1238,"children":1239},{"style":420},[1240],{"type":48,"value":382},{"type":43,"tag":361,"props":1242,"children":1243},{"style":426},[1244],{"type":48,"value":1245}," consents added to closing checklist",{"type":43,"tag":361,"props":1247,"children":1248},{"style":420},[1249],{"type":48,"value":506},{"type":43,"tag":51,"props":1251,"children":1253},{"id":1252},"close-with-the-next-steps-decision-tree",[1254],{"type":48,"value":1255},"Close with the next-steps decision tree",{"type":43,"tag":58,"props":1257,"children":1258},{},[1259,1261,1267],{"type":48,"value":1260},"End with the next-steps decision tree per CLAUDE.md ",{"type":43,"tag":70,"props":1262,"children":1264},{"className":1263},[],[1265],{"type":48,"value":1266},"## Outputs",{"type":48,"value":1268},". 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":1270,"children":1272},{"id":1271},"what-this-skill-does-not-do",[1273],{"type":48,"value":1274},"What this skill does not do",{"type":43,"tag":205,"props":1276,"children":1277},{},[1278,1283,1295],{"type":43,"tag":209,"props":1279,"children":1280},{},[1281],{"type":48,"value":1282},"It doesn't run Luminance or Kira — it manages the handoff and QA. A human (or the tool's own interface) runs the extraction.",{"type":43,"tag":209,"props":1284,"children":1285},{},[1286,1288,1293],{"type":48,"value":1287},"It doesn't replace the tool's output with its own judgment entirely — if ",{"type":43,"tag":70,"props":1289,"children":1291},{"className":1290},[],[1292],{"type":48,"value":201},{"type":48,"value":1294}," says spot-check 10%, check 10%, not 100%.",{"type":43,"tag":209,"props":1296,"children":1297},{},[1298,1300,1305],{"type":48,"value":1299},"It doesn't decide the trust level — that's in ",{"type":43,"tag":70,"props":1301,"children":1303},{"className":1302},[],[1304],{"type":48,"value":201},{"type":48,"value":1306},", set at cold-start based on the team's experience with the tool.",{"type":43,"tag":1308,"props":1309,"children":1310},"style",{},[1311],{"type":48,"value":1312},"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":1314,"total":1501},[1315,1336,1350,1362,1381,1394,1415,1435,1449,1464,1472,1485],{"slug":1316,"name":1316,"fn":1317,"description":1318,"org":1319,"tags":1320,"stars":1333,"repoUrl":1334,"updatedAt":1335},"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},[1321,1324,1327,1330],{"name":1322,"slug":1323,"type":16},"Creative","creative",{"name":1325,"slug":1326,"type":16},"Design","design",{"name":1328,"slug":1329,"type":16},"Generative Art","generative-art",{"name":1331,"slug":1332,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1337,"name":1337,"fn":1338,"description":1339,"org":1340,"tags":1341,"stars":1333,"repoUrl":1334,"updatedAt":1349},"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},[1342,1345,1346],{"name":1343,"slug":1344,"type":16},"Branding","branding",{"name":1325,"slug":1326,"type":16},{"name":1347,"slug":1348,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1351,"name":1351,"fn":1352,"description":1353,"org":1354,"tags":1355,"stars":1333,"repoUrl":1334,"updatedAt":1361},"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},[1356,1357,1358],{"name":1322,"slug":1323,"type":16},{"name":1325,"slug":1326,"type":16},{"name":1359,"slug":1360,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1363,"name":1363,"fn":1364,"description":1365,"org":1366,"tags":1367,"stars":1333,"repoUrl":1334,"updatedAt":1380},"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},[1368,1371,1372,1375,1377],{"name":1369,"slug":1370,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1373,"slug":1374,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1376,"slug":1363,"type":16},"Claude API",{"name":1378,"slug":1379,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1382,"name":1382,"fn":1383,"description":1384,"org":1385,"tags":1386,"stars":1333,"repoUrl":1334,"updatedAt":1393},"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},[1387,1390],{"name":1388,"slug":1389,"type":16},"Documentation","documentation",{"name":1391,"slug":1392,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1395,"name":1395,"fn":1396,"description":1397,"org":1398,"tags":1399,"stars":1333,"repoUrl":1334,"updatedAt":1414},"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},[1400,1403,1405,1408,1411],{"name":1401,"slug":1402,"type":16},"Documents","documents",{"name":1404,"slug":1395,"type":16},"DOCX",{"name":1406,"slug":1407,"type":16},"Office","office",{"name":1409,"slug":1410,"type":16},"Templates","templates",{"name":1412,"slug":1413,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1416,"name":1416,"fn":1417,"description":1418,"org":1419,"tags":1420,"stars":1333,"repoUrl":1334,"updatedAt":1434},"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},[1421,1422,1425,1428,1431],{"name":1325,"slug":1326,"type":16},{"name":1423,"slug":1424,"type":16},"Frontend","frontend",{"name":1426,"slug":1427,"type":16},"React","react",{"name":1429,"slug":1430,"type":16},"Tailwind CSS","tailwind-css",{"name":1432,"slug":1433,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1436,"name":1436,"fn":1437,"description":1438,"org":1439,"tags":1440,"stars":1333,"repoUrl":1334,"updatedAt":1448},"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},[1441,1444,1445],{"name":1442,"slug":1443,"type":16},"Communications","communications",{"name":1409,"slug":1410,"type":16},{"name":1446,"slug":1447,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1450,"name":1450,"fn":1451,"description":1452,"org":1453,"tags":1454,"stars":1333,"repoUrl":1334,"updatedAt":1463},"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},[1455,1456,1459,1460],{"name":1369,"slug":1370,"type":16},{"name":1457,"slug":1458,"type":16},"API Development","api-development",{"name":1378,"slug":1379,"type":16},{"name":1461,"slug":1462,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1360,"name":1360,"fn":1465,"description":1466,"org":1467,"tags":1468,"stars":1333,"repoUrl":1334,"updatedAt":1471},"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},[1469,1470],{"name":1401,"slug":1402,"type":16},{"name":1359,"slug":1360,"type":16},"2026-04-06T17:56:02.483316",{"slug":1473,"name":1473,"fn":1474,"description":1475,"org":1476,"tags":1477,"stars":1333,"repoUrl":1334,"updatedAt":1484},"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},[1478,1481],{"name":1479,"slug":1480,"type":16},"PowerPoint","powerpoint",{"name":1482,"slug":1483,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1486,"name":1486,"fn":1487,"description":1488,"org":1489,"tags":1490,"stars":1333,"repoUrl":1334,"updatedAt":1500},"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},[1491,1492,1493,1496,1499],{"name":1369,"slug":1370,"type":16},{"name":1388,"slug":1389,"type":16},{"name":1494,"slug":1495,"type":16},"Evals","evals",{"name":1497,"slug":1498,"type":16},"Performance","performance",{"name":1391,"slug":1392,"type":16},"2026-04-19T06:45:40.804",490,{"items":1503,"total":1587},[1504,1518,1525,1542,1552,1563,1574],{"slug":1505,"name":1505,"fn":1506,"description":1507,"org":1508,"tags":1509,"stars":26,"repoUrl":27,"updatedAt":1517},"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},[1510,1513,1516],{"name":1511,"slug":1512,"type":16},"Compliance","compliance",{"name":1514,"slug":1515,"type":16},"Governance","governance",{"name":24,"slug":25,"type":16},"2026-05-14T06:02:19.677579",{"slug":4,"name":4,"fn":5,"description":6,"org":1519,"tags":1520,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1521,1522,1523,1524],{"name":18,"slug":19,"type":16},{"name":14,"slug":15,"type":16},{"name":24,"slug":25,"type":16},{"name":21,"slug":22,"type":16},{"slug":1526,"name":1526,"fn":1527,"description":1528,"org":1529,"tags":1530,"stars":26,"repoUrl":27,"updatedAt":1541},"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},[1531,1532,1535,1538],{"name":24,"slug":25,"type":16},{"name":1533,"slug":1534,"type":16},"Policy","policy",{"name":1536,"slug":1537,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1539,"slug":1540,"type":16},"Risk Assessment","risk-assessment","2026-05-13T06:03:19.61029",{"slug":1543,"name":1543,"fn":1544,"description":1545,"org":1546,"tags":1547,"stars":26,"repoUrl":27,"updatedAt":1551},"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},[1548,1549,1550],{"name":14,"slug":15,"type":16},{"name":1401,"slug":1402,"type":16},{"name":24,"slug":25,"type":16},"2026-05-13T06:03:34.070339",{"slug":1553,"name":1553,"fn":1554,"description":1555,"org":1556,"tags":1557,"stars":26,"repoUrl":27,"updatedAt":1562},"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},[1558,1559],{"name":18,"slug":19,"type":16},{"name":1560,"slug":1561,"type":16},"Plugin Development","plugin-development","2026-05-13T06:02:55.642269",{"slug":1564,"name":1564,"fn":1565,"description":1566,"org":1567,"tags":1568,"stars":26,"repoUrl":27,"updatedAt":1573},"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},[1569,1572],{"name":1570,"slug":1571,"type":16},"Education","education",{"name":24,"slug":25,"type":16},"2026-07-24T05:41:43.01243",{"slug":1575,"name":1575,"fn":1576,"description":1577,"org":1578,"tags":1579,"stars":26,"repoUrl":27,"updatedAt":1586},"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},[1580,1581,1582,1583],{"name":1388,"slug":1389,"type":16},{"name":1514,"slug":1515,"type":16},{"name":24,"slug":25,"type":16},{"name":1584,"slug":1585,"type":16},"Meetings","meetings","2026-05-14T06:01:29.792942",118]