[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-is-this-a-problem":3,"mdc-2y9n6y-key":37,"related-repo-anthropic-is-this-a-problem":817,"related-org-anthropic-is-this-a-problem":915},{"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},"is-this-a-problem","provide rapid legal risk assessments","Fast \"is this a problem?\" answer for the quick Slack question — pattern-matches against your calibration. Use when the user says \"is this a problem\", \"quick question\", \"can we do X\", \"do I need legal review for\", \"sanity check\", or pastes a PM's question that needs a same-minute fine \u002F needs a look \u002F hold call.\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},"Slack","slack","tag",{"name":18,"slug":19,"type":16},"Legal","legal",{"name":21,"slug":22,"type":16},"Communications","communications",{"name":24,"slug":25,"type":16},"Risk Assessment","risk-assessment",8721,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal","2026-05-13T06:04:23.20749",null,1642,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"A suite of plugins for legal workflows","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-for-legal\u002Ftree\u002FHEAD\u002Fproduct-legal\u002Fskills\u002Fis-this-a-problem","---\nname: is-this-a-problem\ndescription: >\n  Fast \"is this a problem?\" answer for the quick Slack question — pattern-matches\n  against your calibration. Use when the user says \"is this a problem\", \"quick\n  question\", \"can we do X\", \"do I need legal review for\", \"sanity check\", or\n  pastes a PM's question that needs a same-minute fine \u002F needs a look \u002F hold call.\nargument-hint: \"[the question]\"\n---\n\n# \u002Fis-this-a-problem\n\n1. Load `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md` → Risk calibration.\n2. Apply the triage workflow below.\n3. Pattern-match. Check for common traps.\n4. Answer in one minute: ✅ Fine \u002F ⚠️ Needs a look \u002F 🛑 Hold. One sentence why.\n5. If ⚠️ or 🛑: name the next step.\n\n```\n\u002Fproduct-legal:is-this-a-problem \"Can we use customer logos on the pricing page?\"\n```\n\n---\n\n## Matter context\n\n**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: \"Which matter is this for? Run `\u002Fproduct-legal:matter-workspace switch \u003Cslug>` or say `practice-level`.\" Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F`. Never read another matter's files unless `Cross-matter context` is `on`.\n\n---\n\n## Destination check\n\nBefore producing output, check where it's going. If the user has named a destination (a channel, a distribution list, a counterparty, \"everyone\"), ask whether it's inside the privilege circle. Public channels, company-wide lists, counterparty\u002Fopposing counsel, vendors, and clients (for work product) waive the protection. When the destination looks outside the circle, flag it and offer (a) the privileged version for legal only, (b) a sanitized version for the broader channel, or (c) both — don't silently apply a privileged header and then help paste it somewhere the header won't protect it. See the canonical `## Shared guardrails → Destination check` in this plugin's CLAUDE.md.\n\n## Purpose\n\nMost \"quick legal question\" Slacks are one of three things: (a) not a problem, say so fast, (b) a real thing that needs a real look, route it, (c) a thing that looks fine but has a trap, catch the trap. This skill sorts in under a minute using the calibration table.\n\nThe goal is speed. The PM asked at 4:47pm. They want an answer, not a memo.\n\n## Load calibration\n\nRead `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md` → `## Risk calibration`. The whole point of this skill is pattern-matching against that table.\n\n## The triage\n\n### Match against calibration\n\nDoes the question match a pattern in the calibration table?\n\n**Matches \"usually FYI\":**\n→ Say so. One line. \"You're fine — [pattern]. Ship it.\"\n\n**Matches \"usually requires work\":**\n→ Name the work. \"Needs a [PIA \u002F vendor review \u002F claims check]. Takes [timeline from table]. Want me to start it?\"\n\n**Matches \"usually blocks\":**\n→ Stop them. \"Hold on — [pattern]. This needs a real look before anyone commits to a date. Let's talk.\"\n\n**Doesn't match anything:**\n→ Say that too. \"This doesn't pattern-match to anything I've seen here. Needs a human look — [your name] or me tomorrow?\"\n\n### The trap check\n\nSome questions are fine on the surface but have a twist. Recognize the fact pattern, ask the catch question, then research the applicable doctrine for the specific fact pattern before concluding whether it's a problem or not.\n\n| Question sounds like | Why it might not be simple | Catch it by asking |\n|---|---|---|\n| \"Can we add [vendor] to the integration?\" | Vendor touches a new data category — flag as potentially implicating privacy and vendor-risk regimes and route for research | \"What data flows to them?\" |\n| \"Can we A\u002FB test the pricing page?\" | Differential pricing by segment can implicate consumer-protection and anti-discrimination regimes — flag and route for research | \"Are both arms seeing the same price for the same thing? How are users assigned to arms?\" |\n| \"Can we auto-enroll users in the new feature?\" | Default-on behavior for users who previously opted out can implicate consent and consumer-protection rules — flag and route for research | \"Does this respect existing preferences?\" |\n| \"Can we use customer logos on the site?\" | Logo use is a separate permission from the contract relationship — flag as potentially implicating publicity \u002F endorsement rules and the customer's own contract terms | \"What does the contract say about publicity? Do we have written permission?\" |\n| \"Can we train on this data?\" | Usage rights for the original collection purpose may not extend to training — flag and research the notice\u002Fconsent the users were given at collection | \"What did we tell users when we collected it? What jurisdictions are the users in?\" |\n| \"It's just an internal tool\" | Internal tools still process personal data — flag as potentially implicating privacy regimes and route for research | \"Whose data does it touch? Employees, customers, third parties?\" |\n| \"We already do something similar\" | \"Similar\" is doing a lot of work — the delta is where the issue usually is | \"Similar how? What's actually different?\" |\n| \"Can we use [AI vendor \u002F LLM] for this?\" | Vendor AI terms may permit training on inputs; use case may need an AIA — flag and route to `\u002Fai-governance-legal:use-case-triage` | \"Is there an AI addendum? What data goes into the model?\" |\n| \"Can we add AI to this feature?\" | May be a new use case not in the registry; may trigger AIA requirement — flag and route to `\u002Fai-governance-legal:use-case-triage` | \"What does the AI do — assistive or automated? Who does it act on?\" |\n| \"The model just decides automatically\" | Automated decision-making without human review is regulated in some jurisdictions — flag and research the applicable rules for the affected users' jurisdictions | \"Who's affected? Is there a human in the loop? Where are the affected users?\" |\n| \"It's AI-generated content\" | Output IP and disclosure duties vary by jurisdiction and vendor terms — flag and route for research | \"What's the content type? Does the vendor's ToS address output ownership? Who is the audience?\" |\n| \"We're just fine-tuning on our data\" | Training data rights, output IP, and vendor obligations all change — flag and route to `\u002Fai-governance-legal:vendor-ai-review` | \"What's in the training data? Is any of it customer or employee data?\" |\n\nIf a trap might be present, ask the one question before answering. One question, not a checklist. When the answer suggests a real issue, flag for research and route — don't pattern-match to a legal conclusion from the question alone.\n\n## Output format\n\n**For Slack (the common case):**\n\nSlack triage replies are internal legal advice. If the reply is being pasted into a ticket, document, or channel that's broadly shared with non-legal, prepend the work-product header from `~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md` `## Outputs` (it differs by user role — see `## Who's using this`):\n\n```\n[WORK-PRODUCT HEADER — per plugin config ## Outputs]\n```\n\nFor an in-the-flow Slack DM reply to the PM, the short form is:\n\n```\n[✅ Fine | ⚠️ Needs a look | 🛑 Hold]\n\n[One sentence: the call and why.]\n\n[If ⚠️: what the look involves, how long]\n[If 🛑: who to talk to, when]\n```\n\n**Examples:**\n\n```\n✅ Fine — adding an analytics event is an FYI here as long as it's covered by\nthe existing privacy policy categories. This one is.\n```\n\n```\n⚠️ Needs a PIA — new data collection for [category]. Usually takes a day.\nWant me to kick it off?\n```\n\n```\n🛑 Hold — \"train on customer data\" triggers a bunch of things. What did the\ncustomer agreement say about data use? Let's pull it before anyone promises\nthis to the customer.\n```\n\n```\n⚠️ Needs an AI governance triage — adding an LLM to this workflow means we need\nto check the use case against the registry and confirm an AIA is done before it\nships. Takes a day. Want me to run `\u002Fai-governance-legal:use-case-triage` now?\n```\n\n## When to NOT use this skill\n\n- The question is actually complex (multiple issues, novel area) → route to launch-review or feature-risk-assessment\n- The question is \"can you review this PRD\" → that's launch-review, not triage\n- You're not sure → say \"I'm not sure, let me look properly\" — a wrong fast answer is worse than a slow right one\n\n## Tone\n\nFast, direct, helpful. The PM is not asking for a lecture. If it's fine, say \"fine\" — don't list the seven things you checked. If it's not fine, say what's not fine and what to do about it.\n\nYou are the lawyer people want to ask, not the one they route around.\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",{"data":38,"body":40},{"name":4,"description":6,"argument-hint":39},"[the question]",{"type":41,"children":42},"root",[43,51,90,102,106,113,196,199,205,218,224,229,234,240,260,266,273,278,296,320,336,353,359,364,644,649,655,663,691,700,705,714,722,731,740,749,758,764,783,789,794,799,805],{"type":44,"tag":45,"props":46,"children":47},"element","h1",{"id":4},[48],{"type":49,"value":50},"text","\u002Fis-this-a-problem",{"type":44,"tag":52,"props":53,"children":54},"ol",{},[55,70,75,80,85],{"type":44,"tag":56,"props":57,"children":58},"li",{},[59,61,68],{"type":49,"value":60},"Load ",{"type":44,"tag":62,"props":63,"children":65},"code",{"className":64},[],[66],{"type":49,"value":67},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002FCLAUDE.md",{"type":49,"value":69}," → Risk calibration.",{"type":44,"tag":56,"props":71,"children":72},{},[73],{"type":49,"value":74},"Apply the triage workflow below.",{"type":44,"tag":56,"props":76,"children":77},{},[78],{"type":49,"value":79},"Pattern-match. Check for common traps.",{"type":44,"tag":56,"props":81,"children":82},{},[83],{"type":49,"value":84},"Answer in one minute: ✅ Fine \u002F ⚠️ Needs a look \u002F 🛑 Hold. One sentence why.",{"type":44,"tag":56,"props":86,"children":87},{},[88],{"type":49,"value":89},"If ⚠️ or 🛑: name the next step.",{"type":44,"tag":91,"props":92,"children":96},"pre",{"className":93,"code":95,"language":49},[94],"language-text","\u002Fproduct-legal:is-this-a-problem \"Can we use customer logos on the pricing page?\"\n",[97],{"type":44,"tag":62,"props":98,"children":100},{"__ignoreMap":99},"",[101],{"type":49,"value":95},{"type":44,"tag":103,"props":104,"children":105},"hr",{},[],{"type":44,"tag":107,"props":108,"children":110},"h2",{"id":109},"matter-context",[111],{"type":49,"value":112},"Matter context",{"type":44,"tag":114,"props":115,"children":116},"p",{},[117,123,125,131,133,139,141,147,149,155,157,163,165,171,173,179,181,187,188,194],{"type":44,"tag":118,"props":119,"children":120},"strong",{},[121],{"type":49,"value":122},"Matter context.",{"type":49,"value":124}," Check ",{"type":44,"tag":62,"props":126,"children":128},{"className":127},[],[129],{"type":49,"value":130},"## Matter workspaces",{"type":49,"value":132}," in the practice-level CLAUDE.md. If ",{"type":44,"tag":62,"props":134,"children":136},{"className":135},[],[137],{"type":49,"value":138},"Enabled",{"type":49,"value":140}," is ",{"type":44,"tag":62,"props":142,"children":144},{"className":143},[],[145],{"type":49,"value":146},"✗",{"type":49,"value":148}," (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":44,"tag":62,"props":150,"children":152},{"className":151},[],[153],{"type":49,"value":154},"\u002Fproduct-legal:matter-workspace switch \u003Cslug>",{"type":49,"value":156}," or say ",{"type":44,"tag":62,"props":158,"children":160},{"className":159},[],[161],{"type":49,"value":162},"practice-level",{"type":49,"value":164},".\" Load the active matter's ",{"type":44,"tag":62,"props":166,"children":168},{"className":167},[],[169],{"type":49,"value":170},"matter.md",{"type":49,"value":172}," for matter-specific context and overrides. Write outputs to the matter folder at ",{"type":44,"tag":62,"props":174,"children":176},{"className":175},[],[177],{"type":49,"value":178},"~\u002F.claude\u002Fplugins\u002Fconfig\u002Fclaude-for-legal\u002Fproduct-legal\u002Fmatters\u002F\u003Cmatter-slug>\u002F",{"type":49,"value":180},". Never read another matter's files unless ",{"type":44,"tag":62,"props":182,"children":184},{"className":183},[],[185],{"type":49,"value":186},"Cross-matter context",{"type":49,"value":140},{"type":44,"tag":62,"props":189,"children":191},{"className":190},[],[192],{"type":49,"value":193},"on",{"type":49,"value":195},".",{"type":44,"tag":103,"props":197,"children":198},{},[],{"type":44,"tag":107,"props":200,"children":202},{"id":201},"destination-check",[203],{"type":49,"value":204},"Destination check",{"type":44,"tag":114,"props":206,"children":207},{},[208,210,216],{"type":49,"value":209},"Before producing output, check where it's going. If the user has named a destination (a channel, a distribution list, a counterparty, \"everyone\"), ask whether it's inside the privilege circle. Public channels, company-wide lists, counterparty\u002Fopposing counsel, vendors, and clients (for work product) waive the protection. When the destination looks outside the circle, flag it and offer (a) the privileged version for legal only, (b) a sanitized version for the broader channel, or (c) both — don't silently apply a privileged header and then help paste it somewhere the header won't protect it. See the canonical ",{"type":44,"tag":62,"props":211,"children":213},{"className":212},[],[214],{"type":49,"value":215},"## Shared guardrails → Destination check",{"type":49,"value":217}," in this plugin's CLAUDE.md.",{"type":44,"tag":107,"props":219,"children":221},{"id":220},"purpose",[222],{"type":49,"value":223},"Purpose",{"type":44,"tag":114,"props":225,"children":226},{},[227],{"type":49,"value":228},"Most \"quick legal question\" Slacks are one of three things: (a) not a problem, say so fast, (b) a real thing that needs a real look, route it, (c) a thing that looks fine but has a trap, catch the trap. This skill sorts in under a minute using the calibration table.",{"type":44,"tag":114,"props":230,"children":231},{},[232],{"type":49,"value":233},"The goal is speed. The PM asked at 4:47pm. They want an answer, not a memo.",{"type":44,"tag":107,"props":235,"children":237},{"id":236},"load-calibration",[238],{"type":49,"value":239},"Load calibration",{"type":44,"tag":114,"props":241,"children":242},{},[243,245,250,252,258],{"type":49,"value":244},"Read ",{"type":44,"tag":62,"props":246,"children":248},{"className":247},[],[249],{"type":49,"value":67},{"type":49,"value":251}," → ",{"type":44,"tag":62,"props":253,"children":255},{"className":254},[],[256],{"type":49,"value":257},"## Risk calibration",{"type":49,"value":259},". The whole point of this skill is pattern-matching against that table.",{"type":44,"tag":107,"props":261,"children":263},{"id":262},"the-triage",[264],{"type":49,"value":265},"The triage",{"type":44,"tag":267,"props":268,"children":270},"h3",{"id":269},"match-against-calibration",[271],{"type":49,"value":272},"Match against calibration",{"type":44,"tag":114,"props":274,"children":275},{},[276],{"type":49,"value":277},"Does the question match a pattern in the calibration table?",{"type":44,"tag":114,"props":279,"children":280},{},[281,286,288,294],{"type":44,"tag":118,"props":282,"children":283},{},[284],{"type":49,"value":285},"Matches \"usually FYI\":",{"type":49,"value":287},"\n→ Say so. One line. \"You're fine — ",{"type":44,"tag":289,"props":290,"children":291},"span",{},[292],{"type":49,"value":293},"pattern",{"type":49,"value":295},". Ship it.\"",{"type":44,"tag":114,"props":297,"children":298},{},[299,304,306,311,313,318],{"type":44,"tag":118,"props":300,"children":301},{},[302],{"type":49,"value":303},"Matches \"usually requires work\":",{"type":49,"value":305},"\n→ Name the work. \"Needs a ",{"type":44,"tag":289,"props":307,"children":308},{},[309],{"type":49,"value":310},"PIA \u002F vendor review \u002F claims check",{"type":49,"value":312},". Takes ",{"type":44,"tag":289,"props":314,"children":315},{},[316],{"type":49,"value":317},"timeline from table",{"type":49,"value":319},". Want me to start it?\"",{"type":44,"tag":114,"props":321,"children":322},{},[323,328,330,334],{"type":44,"tag":118,"props":324,"children":325},{},[326],{"type":49,"value":327},"Matches \"usually blocks\":",{"type":49,"value":329},"\n→ Stop them. \"Hold on — ",{"type":44,"tag":289,"props":331,"children":332},{},[333],{"type":49,"value":293},{"type":49,"value":335},". This needs a real look before anyone commits to a date. Let's talk.\"",{"type":44,"tag":114,"props":337,"children":338},{},[339,344,346,351],{"type":44,"tag":118,"props":340,"children":341},{},[342],{"type":49,"value":343},"Doesn't match anything:",{"type":49,"value":345},"\n→ Say that too. \"This doesn't pattern-match to anything I've seen here. Needs a human look — ",{"type":44,"tag":289,"props":347,"children":348},{},[349],{"type":49,"value":350},"your name",{"type":49,"value":352}," or me tomorrow?\"",{"type":44,"tag":267,"props":354,"children":356},{"id":355},"the-trap-check",[357],{"type":49,"value":358},"The trap check",{"type":44,"tag":114,"props":360,"children":361},{},[362],{"type":49,"value":363},"Some questions are fine on the surface but have a twist. Recognize the fact pattern, ask the catch question, then research the applicable doctrine for the specific fact pattern before concluding whether it's a problem or not.",{"type":44,"tag":365,"props":366,"children":367},"table",{},[368,392],{"type":44,"tag":369,"props":370,"children":371},"thead",{},[372],{"type":44,"tag":373,"props":374,"children":375},"tr",{},[376,382,387],{"type":44,"tag":377,"props":378,"children":379},"th",{},[380],{"type":49,"value":381},"Question sounds like",{"type":44,"tag":377,"props":383,"children":384},{},[385],{"type":49,"value":386},"Why it might not be simple",{"type":44,"tag":377,"props":388,"children":389},{},[390],{"type":49,"value":391},"Catch it by asking",{"type":44,"tag":393,"props":394,"children":395},"tbody",{},[396,422,440,458,476,494,512,530,561,584,602,620],{"type":44,"tag":373,"props":397,"children":398},{},[399,412,417],{"type":44,"tag":400,"props":401,"children":402},"td",{},[403,405,410],{"type":49,"value":404},"\"Can we add ",{"type":44,"tag":289,"props":406,"children":407},{},[408],{"type":49,"value":409},"vendor",{"type":49,"value":411}," to the integration?\"",{"type":44,"tag":400,"props":413,"children":414},{},[415],{"type":49,"value":416},"Vendor touches a new data category — flag as potentially implicating privacy and vendor-risk regimes and route for research",{"type":44,"tag":400,"props":418,"children":419},{},[420],{"type":49,"value":421},"\"What data flows to them?\"",{"type":44,"tag":373,"props":423,"children":424},{},[425,430,435],{"type":44,"tag":400,"props":426,"children":427},{},[428],{"type":49,"value":429},"\"Can we A\u002FB test the pricing page?\"",{"type":44,"tag":400,"props":431,"children":432},{},[433],{"type":49,"value":434},"Differential pricing by segment can implicate consumer-protection and anti-discrimination regimes — flag and route for research",{"type":44,"tag":400,"props":436,"children":437},{},[438],{"type":49,"value":439},"\"Are both arms seeing the same price for the same thing? How are users assigned to arms?\"",{"type":44,"tag":373,"props":441,"children":442},{},[443,448,453],{"type":44,"tag":400,"props":444,"children":445},{},[446],{"type":49,"value":447},"\"Can we auto-enroll users in the new feature?\"",{"type":44,"tag":400,"props":449,"children":450},{},[451],{"type":49,"value":452},"Default-on behavior for users who previously opted out can implicate consent and consumer-protection rules — flag and route for research",{"type":44,"tag":400,"props":454,"children":455},{},[456],{"type":49,"value":457},"\"Does this respect existing preferences?\"",{"type":44,"tag":373,"props":459,"children":460},{},[461,466,471],{"type":44,"tag":400,"props":462,"children":463},{},[464],{"type":49,"value":465},"\"Can we use customer logos on the site?\"",{"type":44,"tag":400,"props":467,"children":468},{},[469],{"type":49,"value":470},"Logo use is a separate permission from the contract relationship — flag as potentially implicating publicity \u002F endorsement rules and the customer's own contract terms",{"type":44,"tag":400,"props":472,"children":473},{},[474],{"type":49,"value":475},"\"What does the contract say about publicity? Do we have written permission?\"",{"type":44,"tag":373,"props":477,"children":478},{},[479,484,489],{"type":44,"tag":400,"props":480,"children":481},{},[482],{"type":49,"value":483},"\"Can we train on this data?\"",{"type":44,"tag":400,"props":485,"children":486},{},[487],{"type":49,"value":488},"Usage rights for the original collection purpose may not extend to training — flag and research the notice\u002Fconsent the users were given at collection",{"type":44,"tag":400,"props":490,"children":491},{},[492],{"type":49,"value":493},"\"What did we tell users when we collected it? What jurisdictions are the users in?\"",{"type":44,"tag":373,"props":495,"children":496},{},[497,502,507],{"type":44,"tag":400,"props":498,"children":499},{},[500],{"type":49,"value":501},"\"It's just an internal tool\"",{"type":44,"tag":400,"props":503,"children":504},{},[505],{"type":49,"value":506},"Internal tools still process personal data — flag as potentially implicating privacy regimes and route for research",{"type":44,"tag":400,"props":508,"children":509},{},[510],{"type":49,"value":511},"\"Whose data does it touch? Employees, customers, third parties?\"",{"type":44,"tag":373,"props":513,"children":514},{},[515,520,525],{"type":44,"tag":400,"props":516,"children":517},{},[518],{"type":49,"value":519},"\"We already do something similar\"",{"type":44,"tag":400,"props":521,"children":522},{},[523],{"type":49,"value":524},"\"Similar\" is doing a lot of work — the delta is where the issue usually is",{"type":44,"tag":400,"props":526,"children":527},{},[528],{"type":49,"value":529},"\"Similar how? What's actually different?\"",{"type":44,"tag":373,"props":531,"children":532},{},[533,545,556],{"type":44,"tag":400,"props":534,"children":535},{},[536,538,543],{"type":49,"value":537},"\"Can we use ",{"type":44,"tag":289,"props":539,"children":540},{},[541],{"type":49,"value":542},"AI vendor \u002F LLM",{"type":49,"value":544}," for this?\"",{"type":44,"tag":400,"props":546,"children":547},{},[548,550],{"type":49,"value":549},"Vendor AI terms may permit training on inputs; use case may need an AIA — flag and route to ",{"type":44,"tag":62,"props":551,"children":553},{"className":552},[],[554],{"type":49,"value":555},"\u002Fai-governance-legal:use-case-triage",{"type":44,"tag":400,"props":557,"children":558},{},[559],{"type":49,"value":560},"\"Is there an AI addendum? What data goes into the model?\"",{"type":44,"tag":373,"props":562,"children":563},{},[564,569,579],{"type":44,"tag":400,"props":565,"children":566},{},[567],{"type":49,"value":568},"\"Can we add AI to this feature?\"",{"type":44,"tag":400,"props":570,"children":571},{},[572,574],{"type":49,"value":573},"May be a new use case not in the registry; may trigger AIA requirement — flag and route to ",{"type":44,"tag":62,"props":575,"children":577},{"className":576},[],[578],{"type":49,"value":555},{"type":44,"tag":400,"props":580,"children":581},{},[582],{"type":49,"value":583},"\"What does the AI do — assistive or automated? Who does it act on?\"",{"type":44,"tag":373,"props":585,"children":586},{},[587,592,597],{"type":44,"tag":400,"props":588,"children":589},{},[590],{"type":49,"value":591},"\"The model just decides automatically\"",{"type":44,"tag":400,"props":593,"children":594},{},[595],{"type":49,"value":596},"Automated decision-making without human review is regulated in some jurisdictions — flag and research the applicable rules for the affected users' jurisdictions",{"type":44,"tag":400,"props":598,"children":599},{},[600],{"type":49,"value":601},"\"Who's affected? Is there a human in the loop? Where are the affected users?\"",{"type":44,"tag":373,"props":603,"children":604},{},[605,610,615],{"type":44,"tag":400,"props":606,"children":607},{},[608],{"type":49,"value":609},"\"It's AI-generated content\"",{"type":44,"tag":400,"props":611,"children":612},{},[613],{"type":49,"value":614},"Output IP and disclosure duties vary by jurisdiction and vendor terms — flag and route for research",{"type":44,"tag":400,"props":616,"children":617},{},[618],{"type":49,"value":619},"\"What's the content type? Does the vendor's ToS address output ownership? Who is the audience?\"",{"type":44,"tag":373,"props":621,"children":622},{},[623,628,639],{"type":44,"tag":400,"props":624,"children":625},{},[626],{"type":49,"value":627},"\"We're just fine-tuning on our data\"",{"type":44,"tag":400,"props":629,"children":630},{},[631,633],{"type":49,"value":632},"Training data rights, output IP, and vendor obligations all change — flag and route to ",{"type":44,"tag":62,"props":634,"children":636},{"className":635},[],[637],{"type":49,"value":638},"\u002Fai-governance-legal:vendor-ai-review",{"type":44,"tag":400,"props":640,"children":641},{},[642],{"type":49,"value":643},"\"What's in the training data? Is any of it customer or employee data?\"",{"type":44,"tag":114,"props":645,"children":646},{},[647],{"type":49,"value":648},"If a trap might be present, ask the one question before answering. One question, not a checklist. When the answer suggests a real issue, flag for research and route — don't pattern-match to a legal conclusion from the question alone.",{"type":44,"tag":107,"props":650,"children":652},{"id":651},"output-format",[653],{"type":49,"value":654},"Output format",{"type":44,"tag":114,"props":656,"children":657},{},[658],{"type":44,"tag":118,"props":659,"children":660},{},[661],{"type":49,"value":662},"For Slack (the common case):",{"type":44,"tag":114,"props":664,"children":665},{},[666,668,673,675,681,683,689],{"type":49,"value":667},"Slack triage replies are internal legal advice. If the reply is being pasted into a ticket, document, or channel that's broadly shared with non-legal, prepend the work-product header from ",{"type":44,"tag":62,"props":669,"children":671},{"className":670},[],[672],{"type":49,"value":67},{"type":49,"value":674}," ",{"type":44,"tag":62,"props":676,"children":678},{"className":677},[],[679],{"type":49,"value":680},"## Outputs",{"type":49,"value":682}," (it differs by user role — see ",{"type":44,"tag":62,"props":684,"children":686},{"className":685},[],[687],{"type":49,"value":688},"## Who's using this",{"type":49,"value":690},"):",{"type":44,"tag":91,"props":692,"children":695},{"className":693,"code":694,"language":49},[94],"[WORK-PRODUCT HEADER — per plugin config ## Outputs]\n",[696],{"type":44,"tag":62,"props":697,"children":698},{"__ignoreMap":99},[699],{"type":49,"value":694},{"type":44,"tag":114,"props":701,"children":702},{},[703],{"type":49,"value":704},"For an in-the-flow Slack DM reply to the PM, the short form is:",{"type":44,"tag":91,"props":706,"children":709},{"className":707,"code":708,"language":49},[94],"[✅ Fine | ⚠️ Needs a look | 🛑 Hold]\n\n[One sentence: the call and why.]\n\n[If ⚠️: what the look involves, how long]\n[If 🛑: who to talk to, when]\n",[710],{"type":44,"tag":62,"props":711,"children":712},{"__ignoreMap":99},[713],{"type":49,"value":708},{"type":44,"tag":114,"props":715,"children":716},{},[717],{"type":44,"tag":118,"props":718,"children":719},{},[720],{"type":49,"value":721},"Examples:",{"type":44,"tag":91,"props":723,"children":726},{"className":724,"code":725,"language":49},[94],"✅ Fine — adding an analytics event is an FYI here as long as it's covered by\nthe existing privacy policy categories. This one is.\n",[727],{"type":44,"tag":62,"props":728,"children":729},{"__ignoreMap":99},[730],{"type":49,"value":725},{"type":44,"tag":91,"props":732,"children":735},{"className":733,"code":734,"language":49},[94],"⚠️ Needs a PIA — new data collection for [category]. Usually takes a day.\nWant me to kick it off?\n",[736],{"type":44,"tag":62,"props":737,"children":738},{"__ignoreMap":99},[739],{"type":49,"value":734},{"type":44,"tag":91,"props":741,"children":744},{"className":742,"code":743,"language":49},[94],"🛑 Hold — \"train on customer data\" triggers a bunch of things. What did the\ncustomer agreement say about data use? Let's pull it before anyone promises\nthis to the customer.\n",[745],{"type":44,"tag":62,"props":746,"children":747},{"__ignoreMap":99},[748],{"type":49,"value":743},{"type":44,"tag":91,"props":750,"children":753},{"className":751,"code":752,"language":49},[94],"⚠️ Needs an AI governance triage — adding an LLM to this workflow means we need\nto check the use case against the registry and confirm an AIA is done before it\nships. Takes a day. Want me to run `\u002Fai-governance-legal:use-case-triage` now?\n",[754],{"type":44,"tag":62,"props":755,"children":756},{"__ignoreMap":99},[757],{"type":49,"value":752},{"type":44,"tag":107,"props":759,"children":761},{"id":760},"when-to-not-use-this-skill",[762],{"type":49,"value":763},"When to NOT use this skill",{"type":44,"tag":765,"props":766,"children":767},"ul",{},[768,773,778],{"type":44,"tag":56,"props":769,"children":770},{},[771],{"type":49,"value":772},"The question is actually complex (multiple issues, novel area) → route to launch-review or feature-risk-assessment",{"type":44,"tag":56,"props":774,"children":775},{},[776],{"type":49,"value":777},"The question is \"can you review this PRD\" → that's launch-review, not triage",{"type":44,"tag":56,"props":779,"children":780},{},[781],{"type":49,"value":782},"You're not sure → say \"I'm not sure, let me look properly\" — a wrong fast answer is worse than a slow right one",{"type":44,"tag":107,"props":784,"children":786},{"id":785},"tone",[787],{"type":49,"value":788},"Tone",{"type":44,"tag":114,"props":790,"children":791},{},[792],{"type":49,"value":793},"Fast, direct, helpful. The PM is not asking for a lecture. If it's fine, say \"fine\" — don't list the seven things you checked. If it's not fine, say what's not fine and what to do about it.",{"type":44,"tag":114,"props":795,"children":796},{},[797],{"type":49,"value":798},"You are the lawyer people want to ask, not the one they route around.",{"type":44,"tag":107,"props":800,"children":802},{"id":801},"close-with-the-next-steps-decision-tree",[803],{"type":49,"value":804},"Close with the next-steps decision tree",{"type":44,"tag":114,"props":806,"children":807},{},[808,810,815],{"type":49,"value":809},"End with the next-steps decision tree per CLAUDE.md ",{"type":44,"tag":62,"props":811,"children":813},{"className":812},[],[814],{"type":49,"value":680},{"type":49,"value":816},". 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.",{"items":818,"total":914},[819,833,850,865,877,888,899],{"slug":820,"name":820,"fn":821,"description":822,"org":823,"tags":824,"stars":26,"repoUrl":27,"updatedAt":832},"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},[825,828,831],{"name":826,"slug":827,"type":16},"Compliance","compliance",{"name":829,"slug":830,"type":16},"Governance","governance",{"name":18,"slug":19,"type":16},"2026-05-14T06:02:19.677579",{"slug":834,"name":834,"fn":835,"description":836,"org":837,"tags":838,"stars":26,"repoUrl":27,"updatedAt":849},"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},[839,842,845,846],{"name":840,"slug":841,"type":16},"Automation","automation",{"name":843,"slug":844,"type":16},"Contracts","contracts",{"name":18,"slug":19,"type":16},{"name":847,"slug":848,"type":16},"QA","qa","2026-05-14T06:01:31.00555",{"slug":851,"name":851,"fn":852,"description":853,"org":854,"tags":855,"stars":26,"repoUrl":27,"updatedAt":864},"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},[856,857,860,863],{"name":18,"slug":19,"type":16},{"name":858,"slug":859,"type":16},"Policy","policy",{"name":861,"slug":862,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":24,"slug":25,"type":16},"2026-05-13T06:03:19.61029",{"slug":866,"name":866,"fn":867,"description":868,"org":869,"tags":870,"stars":26,"repoUrl":27,"updatedAt":876},"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},[871,872,875],{"name":843,"slug":844,"type":16},{"name":873,"slug":874,"type":16},"Documents","documents",{"name":18,"slug":19,"type":16},"2026-05-13T06:03:34.070339",{"slug":878,"name":878,"fn":879,"description":880,"org":881,"tags":882,"stars":26,"repoUrl":27,"updatedAt":887},"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},[883,884],{"name":840,"slug":841,"type":16},{"name":885,"slug":886,"type":16},"Plugin Development","plugin-development","2026-05-13T06:02:55.642269",{"slug":889,"name":889,"fn":890,"description":891,"org":892,"tags":893,"stars":26,"repoUrl":27,"updatedAt":898},"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},[894,897],{"name":895,"slug":896,"type":16},"Education","education",{"name":18,"slug":19,"type":16},"2026-07-24T05:41:43.01243",{"slug":900,"name":900,"fn":901,"description":902,"org":903,"tags":904,"stars":26,"repoUrl":27,"updatedAt":913},"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},[905,908,909,910],{"name":906,"slug":907,"type":16},"Documentation","documentation",{"name":829,"slug":830,"type":16},{"name":18,"slug":19,"type":16},{"name":911,"slug":912,"type":16},"Meetings","meetings","2026-05-14T06:01:29.792942",118,{"items":916,"total":1097},[917,938,952,964,983,994,1013,1033,1045,1060,1068,1081],{"slug":918,"name":918,"fn":919,"description":920,"org":921,"tags":922,"stars":935,"repoUrl":936,"updatedAt":937},"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},[923,926,929,932],{"name":924,"slug":925,"type":16},"Creative","creative",{"name":927,"slug":928,"type":16},"Design","design",{"name":930,"slug":931,"type":16},"Generative Art","generative-art",{"name":933,"slug":934,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":939,"name":939,"fn":940,"description":941,"org":942,"tags":943,"stars":935,"repoUrl":936,"updatedAt":951},"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},[944,947,948],{"name":945,"slug":946,"type":16},"Branding","branding",{"name":927,"slug":928,"type":16},{"name":949,"slug":950,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":953,"name":953,"fn":954,"description":955,"org":956,"tags":957,"stars":935,"repoUrl":936,"updatedAt":963},"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},[958,959,960],{"name":924,"slug":925,"type":16},{"name":927,"slug":928,"type":16},{"name":961,"slug":962,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":965,"name":965,"fn":966,"description":967,"org":968,"tags":969,"stars":935,"repoUrl":936,"updatedAt":982},"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},[970,973,974,977,979],{"name":971,"slug":972,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":975,"slug":976,"type":16},"Anthropic SDK","anthropic-sdk",{"name":978,"slug":965,"type":16},"Claude API",{"name":980,"slug":981,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":984,"name":984,"fn":985,"description":986,"org":987,"tags":988,"stars":935,"repoUrl":936,"updatedAt":993},"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},[989,990],{"name":906,"slug":907,"type":16},{"name":991,"slug":992,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":995,"name":995,"fn":996,"description":997,"org":998,"tags":999,"stars":935,"repoUrl":936,"updatedAt":1012},"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},[1000,1001,1003,1006,1009],{"name":873,"slug":874,"type":16},{"name":1002,"slug":995,"type":16},"DOCX",{"name":1004,"slug":1005,"type":16},"Office","office",{"name":1007,"slug":1008,"type":16},"Templates","templates",{"name":1010,"slug":1011,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":1014,"name":1014,"fn":1015,"description":1016,"org":1017,"tags":1018,"stars":935,"repoUrl":936,"updatedAt":1032},"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},[1019,1020,1023,1026,1029],{"name":927,"slug":928,"type":16},{"name":1021,"slug":1022,"type":16},"Frontend","frontend",{"name":1024,"slug":1025,"type":16},"React","react",{"name":1027,"slug":1028,"type":16},"Tailwind CSS","tailwind-css",{"name":1030,"slug":1031,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":1034,"name":1034,"fn":1035,"description":1036,"org":1037,"tags":1038,"stars":935,"repoUrl":936,"updatedAt":1044},"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},[1039,1040,1041],{"name":21,"slug":22,"type":16},{"name":1007,"slug":1008,"type":16},{"name":1042,"slug":1043,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":1046,"name":1046,"fn":1047,"description":1048,"org":1049,"tags":1050,"stars":935,"repoUrl":936,"updatedAt":1059},"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},[1051,1052,1055,1056],{"name":971,"slug":972,"type":16},{"name":1053,"slug":1054,"type":16},"API Development","api-development",{"name":980,"slug":981,"type":16},{"name":1057,"slug":1058,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":962,"name":962,"fn":1061,"description":1062,"org":1063,"tags":1064,"stars":935,"repoUrl":936,"updatedAt":1067},"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},[1065,1066],{"name":873,"slug":874,"type":16},{"name":961,"slug":962,"type":16},"2026-04-06T17:56:02.483316",{"slug":1069,"name":1069,"fn":1070,"description":1071,"org":1072,"tags":1073,"stars":935,"repoUrl":936,"updatedAt":1080},"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},[1074,1077],{"name":1075,"slug":1076,"type":16},"PowerPoint","powerpoint",{"name":1078,"slug":1079,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":1082,"name":1082,"fn":1083,"description":1084,"org":1085,"tags":1086,"stars":935,"repoUrl":936,"updatedAt":1096},"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},[1087,1088,1089,1092,1095],{"name":971,"slug":972,"type":16},{"name":906,"slug":907,"type":16},{"name":1090,"slug":1091,"type":16},"Evals","evals",{"name":1093,"slug":1094,"type":16},"Performance","performance",{"name":991,"slug":992,"type":16},"2026-04-19T06:45:40.804",490]