[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-ai-inventory":3,"mdc-rzvze1-key":34,"related-repo-anthropic-ai-inventory":1605,"related-org-anthropic-ai-inventory":1697},{"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},"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},"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},"Compliance","compliance","tag",{"name":18,"slug":19,"type":16},"Governance","governance",{"name":21,"slug":22,"type":16},"Legal","legal",8721,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","2026-05-14T06:02:19.677579",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\u002Fai-inventory","---\nname: ai-inventory\ndescription: >\n  EU AI Act per-system inventory — track each AI system's role (provider,\n  deployer, importer, distributor, authorized representative, product\n  manufacturer) and risk tier (prohibited, high-risk, limited, minimal,\n  GPAI, GPAI+systemic). Role and tier are assessed per system, not per\n  company. Use when the user says \"ai inventory\", \"add an ai system\",\n  \"what systems do we have\", \"classify this ai system\", \"eu ai act\n  register\", or \"ai system registry\".\nargument-hint: \"[list | add | edit \u003Cid> | classify \u003Cid> | show \u003Cid>]\"\n---\n\n# \u002Fai-inventory\n\n## When this runs\n\nThe user wants to manage their AI system inventory under the EU AI Act. The\ncore idea the skill exists to enforce: **role and tier are per-system, not\nper-company.** A single organization can be a *provider* of System A, a\n*deployer* of System B, and an *importer* of System C. Each combination\ntriggers a different set of obligations under the AI Act. The inventory\nexists so those assessments are tracked where you can find them — the\nobligations themselves are derived in conversation, not from a table.\n\n## What to do\n\n1. **Read the config.** Read\n   `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002FCLAUDE.md`.\n   If it doesn't exist or still has `[PLACEHOLDER]` markers, direct the user\n   to `\u002Fai-governance-legal:cold-start-interview` first.\n\n2. **Read the inventory.** Inventory lives at\n   `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002Fai-systems.yaml`.\n   If it doesn't exist, create it with an empty `systems:` list when the\n   first `add` runs.\n\n3. **Dispatch on the argument:**\n\n   - No argument, or `list` → show the inventory table (see **List** below).\n   - `add` → run the **Add** flow.\n   - `edit \u003Cid>` → show the current record, ask what to change, update one\n     field, confirm, write.\n   - `classify \u003Cid>` → run the **Classification walk-through** on an\n     existing record, updating role, tier, role_basis, and tier_basis.\n   - `show \u003Cid>` → show the full record.\n\n4. **On list, offer the dashboard:**\n   \"Want the full dashboard? Filter by status \u002F tier \u002F EU nexus \u002F owner.\n   Say the word.\"\n\n5. **Close every action with a hook into the lawyer's work.**\n   After any write, say:\n   > Recorded. When you're ready to walk through obligations for this\n   > system, just ask — I'll do it in-conversation and flag where the AI\n   > Act article mapping needs your verification. I don't derive\n   > obligations from a table because the mapping is complex and changing.\n\n## List format\n\nRender as a compact table:\n\n| ID | Name | Owner | Status | EU nexus | Role | Tier | Next review |\n|----|------|-------|--------|----------|------|------|-------------|\n| sys-001 | Resume screening | HR \u002F Jamie | in_production | yes | deployer | high_risk | 2026-08-01 |\n| sys-002 | Email drafting assistant | IT \u002F Priya | in_production | no | deployer | limited | 2026-12-01 |\n\nUnder the table, show counts by tier and a line: \"N systems flagged for\nreview within 30 days.\"\n\n## Add flow (interview)\n\nAsk, one field at a time (or accept a paste). The required fields are\n`name`, `owner`, `description`, `status`, `eu_nexus`. The rest can be\ndeferred — say so explicitly: \"you can come back to classification with\n`\u002Fai-governance-legal:ai-inventory classify \u003Cid>`.\"\n\n1. **Name.** Short label for the system.\n2. **Owner.** Person or team accountable for it day-to-day.\n3. **Description.** One or two sentences. What does it do, and against\n   what data?\n4. **Status.** `planned | in_development | in_production | deprecated`.\n5. **EU nexus.** Is the system deployed in the EU\u002FEEA, offered to users in\n   the EU\u002FEEA, or used to produce outputs that affect people in the\n   EU\u002FEEA? If any of these are true, EU AI Act analysis applies.\n6. **Proceed to classification?** Offer to run the walk-through now, or\n   skip and come back later.\n\nAssign an ID: `sys-NNN` where NNN is the next integer in the file.\n\n## Classification walk-through\n\nThe walk-through produces `role`, `role_basis`, `tier`, `tier_basis`. Both\nbases are tagged `[verify against current AI Act text]` — not because the\nskill is hedging, but because the article mapping is complex and the AI\nAct is still phasing in. The lawyer owns verification.\n\n### Step 1: Role\n\n> **Who does what to this system?**\n\nOptions, with the distinguishing test:\n\n- **Provider** — you develop it (or have it developed) and place it on the\n  EU market or put it into service under your own name or trademark.\n- **Deployer** — you use it under your own authority, not for personal\n  non-professional use. (Most common inside companies.)\n- **Importer** — you bring an AI system into the EU from a provider\n  established outside the EU.\n- **Distributor** — you make an AI system available on the EU market\n  without being the provider or importer.\n- **Authorized representative** — you act on behalf of a non-EU provider\n  and are established in the EU.\n- **Product manufacturer** — you put a general-purpose AI system (or\n  another AI system) into a product under your own name\u002Ftrademark. Treated\n  as provider for the product.\n\n**Dual-role flag.** If the user substantially modifies a vendor system\n(fine-tunes on their own data, changes the intended purpose, rebrands),\nthey may become a **provider** of the modified system even if they started\nas a deployer. Call this out when they describe any modification beyond\nconfiguration. `[verify against current AI Act text — Article 25, provider\nobligations and substantial modification]`\n\nWrite the role. Write `role_basis` in one sentence.\n\n### Step 2: Tier\n\n> **What does the system do, and does the use case fall into a regulated\n> category?**\n\nCheck in order:\n\n**A. Article 5 prohibited practices.** `[verify against current AI Act\ntext — Article 5]`\n\nSummaries, not definitive text:\n- Subliminal or deceptive techniques materially distorting behavior\n- Exploiting vulnerabilities (age, disability, socio-economic status) to\n  materially distort behavior\n- Social scoring by public authorities leading to detrimental treatment\n- Real-time remote biometric ID in publicly accessible spaces for law\n  enforcement (narrow exceptions)\n- Biometric categorization inferring race, political opinions, union\n  membership, religious or philosophical beliefs, sex life, or sexual\n  orientation\n- Emotion recognition in the workplace or education (medical and safety\n  exceptions)\n- Facial image database scraping from the internet or CCTV\n- Predictive policing based solely on personality traits\n\nIf matched → tier is `prohibited`. Flag the use case as stop and route to\nthe governance team's prohibited-practice workflow.\n\n**B. Annex III high-risk areas.** `[verify against current AI Act text —\nAnnex III]`\n\nSummaries:\n1. Biometric identification and categorization\n2. Critical infrastructure (digital infrastructure, road traffic, supply of\n   water \u002F gas \u002F heating \u002F electricity)\n3. Education and vocational training (access, evaluation, proctoring,\n   monitoring prohibited behavior)\n4. Employment, worker management, self-employment access — recruitment,\n   selection, promotion, termination, task allocation, monitoring, performance\n5. Essential private and public services (public benefits, credit scoring\n   for individuals, risk assessment and pricing for life\u002Fhealth insurance,\n   emergency dispatch)\n6. Law enforcement (risk assessment, polygraphs, deepfake detection,\n   reliability of evidence, profiling)\n7. Migration, asylum, border control (risk assessment, travel document\n   verification, examination of applications)\n8. Administration of justice and democratic processes (research and\n   interpretation, influencing elections)\n\nIf matched → tier is `high_risk`. Note the Annex III area and subsection.\n\n**C. GPAI.** `[verify against current AI Act text — Article 51 and\nsurrounding]`\n\n- **GPAI:** model trained on broad data at scale, designed for generality,\n  capable of competently performing a wide range of distinct tasks.\n- **GPAI + systemic risk:** cumulative compute > 10^25 FLOPs, or designated\n  by the Commission.\n\n**D. Limited risk.** Chatbots interacting with natural persons, deepfakes,\nemotion recognition and biometric categorization systems outside Article 5\nscope — transparency obligations apply.\n\n**E. Minimal risk.** Everything else.\n\nWrite the tier. Write `tier_basis` in one sentence, citing the article or\nAnnex entry that matched, tagged `[verify against current AI Act text]`.\n\n### Step 3: Recommendations\n\nOffer three next steps:\n1. \"Want me to walk through obligations for this system? I'll do it in\n   conversation — I don't derive them from a table.\"\n2. \"Want to run `\u002Fai-governance-legal:aia-generation` to produce a full\n   impact assessment?\"\n3. \"Want to set a next review date? I'll add it to the inventory.\"\n\n## Record format\n\n```yaml\nsystems:\n  - id: sys-001\n    name: \"Resume screening tool\"\n    owner: \"HR \u002F Jamie\"\n    description: \"Filters inbound CVs against job criteria\"\n    status: in_production          # planned | in_development | in_production | deprecated\n    eu_nexus: true                 # deployed, offered, or affects people in the EU\u002FEEA\n    role: deployer                 # provider | deployer | importer | distributor | authorized_rep | product_manufacturer\n    role_basis: \"We license from VendorX and deploy internally [verify against current AI Act text]\"\n    tier: high_risk                # prohibited | high_risk | limited | minimal | gpai | gpai_systemic\n    tier_basis: \"Annex III(4)(a) — employment, recruitment selection [verify against current AI Act text]\"\n    obligations_assessed: false\n    obligations_note: \"To assess: as deployer of a high-risk system — human oversight, input data quality, monitoring, record-keeping, informing workers, FRIA if public body\u002Fservice — see Article 26 [verify against current AI Act text]\"\n    next_review: \"2026-08-01\"\n    review_trigger: \"on substantial modification or annually\"\n    created: \"2026-05-11\"\n    updated: \"2026-05-11\"\n```\n\n## Why this skill does NOT auto-derive obligations\n\nThe inventory stores role, tier, and the basis for each. It does NOT\ncontain a hardcoded role × tier → obligations table.\n\nWhen the user asks \"what are my obligations for System X?\", the skill\ndoes the analysis **in conversation**, tagged `[verify]`, and routes to\n`\u002Fai-governance-legal:aia-generation` for the formal impact assessment\nif needed.\n\nThis is deliberate:\n- Article mapping is complex and the AI Act is phasing in through 2027.\n- Confident-and-wrong on a compliance obligation ends up in a board memo.\n- The inventory is a registry for the lawyer. The lawyer owns the\n  obligation analysis.\n\n## Guardrails\n\n- **Never classify silently.** The classification walk-through must be\n  visible; do not auto-classify from a system description.\n- **`[verify]` tags stay.** They are not hedging — they are the point.\n  Do not strip them in outputs.\n- **Flag substantial modification.** Whenever a system is modified beyond\n  configuration, prompt the user to re-run `\u002Fai-inventory classify` —\n  modification can change role.\n- **Don't declare obligations from a table.** If asked, do the analysis\n  in conversation and route to `\u002Faia-generation` for anything that needs\n  a formal record.\n",{"data":35,"body":37},{"name":4,"description":6,"argument-hint":36},"[list | add | edit \u003Cid> | classify \u003Cid> | show \u003Cid>]",{"type":38,"children":39},"root",[40,48,55,91,97,288,294,299,440,445,451,501,572,585,590,632,639,650,655,718,740,752,758,769,774,789,794,837,850,865,870,913,924,939,962,972,982,1000,1006,1011,1037,1043,1468,1474,1479,1506,1511,1529,1535,1599],{"type":41,"tag":42,"props":43,"children":44},"element","h1",{"id":4},[45],{"type":46,"value":47},"text","\u002Fai-inventory",{"type":41,"tag":49,"props":50,"children":52},"h2",{"id":51},"when-this-runs",[53],{"type":46,"value":54},"When this runs",{"type":41,"tag":56,"props":57,"children":58},"p",{},[59,61,67,69,75,77,82,84,89],{"type":46,"value":60},"The user wants to manage their AI system inventory under the EU AI Act. The\ncore idea the skill exists to enforce: ",{"type":41,"tag":62,"props":63,"children":64},"strong",{},[65],{"type":46,"value":66},"role and tier are per-system, not\nper-company.",{"type":46,"value":68}," A single organization can be a ",{"type":41,"tag":70,"props":71,"children":72},"em",{},[73],{"type":46,"value":74},"provider",{"type":46,"value":76}," of System A, a\n",{"type":41,"tag":70,"props":78,"children":79},{},[80],{"type":46,"value":81},"deployer",{"type":46,"value":83}," of System B, and an ",{"type":41,"tag":70,"props":85,"children":86},{},[87],{"type":46,"value":88},"importer",{"type":46,"value":90}," of System C. Each combination\ntriggers a different set of obligations under the AI Act. The inventory\nexists so those assessments are tracked where you can find them — the\nobligations themselves are derived in conversation, not from a table.",{"type":41,"tag":49,"props":92,"children":94},{"id":93},"what-to-do",[95],{"type":46,"value":96},"What to do",{"type":41,"tag":98,"props":99,"children":100},"ol",{},[101,137,171,259,269],{"type":41,"tag":102,"props":103,"children":104},"li",{},[105,110,112,119,121,127,129,135],{"type":41,"tag":62,"props":106,"children":107},{},[108],{"type":46,"value":109},"Read the config.",{"type":46,"value":111}," Read\n",{"type":41,"tag":113,"props":114,"children":116},"code",{"className":115},[],[117],{"type":46,"value":118},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002FCLAUDE.md",{"type":46,"value":120},".\nIf it doesn't exist or still has ",{"type":41,"tag":113,"props":122,"children":124},{"className":123},[],[125],{"type":46,"value":126},"[PLACEHOLDER]",{"type":46,"value":128}," markers, direct the user\nto ",{"type":41,"tag":113,"props":130,"children":132},{"className":131},[],[133],{"type":46,"value":134},"\u002Fai-governance-legal:cold-start-interview",{"type":46,"value":136}," first.",{"type":41,"tag":102,"props":138,"children":139},{},[140,145,147,153,155,161,163,169],{"type":41,"tag":62,"props":141,"children":142},{},[143],{"type":46,"value":144},"Read the inventory.",{"type":46,"value":146}," Inventory lives at\n",{"type":41,"tag":113,"props":148,"children":150},{"className":149},[],[151],{"type":46,"value":152},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fai-governance-legal\u002Fai-systems.yaml",{"type":46,"value":154},".\nIf it doesn't exist, create it with an empty ",{"type":41,"tag":113,"props":156,"children":158},{"className":157},[],[159],{"type":46,"value":160},"systems:",{"type":46,"value":162}," list when the\nfirst ",{"type":41,"tag":113,"props":164,"children":166},{"className":165},[],[167],{"type":46,"value":168},"add",{"type":46,"value":170}," runs.",{"type":41,"tag":102,"props":172,"children":173},{},[174,179],{"type":41,"tag":62,"props":175,"children":176},{},[177],{"type":46,"value":178},"Dispatch on the argument:",{"type":41,"tag":180,"props":181,"children":182},"ul",{},[183,203,220,231,248],{"type":41,"tag":102,"props":184,"children":185},{},[186,188,194,196,201],{"type":46,"value":187},"No argument, or ",{"type":41,"tag":113,"props":189,"children":191},{"className":190},[],[192],{"type":46,"value":193},"list",{"type":46,"value":195}," → show the inventory table (see ",{"type":41,"tag":62,"props":197,"children":198},{},[199],{"type":46,"value":200},"List",{"type":46,"value":202}," below).",{"type":41,"tag":102,"props":204,"children":205},{},[206,211,213,218],{"type":41,"tag":113,"props":207,"children":209},{"className":208},[],[210],{"type":46,"value":168},{"type":46,"value":212}," → run the ",{"type":41,"tag":62,"props":214,"children":215},{},[216],{"type":46,"value":217},"Add",{"type":46,"value":219}," flow.",{"type":41,"tag":102,"props":221,"children":222},{},[223,229],{"type":41,"tag":113,"props":224,"children":226},{"className":225},[],[227],{"type":46,"value":228},"edit \u003Cid>",{"type":46,"value":230}," → show the current record, ask what to change, update one\nfield, confirm, write.",{"type":41,"tag":102,"props":232,"children":233},{},[234,240,241,246],{"type":41,"tag":113,"props":235,"children":237},{"className":236},[],[238],{"type":46,"value":239},"classify \u003Cid>",{"type":46,"value":212},{"type":41,"tag":62,"props":242,"children":243},{},[244],{"type":46,"value":245},"Classification walk-through",{"type":46,"value":247}," on an\nexisting record, updating role, tier, role_basis, and tier_basis.",{"type":41,"tag":102,"props":249,"children":250},{},[251,257],{"type":41,"tag":113,"props":252,"children":254},{"className":253},[],[255],{"type":46,"value":256},"show \u003Cid>",{"type":46,"value":258}," → show the full record.",{"type":41,"tag":102,"props":260,"children":261},{},[262,267],{"type":41,"tag":62,"props":263,"children":264},{},[265],{"type":46,"value":266},"On list, offer the dashboard:",{"type":46,"value":268},"\n\"Want the full dashboard? Filter by status \u002F tier \u002F EU nexus \u002F owner.\nSay the word.\"",{"type":41,"tag":102,"props":270,"children":271},{},[272,277,279],{"type":41,"tag":62,"props":273,"children":274},{},[275],{"type":46,"value":276},"Close every action with a hook into the lawyer's work.",{"type":46,"value":278},"\nAfter any write, say:",{"type":41,"tag":280,"props":281,"children":282},"blockquote",{},[283],{"type":41,"tag":56,"props":284,"children":285},{},[286],{"type":46,"value":287},"Recorded. When you're ready to walk through obligations for this\nsystem, just ask — I'll do it in-conversation and flag where the AI\nAct article mapping needs your verification. I don't derive\nobligations from a table because the mapping is complex and changing.",{"type":41,"tag":49,"props":289,"children":291},{"id":290},"list-format",[292],{"type":46,"value":293},"List format",{"type":41,"tag":56,"props":295,"children":296},{},[297],{"type":46,"value":298},"Render as a compact table:",{"type":41,"tag":300,"props":301,"children":302},"table",{},[303,352],{"type":41,"tag":304,"props":305,"children":306},"thead",{},[307],{"type":41,"tag":308,"props":309,"children":310},"tr",{},[311,317,322,327,332,337,342,347],{"type":41,"tag":312,"props":313,"children":314},"th",{},[315],{"type":46,"value":316},"ID",{"type":41,"tag":312,"props":318,"children":319},{},[320],{"type":46,"value":321},"Name",{"type":41,"tag":312,"props":323,"children":324},{},[325],{"type":46,"value":326},"Owner",{"type":41,"tag":312,"props":328,"children":329},{},[330],{"type":46,"value":331},"Status",{"type":41,"tag":312,"props":333,"children":334},{},[335],{"type":46,"value":336},"EU nexus",{"type":41,"tag":312,"props":338,"children":339},{},[340],{"type":46,"value":341},"Role",{"type":41,"tag":312,"props":343,"children":344},{},[345],{"type":46,"value":346},"Tier",{"type":41,"tag":312,"props":348,"children":349},{},[350],{"type":46,"value":351},"Next review",{"type":41,"tag":353,"props":354,"children":355},"tbody",{},[356,399],{"type":41,"tag":308,"props":357,"children":358},{},[359,365,370,375,380,385,389,394],{"type":41,"tag":360,"props":361,"children":362},"td",{},[363],{"type":46,"value":364},"sys-001",{"type":41,"tag":360,"props":366,"children":367},{},[368],{"type":46,"value":369},"Resume screening",{"type":41,"tag":360,"props":371,"children":372},{},[373],{"type":46,"value":374},"HR \u002F Jamie",{"type":41,"tag":360,"props":376,"children":377},{},[378],{"type":46,"value":379},"in_production",{"type":41,"tag":360,"props":381,"children":382},{},[383],{"type":46,"value":384},"yes",{"type":41,"tag":360,"props":386,"children":387},{},[388],{"type":46,"value":81},{"type":41,"tag":360,"props":390,"children":391},{},[392],{"type":46,"value":393},"high_risk",{"type":41,"tag":360,"props":395,"children":396},{},[397],{"type":46,"value":398},"2026-08-01",{"type":41,"tag":308,"props":400,"children":401},{},[402,407,412,417,421,426,430,435],{"type":41,"tag":360,"props":403,"children":404},{},[405],{"type":46,"value":406},"sys-002",{"type":41,"tag":360,"props":408,"children":409},{},[410],{"type":46,"value":411},"Email drafting assistant",{"type":41,"tag":360,"props":413,"children":414},{},[415],{"type":46,"value":416},"IT \u002F Priya",{"type":41,"tag":360,"props":418,"children":419},{},[420],{"type":46,"value":379},{"type":41,"tag":360,"props":422,"children":423},{},[424],{"type":46,"value":425},"no",{"type":41,"tag":360,"props":427,"children":428},{},[429],{"type":46,"value":81},{"type":41,"tag":360,"props":431,"children":432},{},[433],{"type":46,"value":434},"limited",{"type":41,"tag":360,"props":436,"children":437},{},[438],{"type":46,"value":439},"2026-12-01",{"type":41,"tag":56,"props":441,"children":442},{},[443],{"type":46,"value":444},"Under the table, show counts by tier and a line: \"N systems flagged for\nreview within 30 days.\"",{"type":41,"tag":49,"props":446,"children":448},{"id":447},"add-flow-interview",[449],{"type":46,"value":450},"Add flow (interview)",{"type":41,"tag":56,"props":452,"children":453},{},[454,456,462,464,470,471,477,478,484,485,491,493,499],{"type":46,"value":455},"Ask, one field at a time (or accept a paste). The required fields are\n",{"type":41,"tag":113,"props":457,"children":459},{"className":458},[],[460],{"type":46,"value":461},"name",{"type":46,"value":463},", ",{"type":41,"tag":113,"props":465,"children":467},{"className":466},[],[468],{"type":46,"value":469},"owner",{"type":46,"value":463},{"type":41,"tag":113,"props":472,"children":474},{"className":473},[],[475],{"type":46,"value":476},"description",{"type":46,"value":463},{"type":41,"tag":113,"props":479,"children":481},{"className":480},[],[482],{"type":46,"value":483},"status",{"type":46,"value":463},{"type":41,"tag":113,"props":486,"children":488},{"className":487},[],[489],{"type":46,"value":490},"eu_nexus",{"type":46,"value":492},". The rest can be\ndeferred — say so explicitly: \"you can come back to classification with\n",{"type":41,"tag":113,"props":494,"children":496},{"className":495},[],[497],{"type":46,"value":498},"\u002Fai-governance-legal:ai-inventory classify \u003Cid>",{"type":46,"value":500},".\"",{"type":41,"tag":98,"props":502,"children":503},{},[504,514,524,534,552,562],{"type":41,"tag":102,"props":505,"children":506},{},[507,512],{"type":41,"tag":62,"props":508,"children":509},{},[510],{"type":46,"value":511},"Name.",{"type":46,"value":513}," Short label for the system.",{"type":41,"tag":102,"props":515,"children":516},{},[517,522],{"type":41,"tag":62,"props":518,"children":519},{},[520],{"type":46,"value":521},"Owner.",{"type":46,"value":523}," Person or team accountable for it day-to-day.",{"type":41,"tag":102,"props":525,"children":526},{},[527,532],{"type":41,"tag":62,"props":528,"children":529},{},[530],{"type":46,"value":531},"Description.",{"type":46,"value":533}," One or two sentences. What does it do, and against\nwhat data?",{"type":41,"tag":102,"props":535,"children":536},{},[537,542,544,550],{"type":41,"tag":62,"props":538,"children":539},{},[540],{"type":46,"value":541},"Status.",{"type":46,"value":543}," ",{"type":41,"tag":113,"props":545,"children":547},{"className":546},[],[548],{"type":46,"value":549},"planned | in_development | in_production | deprecated",{"type":46,"value":551},".",{"type":41,"tag":102,"props":553,"children":554},{},[555,560],{"type":41,"tag":62,"props":556,"children":557},{},[558],{"type":46,"value":559},"EU nexus.",{"type":46,"value":561}," Is the system deployed in the EU\u002FEEA, offered to users in\nthe EU\u002FEEA, or used to produce outputs that affect people in the\nEU\u002FEEA? If any of these are true, EU AI Act analysis applies.",{"type":41,"tag":102,"props":563,"children":564},{},[565,570],{"type":41,"tag":62,"props":566,"children":567},{},[568],{"type":46,"value":569},"Proceed to classification?",{"type":46,"value":571}," Offer to run the walk-through now, or\nskip and come back later.",{"type":41,"tag":56,"props":573,"children":574},{},[575,577,583],{"type":46,"value":576},"Assign an ID: ",{"type":41,"tag":113,"props":578,"children":580},{"className":579},[],[581],{"type":46,"value":582},"sys-NNN",{"type":46,"value":584}," where NNN is the next integer in the file.",{"type":41,"tag":49,"props":586,"children":588},{"id":587},"classification-walk-through",[589],{"type":46,"value":245},{"type":41,"tag":56,"props":591,"children":592},{},[593,595,601,602,608,609,615,616,622,624,630],{"type":46,"value":594},"The walk-through produces ",{"type":41,"tag":113,"props":596,"children":598},{"className":597},[],[599],{"type":46,"value":600},"role",{"type":46,"value":463},{"type":41,"tag":113,"props":603,"children":605},{"className":604},[],[606],{"type":46,"value":607},"role_basis",{"type":46,"value":463},{"type":41,"tag":113,"props":610,"children":612},{"className":611},[],[613],{"type":46,"value":614},"tier",{"type":46,"value":463},{"type":41,"tag":113,"props":617,"children":619},{"className":618},[],[620],{"type":46,"value":621},"tier_basis",{"type":46,"value":623},". Both\nbases are tagged ",{"type":41,"tag":113,"props":625,"children":627},{"className":626},[],[628],{"type":46,"value":629},"[verify against current AI Act text]",{"type":46,"value":631}," — not because the\nskill is hedging, but because the article mapping is complex and the AI\nAct is still phasing in. The lawyer owns verification.",{"type":41,"tag":633,"props":634,"children":636},"h3",{"id":635},"step-1-role",[637],{"type":46,"value":638},"Step 1: Role",{"type":41,"tag":280,"props":640,"children":641},{},[642],{"type":41,"tag":56,"props":643,"children":644},{},[645],{"type":41,"tag":62,"props":646,"children":647},{},[648],{"type":46,"value":649},"Who does what to this system?",{"type":41,"tag":56,"props":651,"children":652},{},[653],{"type":46,"value":654},"Options, with the distinguishing test:",{"type":41,"tag":180,"props":656,"children":657},{},[658,668,678,688,698,708],{"type":41,"tag":102,"props":659,"children":660},{},[661,666],{"type":41,"tag":62,"props":662,"children":663},{},[664],{"type":46,"value":665},"Provider",{"type":46,"value":667}," — you develop it (or have it developed) and place it on the\nEU market or put it into service under your own name or trademark.",{"type":41,"tag":102,"props":669,"children":670},{},[671,676],{"type":41,"tag":62,"props":672,"children":673},{},[674],{"type":46,"value":675},"Deployer",{"type":46,"value":677}," — you use it under your own authority, not for personal\nnon-professional use. (Most common inside companies.)",{"type":41,"tag":102,"props":679,"children":680},{},[681,686],{"type":41,"tag":62,"props":682,"children":683},{},[684],{"type":46,"value":685},"Importer",{"type":46,"value":687}," — you bring an AI system into the EU from a provider\nestablished outside the EU.",{"type":41,"tag":102,"props":689,"children":690},{},[691,696],{"type":41,"tag":62,"props":692,"children":693},{},[694],{"type":46,"value":695},"Distributor",{"type":46,"value":697}," — you make an AI system available on the EU market\nwithout being the provider or importer.",{"type":41,"tag":102,"props":699,"children":700},{},[701,706],{"type":41,"tag":62,"props":702,"children":703},{},[704],{"type":46,"value":705},"Authorized representative",{"type":46,"value":707}," — you act on behalf of a non-EU provider\nand are established in the EU.",{"type":41,"tag":102,"props":709,"children":710},{},[711,716],{"type":41,"tag":62,"props":712,"children":713},{},[714],{"type":46,"value":715},"Product manufacturer",{"type":46,"value":717}," — you put a general-purpose AI system (or\nanother AI system) into a product under your own name\u002Ftrademark. Treated\nas provider for the product.",{"type":41,"tag":56,"props":719,"children":720},{},[721,726,728,732,734],{"type":41,"tag":62,"props":722,"children":723},{},[724],{"type":46,"value":725},"Dual-role flag.",{"type":46,"value":727}," If the user substantially modifies a vendor system\n(fine-tunes on their own data, changes the intended purpose, rebrands),\nthey may become a ",{"type":41,"tag":62,"props":729,"children":730},{},[731],{"type":46,"value":74},{"type":46,"value":733}," of the modified system even if they started\nas a deployer. Call this out when they describe any modification beyond\nconfiguration. ",{"type":41,"tag":113,"props":735,"children":737},{"className":736},[],[738],{"type":46,"value":739},"[verify against current AI Act text — Article 25, provider obligations and substantial modification]",{"type":41,"tag":56,"props":741,"children":742},{},[743,745,750],{"type":46,"value":744},"Write the role. Write ",{"type":41,"tag":113,"props":746,"children":748},{"className":747},[],[749],{"type":46,"value":607},{"type":46,"value":751}," in one sentence.",{"type":41,"tag":633,"props":753,"children":755},{"id":754},"step-2-tier",[756],{"type":46,"value":757},"Step 2: Tier",{"type":41,"tag":280,"props":759,"children":760},{},[761],{"type":41,"tag":56,"props":762,"children":763},{},[764],{"type":41,"tag":62,"props":765,"children":766},{},[767],{"type":46,"value":768},"What does the system do, and does the use case fall into a regulated\ncategory?",{"type":41,"tag":56,"props":770,"children":771},{},[772],{"type":46,"value":773},"Check in order:",{"type":41,"tag":56,"props":775,"children":776},{},[777,782,783],{"type":41,"tag":62,"props":778,"children":779},{},[780],{"type":46,"value":781},"A. Article 5 prohibited practices.",{"type":46,"value":543},{"type":41,"tag":113,"props":784,"children":786},{"className":785},[],[787],{"type":46,"value":788},"[verify against current AI Act text — Article 5]",{"type":41,"tag":56,"props":790,"children":791},{},[792],{"type":46,"value":793},"Summaries, not definitive text:",{"type":41,"tag":180,"props":795,"children":796},{},[797,802,807,812,817,822,827,832],{"type":41,"tag":102,"props":798,"children":799},{},[800],{"type":46,"value":801},"Subliminal or deceptive techniques materially distorting behavior",{"type":41,"tag":102,"props":803,"children":804},{},[805],{"type":46,"value":806},"Exploiting vulnerabilities (age, disability, socio-economic status) to\nmaterially distort behavior",{"type":41,"tag":102,"props":808,"children":809},{},[810],{"type":46,"value":811},"Social scoring by public authorities leading to detrimental treatment",{"type":41,"tag":102,"props":813,"children":814},{},[815],{"type":46,"value":816},"Real-time remote biometric ID in publicly accessible spaces for law\nenforcement (narrow exceptions)",{"type":41,"tag":102,"props":818,"children":819},{},[820],{"type":46,"value":821},"Biometric categorization inferring race, political opinions, union\nmembership, religious or philosophical beliefs, sex life, or sexual\norientation",{"type":41,"tag":102,"props":823,"children":824},{},[825],{"type":46,"value":826},"Emotion recognition in the workplace or education (medical and safety\nexceptions)",{"type":41,"tag":102,"props":828,"children":829},{},[830],{"type":46,"value":831},"Facial image database scraping from the internet or CCTV",{"type":41,"tag":102,"props":833,"children":834},{},[835],{"type":46,"value":836},"Predictive policing based solely on personality traits",{"type":41,"tag":56,"props":838,"children":839},{},[840,842,848],{"type":46,"value":841},"If matched → tier is ",{"type":41,"tag":113,"props":843,"children":845},{"className":844},[],[846],{"type":46,"value":847},"prohibited",{"type":46,"value":849},". Flag the use case as stop and route to\nthe governance team's prohibited-practice workflow.",{"type":41,"tag":56,"props":851,"children":852},{},[853,858,859],{"type":41,"tag":62,"props":854,"children":855},{},[856],{"type":46,"value":857},"B. Annex III high-risk areas.",{"type":46,"value":543},{"type":41,"tag":113,"props":860,"children":862},{"className":861},[],[863],{"type":46,"value":864},"[verify against current AI Act text — Annex III]",{"type":41,"tag":56,"props":866,"children":867},{},[868],{"type":46,"value":869},"Summaries:",{"type":41,"tag":98,"props":871,"children":872},{},[873,878,883,888,893,898,903,908],{"type":41,"tag":102,"props":874,"children":875},{},[876],{"type":46,"value":877},"Biometric identification and categorization",{"type":41,"tag":102,"props":879,"children":880},{},[881],{"type":46,"value":882},"Critical infrastructure (digital infrastructure, road traffic, supply of\nwater \u002F gas \u002F heating \u002F electricity)",{"type":41,"tag":102,"props":884,"children":885},{},[886],{"type":46,"value":887},"Education and vocational training (access, evaluation, proctoring,\nmonitoring prohibited behavior)",{"type":41,"tag":102,"props":889,"children":890},{},[891],{"type":46,"value":892},"Employment, worker management, self-employment access — recruitment,\nselection, promotion, termination, task allocation, monitoring, performance",{"type":41,"tag":102,"props":894,"children":895},{},[896],{"type":46,"value":897},"Essential private and public services (public benefits, credit scoring\nfor individuals, risk assessment and pricing for life\u002Fhealth insurance,\nemergency dispatch)",{"type":41,"tag":102,"props":899,"children":900},{},[901],{"type":46,"value":902},"Law enforcement (risk assessment, polygraphs, deepfake detection,\nreliability of evidence, profiling)",{"type":41,"tag":102,"props":904,"children":905},{},[906],{"type":46,"value":907},"Migration, asylum, border control (risk assessment, travel document\nverification, examination of applications)",{"type":41,"tag":102,"props":909,"children":910},{},[911],{"type":46,"value":912},"Administration of justice and democratic processes (research and\ninterpretation, influencing elections)",{"type":41,"tag":56,"props":914,"children":915},{},[916,917,922],{"type":46,"value":841},{"type":41,"tag":113,"props":918,"children":920},{"className":919},[],[921],{"type":46,"value":393},{"type":46,"value":923},". Note the Annex III area and subsection.",{"type":41,"tag":56,"props":925,"children":926},{},[927,932,933],{"type":41,"tag":62,"props":928,"children":929},{},[930],{"type":46,"value":931},"C. GPAI.",{"type":46,"value":543},{"type":41,"tag":113,"props":934,"children":936},{"className":935},[],[937],{"type":46,"value":938},"[verify against current AI Act text — Article 51 and surrounding]",{"type":41,"tag":180,"props":940,"children":941},{},[942,952],{"type":41,"tag":102,"props":943,"children":944},{},[945,950],{"type":41,"tag":62,"props":946,"children":947},{},[948],{"type":46,"value":949},"GPAI:",{"type":46,"value":951}," model trained on broad data at scale, designed for generality,\ncapable of competently performing a wide range of distinct tasks.",{"type":41,"tag":102,"props":953,"children":954},{},[955,960],{"type":41,"tag":62,"props":956,"children":957},{},[958],{"type":46,"value":959},"GPAI + systemic risk:",{"type":46,"value":961}," cumulative compute > 10^25 FLOPs, or designated\nby the Commission.",{"type":41,"tag":56,"props":963,"children":964},{},[965,970],{"type":41,"tag":62,"props":966,"children":967},{},[968],{"type":46,"value":969},"D. Limited risk.",{"type":46,"value":971}," Chatbots interacting with natural persons, deepfakes,\nemotion recognition and biometric categorization systems outside Article 5\nscope — transparency obligations apply.",{"type":41,"tag":56,"props":973,"children":974},{},[975,980],{"type":41,"tag":62,"props":976,"children":977},{},[978],{"type":46,"value":979},"E. Minimal risk.",{"type":46,"value":981}," Everything else.",{"type":41,"tag":56,"props":983,"children":984},{},[985,987,992,994,999],{"type":46,"value":986},"Write the tier. Write ",{"type":41,"tag":113,"props":988,"children":990},{"className":989},[],[991],{"type":46,"value":621},{"type":46,"value":993}," in one sentence, citing the article or\nAnnex entry that matched, tagged ",{"type":41,"tag":113,"props":995,"children":997},{"className":996},[],[998],{"type":46,"value":629},{"type":46,"value":551},{"type":41,"tag":633,"props":1001,"children":1003},{"id":1002},"step-3-recommendations",[1004],{"type":46,"value":1005},"Step 3: Recommendations",{"type":41,"tag":56,"props":1007,"children":1008},{},[1009],{"type":46,"value":1010},"Offer three next steps:",{"type":41,"tag":98,"props":1012,"children":1013},{},[1014,1019,1032],{"type":41,"tag":102,"props":1015,"children":1016},{},[1017],{"type":46,"value":1018},"\"Want me to walk through obligations for this system? I'll do it in\nconversation — I don't derive them from a table.\"",{"type":41,"tag":102,"props":1020,"children":1021},{},[1022,1024,1030],{"type":46,"value":1023},"\"Want to run ",{"type":41,"tag":113,"props":1025,"children":1027},{"className":1026},[],[1028],{"type":46,"value":1029},"\u002Fai-governance-legal:aia-generation",{"type":46,"value":1031}," to produce a full\nimpact assessment?\"",{"type":41,"tag":102,"props":1033,"children":1034},{},[1035],{"type":46,"value":1036},"\"Want to set a next review date? I'll add it to the inventory.\"",{"type":41,"tag":49,"props":1038,"children":1040},{"id":1039},"record-format",[1041],{"type":46,"value":1042},"Record format",{"type":41,"tag":1044,"props":1045,"children":1050},"pre",{"className":1046,"code":1047,"language":1048,"meta":1049,"style":1049},"language-yaml shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","systems:\n  - id: sys-001\n    name: \"Resume screening tool\"\n    owner: \"HR \u002F Jamie\"\n    description: \"Filters inbound CVs against job criteria\"\n    status: in_production          # planned | in_development | in_production | deprecated\n    eu_nexus: true                 # deployed, offered, or affects people in the EU\u002FEEA\n    role: deployer                 # provider | deployer | importer | distributor | authorized_rep | product_manufacturer\n    role_basis: \"We license from VendorX and deploy internally [verify against current AI Act text]\"\n    tier: high_risk                # prohibited | high_risk | limited | minimal | gpai | gpai_systemic\n    tier_basis: \"Annex III(4)(a) — employment, recruitment selection [verify against current AI Act text]\"\n    obligations_assessed: false\n    obligations_note: \"To assess: as deployer of a high-risk system — human oversight, input data quality, monitoring, record-keeping, informing workers, FRIA if public body\u002Fservice — see Article 26 [verify against current AI Act text]\"\n    next_review: \"2026-08-01\"\n    review_trigger: \"on substantial modification or annually\"\n    created: \"2026-05-11\"\n    updated: \"2026-05-11\"\n","yaml","",[1051],{"type":41,"tag":113,"props":1052,"children":1053},{"__ignoreMap":1049},[1054,1072,1097,1125,1150,1176,1200,1224,1247,1273,1296,1322,1340,1366,1391,1417,1443],{"type":41,"tag":1055,"props":1056,"children":1059},"span",{"class":1057,"line":1058},"line",1,[1060,1066],{"type":41,"tag":1055,"props":1061,"children":1063},{"style":1062},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[1064],{"type":46,"value":1065},"systems",{"type":41,"tag":1055,"props":1067,"children":1069},{"style":1068},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[1070],{"type":46,"value":1071},":\n",{"type":41,"tag":1055,"props":1073,"children":1075},{"class":1057,"line":1074},2,[1076,1081,1086,1091],{"type":41,"tag":1055,"props":1077,"children":1078},{"style":1068},[1079],{"type":46,"value":1080},"  -",{"type":41,"tag":1055,"props":1082,"children":1083},{"style":1062},[1084],{"type":46,"value":1085}," id",{"type":41,"tag":1055,"props":1087,"children":1088},{"style":1068},[1089],{"type":46,"value":1090},":",{"type":41,"tag":1055,"props":1092,"children":1094},{"style":1093},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1095],{"type":46,"value":1096}," sys-001\n",{"type":41,"tag":1055,"props":1098,"children":1100},{"class":1057,"line":1099},3,[1101,1106,1110,1115,1120],{"type":41,"tag":1055,"props":1102,"children":1103},{"style":1062},[1104],{"type":46,"value":1105},"    name",{"type":41,"tag":1055,"props":1107,"children":1108},{"style":1068},[1109],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1111,"children":1112},{"style":1068},[1113],{"type":46,"value":1114}," \"",{"type":41,"tag":1055,"props":1116,"children":1117},{"style":1093},[1118],{"type":46,"value":1119},"Resume screening tool",{"type":41,"tag":1055,"props":1121,"children":1122},{"style":1068},[1123],{"type":46,"value":1124},"\"\n",{"type":41,"tag":1055,"props":1126,"children":1128},{"class":1057,"line":1127},4,[1129,1134,1138,1142,1146],{"type":41,"tag":1055,"props":1130,"children":1131},{"style":1062},[1132],{"type":46,"value":1133},"    owner",{"type":41,"tag":1055,"props":1135,"children":1136},{"style":1068},[1137],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1139,"children":1140},{"style":1068},[1141],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1143,"children":1144},{"style":1093},[1145],{"type":46,"value":374},{"type":41,"tag":1055,"props":1147,"children":1148},{"style":1068},[1149],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1151,"children":1153},{"class":1057,"line":1152},5,[1154,1159,1163,1167,1172],{"type":41,"tag":1055,"props":1155,"children":1156},{"style":1062},[1157],{"type":46,"value":1158},"    description",{"type":41,"tag":1055,"props":1160,"children":1161},{"style":1068},[1162],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1164,"children":1165},{"style":1068},[1166],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1168,"children":1169},{"style":1093},[1170],{"type":46,"value":1171},"Filters inbound CVs against job criteria",{"type":41,"tag":1055,"props":1173,"children":1174},{"style":1068},[1175],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1177,"children":1179},{"class":1057,"line":1178},6,[1180,1185,1189,1194],{"type":41,"tag":1055,"props":1181,"children":1182},{"style":1062},[1183],{"type":46,"value":1184},"    status",{"type":41,"tag":1055,"props":1186,"children":1187},{"style":1068},[1188],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1190,"children":1191},{"style":1093},[1192],{"type":46,"value":1193}," in_production",{"type":41,"tag":1055,"props":1195,"children":1197},{"style":1196},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[1198],{"type":46,"value":1199},"          # planned | in_development | in_production | deprecated\n",{"type":41,"tag":1055,"props":1201,"children":1203},{"class":1057,"line":1202},7,[1204,1209,1213,1219],{"type":41,"tag":1055,"props":1205,"children":1206},{"style":1062},[1207],{"type":46,"value":1208},"    eu_nexus",{"type":41,"tag":1055,"props":1210,"children":1211},{"style":1068},[1212],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1214,"children":1216},{"style":1215},"--shiki-light:#FF5370;--shiki-default:#FF9CAC;--shiki-dark:#FF9CAC",[1217],{"type":46,"value":1218}," true",{"type":41,"tag":1055,"props":1220,"children":1221},{"style":1196},[1222],{"type":46,"value":1223},"                 # deployed, offered, or affects people in the EU\u002FEEA\n",{"type":41,"tag":1055,"props":1225,"children":1227},{"class":1057,"line":1226},8,[1228,1233,1237,1242],{"type":41,"tag":1055,"props":1229,"children":1230},{"style":1062},[1231],{"type":46,"value":1232},"    role",{"type":41,"tag":1055,"props":1234,"children":1235},{"style":1068},[1236],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1238,"children":1239},{"style":1093},[1240],{"type":46,"value":1241}," deployer",{"type":41,"tag":1055,"props":1243,"children":1244},{"style":1196},[1245],{"type":46,"value":1246},"                 # provider | deployer | importer | distributor | authorized_rep | product_manufacturer\n",{"type":41,"tag":1055,"props":1248,"children":1250},{"class":1057,"line":1249},9,[1251,1256,1260,1264,1269],{"type":41,"tag":1055,"props":1252,"children":1253},{"style":1062},[1254],{"type":46,"value":1255},"    role_basis",{"type":41,"tag":1055,"props":1257,"children":1258},{"style":1068},[1259],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1261,"children":1262},{"style":1068},[1263],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1265,"children":1266},{"style":1093},[1267],{"type":46,"value":1268},"We license from VendorX and deploy internally [verify against current AI Act text]",{"type":41,"tag":1055,"props":1270,"children":1271},{"style":1068},[1272],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1274,"children":1276},{"class":1057,"line":1275},10,[1277,1282,1286,1291],{"type":41,"tag":1055,"props":1278,"children":1279},{"style":1062},[1280],{"type":46,"value":1281},"    tier",{"type":41,"tag":1055,"props":1283,"children":1284},{"style":1068},[1285],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1287,"children":1288},{"style":1093},[1289],{"type":46,"value":1290}," high_risk",{"type":41,"tag":1055,"props":1292,"children":1293},{"style":1196},[1294],{"type":46,"value":1295},"                # prohibited | high_risk | limited | minimal | gpai | gpai_systemic\n",{"type":41,"tag":1055,"props":1297,"children":1299},{"class":1057,"line":1298},11,[1300,1305,1309,1313,1318],{"type":41,"tag":1055,"props":1301,"children":1302},{"style":1062},[1303],{"type":46,"value":1304},"    tier_basis",{"type":41,"tag":1055,"props":1306,"children":1307},{"style":1068},[1308],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1310,"children":1311},{"style":1068},[1312],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1314,"children":1315},{"style":1093},[1316],{"type":46,"value":1317},"Annex III(4)(a) — employment, recruitment selection [verify against current AI Act text]",{"type":41,"tag":1055,"props":1319,"children":1320},{"style":1068},[1321],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1323,"children":1325},{"class":1057,"line":1324},12,[1326,1331,1335],{"type":41,"tag":1055,"props":1327,"children":1328},{"style":1062},[1329],{"type":46,"value":1330},"    obligations_assessed",{"type":41,"tag":1055,"props":1332,"children":1333},{"style":1068},[1334],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1336,"children":1337},{"style":1215},[1338],{"type":46,"value":1339}," false\n",{"type":41,"tag":1055,"props":1341,"children":1343},{"class":1057,"line":1342},13,[1344,1349,1353,1357,1362],{"type":41,"tag":1055,"props":1345,"children":1346},{"style":1062},[1347],{"type":46,"value":1348},"    obligations_note",{"type":41,"tag":1055,"props":1350,"children":1351},{"style":1068},[1352],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1354,"children":1355},{"style":1068},[1356],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1358,"children":1359},{"style":1093},[1360],{"type":46,"value":1361},"To assess: as deployer of a high-risk system — human oversight, input data quality, monitoring, record-keeping, informing workers, FRIA if public body\u002Fservice — see Article 26 [verify against current AI Act text]",{"type":41,"tag":1055,"props":1363,"children":1364},{"style":1068},[1365],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1367,"children":1369},{"class":1057,"line":1368},14,[1370,1375,1379,1383,1387],{"type":41,"tag":1055,"props":1371,"children":1372},{"style":1062},[1373],{"type":46,"value":1374},"    next_review",{"type":41,"tag":1055,"props":1376,"children":1377},{"style":1068},[1378],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1380,"children":1381},{"style":1068},[1382],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1384,"children":1385},{"style":1093},[1386],{"type":46,"value":398},{"type":41,"tag":1055,"props":1388,"children":1389},{"style":1068},[1390],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1392,"children":1394},{"class":1057,"line":1393},15,[1395,1400,1404,1408,1413],{"type":41,"tag":1055,"props":1396,"children":1397},{"style":1062},[1398],{"type":46,"value":1399},"    review_trigger",{"type":41,"tag":1055,"props":1401,"children":1402},{"style":1068},[1403],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1405,"children":1406},{"style":1068},[1407],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1409,"children":1410},{"style":1093},[1411],{"type":46,"value":1412},"on substantial modification or annually",{"type":41,"tag":1055,"props":1414,"children":1415},{"style":1068},[1416],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1418,"children":1420},{"class":1057,"line":1419},16,[1421,1426,1430,1434,1439],{"type":41,"tag":1055,"props":1422,"children":1423},{"style":1062},[1424],{"type":46,"value":1425},"    created",{"type":41,"tag":1055,"props":1427,"children":1428},{"style":1068},[1429],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1431,"children":1432},{"style":1068},[1433],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1435,"children":1436},{"style":1093},[1437],{"type":46,"value":1438},"2026-05-11",{"type":41,"tag":1055,"props":1440,"children":1441},{"style":1068},[1442],{"type":46,"value":1124},{"type":41,"tag":1055,"props":1444,"children":1446},{"class":1057,"line":1445},17,[1447,1452,1456,1460,1464],{"type":41,"tag":1055,"props":1448,"children":1449},{"style":1062},[1450],{"type":46,"value":1451},"    updated",{"type":41,"tag":1055,"props":1453,"children":1454},{"style":1068},[1455],{"type":46,"value":1090},{"type":41,"tag":1055,"props":1457,"children":1458},{"style":1068},[1459],{"type":46,"value":1114},{"type":41,"tag":1055,"props":1461,"children":1462},{"style":1093},[1463],{"type":46,"value":1438},{"type":41,"tag":1055,"props":1465,"children":1466},{"style":1068},[1467],{"type":46,"value":1124},{"type":41,"tag":49,"props":1469,"children":1471},{"id":1470},"why-this-skill-does-not-auto-derive-obligations",[1472],{"type":46,"value":1473},"Why this skill does NOT auto-derive obligations",{"type":41,"tag":56,"props":1475,"children":1476},{},[1477],{"type":46,"value":1478},"The inventory stores role, tier, and the basis for each. It does NOT\ncontain a hardcoded role × tier → obligations table.",{"type":41,"tag":56,"props":1480,"children":1481},{},[1482,1484,1489,1491,1497,1499,1504],{"type":46,"value":1483},"When the user asks \"what are my obligations for System X?\", the skill\ndoes the analysis ",{"type":41,"tag":62,"props":1485,"children":1486},{},[1487],{"type":46,"value":1488},"in conversation",{"type":46,"value":1490},", tagged ",{"type":41,"tag":113,"props":1492,"children":1494},{"className":1493},[],[1495],{"type":46,"value":1496},"[verify]",{"type":46,"value":1498},", and routes to\n",{"type":41,"tag":113,"props":1500,"children":1502},{"className":1501},[],[1503],{"type":46,"value":1029},{"type":46,"value":1505}," for the formal impact assessment\nif needed.",{"type":41,"tag":56,"props":1507,"children":1508},{},[1509],{"type":46,"value":1510},"This is deliberate:",{"type":41,"tag":180,"props":1512,"children":1513},{},[1514,1519,1524],{"type":41,"tag":102,"props":1515,"children":1516},{},[1517],{"type":46,"value":1518},"Article mapping is complex and the AI Act is phasing in through 2027.",{"type":41,"tag":102,"props":1520,"children":1521},{},[1522],{"type":46,"value":1523},"Confident-and-wrong on a compliance obligation ends up in a board memo.",{"type":41,"tag":102,"props":1525,"children":1526},{},[1527],{"type":46,"value":1528},"The inventory is a registry for the lawyer. The lawyer owns the\nobligation analysis.",{"type":41,"tag":49,"props":1530,"children":1532},{"id":1531},"guardrails",[1533],{"type":46,"value":1534},"Guardrails",{"type":41,"tag":180,"props":1536,"children":1537},{},[1538,1548,1563,1581],{"type":41,"tag":102,"props":1539,"children":1540},{},[1541,1546],{"type":41,"tag":62,"props":1542,"children":1543},{},[1544],{"type":46,"value":1545},"Never classify silently.",{"type":46,"value":1547}," The classification walk-through must be\nvisible; do not auto-classify from a system description.",{"type":41,"tag":102,"props":1549,"children":1550},{},[1551,1561],{"type":41,"tag":62,"props":1552,"children":1553},{},[1554,1559],{"type":41,"tag":113,"props":1555,"children":1557},{"className":1556},[],[1558],{"type":46,"value":1496},{"type":46,"value":1560}," tags stay.",{"type":46,"value":1562}," They are not hedging — they are the point.\nDo not strip them in outputs.",{"type":41,"tag":102,"props":1564,"children":1565},{},[1566,1571,1573,1579],{"type":41,"tag":62,"props":1567,"children":1568},{},[1569],{"type":46,"value":1570},"Flag substantial modification.",{"type":46,"value":1572}," Whenever a system is modified beyond\nconfiguration, prompt the user to re-run ",{"type":41,"tag":113,"props":1574,"children":1576},{"className":1575},[],[1577],{"type":46,"value":1578},"\u002Fai-inventory classify",{"type":46,"value":1580}," —\nmodification can change role.",{"type":41,"tag":102,"props":1582,"children":1583},{},[1584,1589,1591,1597],{"type":41,"tag":62,"props":1585,"children":1586},{},[1587],{"type":46,"value":1588},"Don't declare obligations from a table.",{"type":46,"value":1590}," If asked, do the analysis\nin conversation and route to ",{"type":41,"tag":113,"props":1592,"children":1594},{"className":1593},[],[1595],{"type":46,"value":1596},"\u002Faia-generation",{"type":46,"value":1598}," for anything that needs\na formal record.",{"type":41,"tag":1600,"props":1601,"children":1602},"style",{},[1603],{"type":46,"value":1604},"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":1606,"total":1696},[1607,1613,1630,1647,1659,1670,1681],{"slug":4,"name":4,"fn":5,"description":6,"org":1608,"tags":1609,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1610,1611,1612],{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"slug":1614,"name":1614,"fn":1615,"description":1616,"org":1617,"tags":1618,"stars":23,"repoUrl":24,"updatedAt":1629},"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},[1619,1622,1625,1626],{"name":1620,"slug":1621,"type":16},"Automation","automation",{"name":1623,"slug":1624,"type":16},"Contracts","contracts",{"name":21,"slug":22,"type":16},{"name":1627,"slug":1628,"type":16},"QA","qa","2026-05-14T06:01:31.00555",{"slug":1631,"name":1631,"fn":1632,"description":1633,"org":1634,"tags":1635,"stars":23,"repoUrl":24,"updatedAt":1646},"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},[1636,1637,1640,1643],{"name":21,"slug":22,"type":16},{"name":1638,"slug":1639,"type":16},"Policy","policy",{"name":1641,"slug":1642,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":1644,"slug":1645,"type":16},"Risk Assessment","risk-assessment","2026-05-13T06:03:19.61029",{"slug":1648,"name":1648,"fn":1649,"description":1650,"org":1651,"tags":1652,"stars":23,"repoUrl":24,"updatedAt":1658},"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},[1653,1654,1657],{"name":1623,"slug":1624,"type":16},{"name":1655,"slug":1656,"type":16},"Documents","documents",{"name":21,"slug":22,"type":16},"2026-05-13T06:03:34.070339",{"slug":1660,"name":1660,"fn":1661,"description":1662,"org":1663,"tags":1664,"stars":23,"repoUrl":24,"updatedAt":1669},"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},[1665,1666],{"name":1620,"slug":1621,"type":16},{"name":1667,"slug":1668,"type":16},"Plugin Development","plugin-development","2026-05-13T06:02:55.642269",{"slug":1671,"name":1671,"fn":1672,"description":1673,"org":1674,"tags":1675,"stars":23,"repoUrl":24,"updatedAt":1680},"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},[1676,1679],{"name":1677,"slug":1678,"type":16},"Education","education",{"name":21,"slug":22,"type":16},"2026-07-24T05:41:43.01243",{"slug":1682,"name":1682,"fn":1683,"description":1684,"org":1685,"tags":1686,"stars":23,"repoUrl":24,"updatedAt":1695},"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},[1687,1690,1691,1692],{"name":1688,"slug":1689,"type":16},"Documentation","documentation",{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":1693,"slug":1694,"type":16},"Meetings","meetings","2026-05-14T06:01:29.792942",118,{"items":1698,"total":1881},[1699,1720,1734,1746,1765,1776,1795,1815,1829,1844,1852,1865],{"slug":1700,"name":1700,"fn":1701,"description":1702,"org":1703,"tags":1704,"stars":1717,"repoUrl":1718,"updatedAt":1719},"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},[1705,1708,1711,1714],{"name":1706,"slug":1707,"type":16},"Creative","creative",{"name":1709,"slug":1710,"type":16},"Design","design",{"name":1712,"slug":1713,"type":16},"Generative Art","generative-art",{"name":1715,"slug":1716,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":1721,"name":1721,"fn":1722,"description":1723,"org":1724,"tags":1725,"stars":1717,"repoUrl":1718,"updatedAt":1733},"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},[1726,1729,1730],{"name":1727,"slug":1728,"type":16},"Branding","branding",{"name":1709,"slug":1710,"type":16},{"name":1731,"slug":1732,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":1735,"name":1735,"fn":1736,"description":1737,"org":1738,"tags":1739,"stars":1717,"repoUrl":1718,"updatedAt":1745},"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},[1740,1741,1742],{"name":1706,"slug":1707,"type":16},{"name":1709,"slug":1710,"type":16},{"name":1743,"slug":1744,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":1747,"name":1747,"fn":1748,"description":1749,"org":1750,"tags":1751,"stars":1717,"repoUrl":1718,"updatedAt":1764},"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},[1752,1755,1756,1759,1761],{"name":1753,"slug":1754,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":1757,"slug":1758,"type":16},"Anthropic SDK","anthropic-sdk",{"name":1760,"slug":1747,"type":16},"Claude API",{"name":1762,"slug":1763,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":1766,"name":1766,"fn":1767,"description":1768,"org":1769,"tags":1770,"stars":1717,"repoUrl":1718,"updatedAt":1775},"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},[1771,1772],{"name":1688,"slug":1689,"type":16},{"name":1773,"slug":1774,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":1777,"name":1777,"fn":1778,"description":1779,"org":1780,"tags":1781,"stars":1717,"repoUrl":1718,"updatedAt":1794},"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},[1782,1783,1785,1788,1791],{"name":1655,"slug":1656,"type":16},{"name":1784,"slug":1777,"type":16},"DOCX",{"name":1786,"slug":1787,"type":16},"Office","office",{"name":1789,"slug":1790,"type":16},"Templates","templates",{"name":1792,"slug":1793,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1796,"name":1796,"fn":1797,"description":1798,"org":1799,"tags":1800,"stars":1717,"repoUrl":1718,"updatedAt":1814},"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},[1801,1802,1805,1808,1811],{"name":1709,"slug":1710,"type":16},{"name":1803,"slug":1804,"type":16},"Frontend","frontend",{"name":1806,"slug":1807,"type":16},"React","react",{"name":1809,"slug":1810,"type":16},"Tailwind CSS","tailwind-css",{"name":1812,"slug":1813,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1816,"name":1816,"fn":1817,"description":1818,"org":1819,"tags":1820,"stars":1717,"repoUrl":1718,"updatedAt":1828},"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},[1821,1824,1825],{"name":1822,"slug":1823,"type":16},"Communications","communications",{"name":1789,"slug":1790,"type":16},{"name":1826,"slug":1827,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1830,"name":1830,"fn":1831,"description":1832,"org":1833,"tags":1834,"stars":1717,"repoUrl":1718,"updatedAt":1843},"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},[1835,1836,1839,1840],{"name":1753,"slug":1754,"type":16},{"name":1837,"slug":1838,"type":16},"API Development","api-development",{"name":1762,"slug":1763,"type":16},{"name":1841,"slug":1842,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":1744,"name":1744,"fn":1845,"description":1846,"org":1847,"tags":1848,"stars":1717,"repoUrl":1718,"updatedAt":1851},"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},[1849,1850],{"name":1655,"slug":1656,"type":16},{"name":1743,"slug":1744,"type":16},"2026-04-06T17:56:02.483316",{"slug":1853,"name":1853,"fn":1854,"description":1855,"org":1856,"tags":1857,"stars":1717,"repoUrl":1718,"updatedAt":1864},"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},[1858,1861],{"name":1859,"slug":1860,"type":16},"PowerPoint","powerpoint",{"name":1862,"slug":1863,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1866,"name":1866,"fn":1867,"description":1868,"org":1869,"tags":1870,"stars":1717,"repoUrl":1718,"updatedAt":1880},"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},[1871,1872,1873,1876,1879],{"name":1753,"slug":1754,"type":16},{"name":1688,"slug":1689,"type":16},{"name":1874,"slug":1875,"type":16},"Evals","evals",{"name":1877,"slug":1878,"type":16},"Performance","performance",{"name":1773,"slug":1774,"type":16},"2026-04-19T06:45:40.804",490]