[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-performance-insights":3,"mdc-k5hawz-key":37,"related-repo-anthropic-performance-insights":363,"related-org-anthropic-performance-insights":479},{"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},"performance-insights","analyze business performance and metrics","Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer. Not needed when the snapshot's headline figures and their change on the prior period answer the question, how a period went included.",{"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},"Performance","performance","tag",{"name":18,"slug":19,"type":16},"Reporting","reporting",{"name":21,"slug":22,"type":16},"Sales","sales",{"name":24,"slug":25,"type":16},"Analytics","analytics",1735,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcommerce-agents","2026-09-04T08:00:56.459351",null,277,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcommerce-agents\u002Ftree\u002FHEAD\u002Fmerchant-agent\u002Fskills\u002Fperformance-insights","---\nname: performance-insights\ndescription: Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer. Not needed when the snapshot's headline figures and their change on the prior period answer the question, how a period went included.\n---\n\n# Performance insights\n\nBelow, \"segment\" means whatever unit this operation reports on: a category, a listing, a property, a plan, or an event.\n\nGive the operator a takeaway they can act on, the figure behind it, and the comparison it rests on, and say which reads it came from.\n\n## Where the figures come from\n\n- Start with `get_business_snapshot` for the period asked about: the headline figures, the prior period (`compare_to` and the change percentages), and the alert counts that every later figure is read against. Then use `query_metrics` for one metric over time, narrowed to a segment when the question is about part of the operation.\n- Take margin and stock from `get_pricing_context` and `get_listing`, and campaign spend and revenue from `get_campaign_performance`; the snapshot does not carry them.\n- Report a series the backend does not hold (an error, an empty series, a different metric name than you asked for) as unavailable, and say which question that leaves open.\n- Show a figure you work out from returned data (a run rate, a shortfall, a sell-out date at the current pace) with its inputs beside it.\n- The latest date in a returned series is the latest date the data covers. A period that runs past it is partial; say so before comparing it with a complete one.\n\n## The comparison\n\n- Choose the comparison period for the question and name it: the prior period for how the week went, the same period last year for a swing that could be seasonal, before and after a change when the question is about that change.\n- Compare a partial period with the matching part of the baseline, or say the comparison is partial against complete; give both end dates.\n- When the question is pace against a comparable (this run against the last run of the same thing, or against its peers at the same point in the cycle), fetch the comparable as its own `query_metrics` series, name it, and say why it is comparable.\n- When the two series came back under different names, put both in `present_metrics` as returned. When they differ only by period, they share a name: query the current period last, present it, and give the comparable's figures in the text with their period. Either way, state the gap at the same point in the cycle instead of the two totals.\n- When the data holds no comparable (a first run, a first season), say so, give the pace on its own terms, and offer the nearest substitute the data holds, labeled as one. Do not build a comparable from memory of similar cases.\n\n## Explaining a movement\n\n- Say first what moved, by how much, and against which baseline; then investigate.\n- Confirm the movement before explaining it. A partial period, a gap in the series, or an unusual baseline accounts for many reported drops; when one of those is the explanation, say so and stop.\n- Locate it: query by segment and name the segment that accounts for most of the movement, with its share.\n- Separate mix from level. An average falls when the unit price fell and also when cheaper units made up more of the total; say which one the returned series show, or say that you cannot tell until the segments are queried.\n- Check candidate causes against tool data for the same dates: campaign windows from `get_campaign_performance`, stockouts or sell-outs from `get_inventory_alerts` or the listing, price moves from `get_pending_changes` or a change applied this conversation.\n- Call something the cause only when its timing lines up and the movement sits in the segment it would affect; otherwise report a correlation and name the read that would settle it.\n- Grade your confidence in words that match the evidence: a finding when the data shows it, a lead when it partly does, and \"not visible in the data\" when nothing does.\n\n## Goals and patterns the operator has stated\n\n- A target stated in this conversation or held in `recall_memories` turns a summary into a pace report: the figure so far, the share of the period elapsed, and what the rest of the period must average, computed from returned figures. Do not supply a target the operator has not stated.\n- Recall the seasonal patterns the operator has stated before calling a swing unusual, and say which pattern it does or does not fit. Save a goal or pattern stated during this flow with `save_memory`, so later summaries can pace against it.\n\n## Presenting the answer\n\n- End with `present_metrics`. Each pick names a measure a tool returned this conversation, under the tool's name for it and with its segment (`sales`, `sales:kids-room`, `conversion_rate`). A single date's value, a difference between two series, and a projection are not picks; they belong in the text.\n- When a `present_metrics` call is refused as ungrounded, present the retrieved series again with the picks corrected to names the tools returned.\n- Before the component, give the takeaway with its baseline (\"sales are down 12% on the prior week, and one category is 9 of those points\"), the comparison used, and the one caveat that changes how to read the figures.\n- When the movement traces to something operational, make the last chip the hand-off to the flow that acts on it.\n",{"data":38,"body":39},{"name":4,"description":6},{"type":40,"children":41},"root",[42,50,56,61,68,147,153,196,202,263,269,298,304],{"type":43,"tag":44,"props":45,"children":46},"element","h1",{"id":4},[47],{"type":48,"value":49},"text","Performance insights",{"type":43,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Below, \"segment\" means whatever unit this operation reports on: a category, a listing, a property, a plan, or an event.",{"type":43,"tag":51,"props":57,"children":58},{},[59],{"type":48,"value":60},"Give the operator a takeaway they can act on, the figure behind it, and the comparison it rests on, and say which reads it came from.",{"type":43,"tag":62,"props":63,"children":65},"h2",{"id":64},"where-the-figures-come-from",[66],{"type":48,"value":67},"Where the figures come from",{"type":43,"tag":69,"props":70,"children":71},"ul",{},[72,103,132,137,142],{"type":43,"tag":73,"props":74,"children":75},"li",{},[76,78,85,87,93,95,101],{"type":48,"value":77},"Start with ",{"type":43,"tag":79,"props":80,"children":82},"code",{"className":81},[],[83],{"type":48,"value":84},"get_business_snapshot",{"type":48,"value":86}," for the period asked about: the headline figures, the prior period (",{"type":43,"tag":79,"props":88,"children":90},{"className":89},[],[91],{"type":48,"value":92},"compare_to",{"type":48,"value":94}," and the change percentages), and the alert counts that every later figure is read against. Then use ",{"type":43,"tag":79,"props":96,"children":98},{"className":97},[],[99],{"type":48,"value":100},"query_metrics",{"type":48,"value":102}," for one metric over time, narrowed to a segment when the question is about part of the operation.",{"type":43,"tag":73,"props":104,"children":105},{},[106,108,114,116,122,124,130],{"type":48,"value":107},"Take margin and stock from ",{"type":43,"tag":79,"props":109,"children":111},{"className":110},[],[112],{"type":48,"value":113},"get_pricing_context",{"type":48,"value":115}," and ",{"type":43,"tag":79,"props":117,"children":119},{"className":118},[],[120],{"type":48,"value":121},"get_listing",{"type":48,"value":123},", and campaign spend and revenue from ",{"type":43,"tag":79,"props":125,"children":127},{"className":126},[],[128],{"type":48,"value":129},"get_campaign_performance",{"type":48,"value":131},"; the snapshot does not carry them.",{"type":43,"tag":73,"props":133,"children":134},{},[135],{"type":48,"value":136},"Report a series the backend does not hold (an error, an empty series, a different metric name than you asked for) as unavailable, and say which question that leaves open.",{"type":43,"tag":73,"props":138,"children":139},{},[140],{"type":48,"value":141},"Show a figure you work out from returned data (a run rate, a shortfall, a sell-out date at the current pace) with its inputs beside it.",{"type":43,"tag":73,"props":143,"children":144},{},[145],{"type":48,"value":146},"The latest date in a returned series is the latest date the data covers. A period that runs past it is partial; say so before comparing it with a complete one.",{"type":43,"tag":62,"props":148,"children":150},{"id":149},"the-comparison",[151],{"type":48,"value":152},"The comparison",{"type":43,"tag":69,"props":154,"children":155},{},[156,161,166,178,191],{"type":43,"tag":73,"props":157,"children":158},{},[159],{"type":48,"value":160},"Choose the comparison period for the question and name it: the prior period for how the week went, the same period last year for a swing that could be seasonal, before and after a change when the question is about that change.",{"type":43,"tag":73,"props":162,"children":163},{},[164],{"type":48,"value":165},"Compare a partial period with the matching part of the baseline, or say the comparison is partial against complete; give both end dates.",{"type":43,"tag":73,"props":167,"children":168},{},[169,171,176],{"type":48,"value":170},"When the question is pace against a comparable (this run against the last run of the same thing, or against its peers at the same point in the cycle), fetch the comparable as its own ",{"type":43,"tag":79,"props":172,"children":174},{"className":173},[],[175],{"type":48,"value":100},{"type":48,"value":177}," series, name it, and say why it is comparable.",{"type":43,"tag":73,"props":179,"children":180},{},[181,183,189],{"type":48,"value":182},"When the two series came back under different names, put both in ",{"type":43,"tag":79,"props":184,"children":186},{"className":185},[],[187],{"type":48,"value":188},"present_metrics",{"type":48,"value":190}," as returned. When they differ only by period, they share a name: query the current period last, present it, and give the comparable's figures in the text with their period. Either way, state the gap at the same point in the cycle instead of the two totals.",{"type":43,"tag":73,"props":192,"children":193},{},[194],{"type":48,"value":195},"When the data holds no comparable (a first run, a first season), say so, give the pace on its own terms, and offer the nearest substitute the data holds, labeled as one. Do not build a comparable from memory of similar cases.",{"type":43,"tag":62,"props":197,"children":199},{"id":198},"explaining-a-movement",[200],{"type":48,"value":201},"Explaining a movement",{"type":43,"tag":69,"props":203,"children":204},{},[205,210,215,220,225,253,258],{"type":43,"tag":73,"props":206,"children":207},{},[208],{"type":48,"value":209},"Say first what moved, by how much, and against which baseline; then investigate.",{"type":43,"tag":73,"props":211,"children":212},{},[213],{"type":48,"value":214},"Confirm the movement before explaining it. A partial period, a gap in the series, or an unusual baseline accounts for many reported drops; when one of those is the explanation, say so and stop.",{"type":43,"tag":73,"props":216,"children":217},{},[218],{"type":48,"value":219},"Locate it: query by segment and name the segment that accounts for most of the movement, with its share.",{"type":43,"tag":73,"props":221,"children":222},{},[223],{"type":48,"value":224},"Separate mix from level. An average falls when the unit price fell and also when cheaper units made up more of the total; say which one the returned series show, or say that you cannot tell until the segments are queried.",{"type":43,"tag":73,"props":226,"children":227},{},[228,230,235,237,243,245,251],{"type":48,"value":229},"Check candidate causes against tool data for the same dates: campaign windows from ",{"type":43,"tag":79,"props":231,"children":233},{"className":232},[],[234],{"type":48,"value":129},{"type":48,"value":236},", stockouts or sell-outs from ",{"type":43,"tag":79,"props":238,"children":240},{"className":239},[],[241],{"type":48,"value":242},"get_inventory_alerts",{"type":48,"value":244}," or the listing, price moves from ",{"type":43,"tag":79,"props":246,"children":248},{"className":247},[],[249],{"type":48,"value":250},"get_pending_changes",{"type":48,"value":252}," or a change applied this conversation.",{"type":43,"tag":73,"props":254,"children":255},{},[256],{"type":48,"value":257},"Call something the cause only when its timing lines up and the movement sits in the segment it would affect; otherwise report a correlation and name the read that would settle it.",{"type":43,"tag":73,"props":259,"children":260},{},[261],{"type":48,"value":262},"Grade your confidence in words that match the evidence: a finding when the data shows it, a lead when it partly does, and \"not visible in the data\" when nothing does.",{"type":43,"tag":62,"props":264,"children":266},{"id":265},"goals-and-patterns-the-operator-has-stated",[267],{"type":48,"value":268},"Goals and patterns the operator has stated",{"type":43,"tag":69,"props":270,"children":271},{},[272,285],{"type":43,"tag":73,"props":273,"children":274},{},[275,277,283],{"type":48,"value":276},"A target stated in this conversation or held in ",{"type":43,"tag":79,"props":278,"children":280},{"className":279},[],[281],{"type":48,"value":282},"recall_memories",{"type":48,"value":284}," turns a summary into a pace report: the figure so far, the share of the period elapsed, and what the rest of the period must average, computed from returned figures. Do not supply a target the operator has not stated.",{"type":43,"tag":73,"props":286,"children":287},{},[288,290,296],{"type":48,"value":289},"Recall the seasonal patterns the operator has stated before calling a swing unusual, and say which pattern it does or does not fit. Save a goal or pattern stated during this flow with ",{"type":43,"tag":79,"props":291,"children":293},{"className":292},[],[294],{"type":48,"value":295},"save_memory",{"type":48,"value":297},", so later summaries can pace against it.",{"type":43,"tag":62,"props":299,"children":301},{"id":300},"presenting-the-answer",[302],{"type":48,"value":303},"Presenting the answer",{"type":43,"tag":69,"props":305,"children":306},{},[307,341,353,358],{"type":43,"tag":73,"props":308,"children":309},{},[310,312,317,319,324,326,332,333,339],{"type":48,"value":311},"End with ",{"type":43,"tag":79,"props":313,"children":315},{"className":314},[],[316],{"type":48,"value":188},{"type":48,"value":318},". Each pick names a measure a tool returned this conversation, under the tool's name for it and with its segment (",{"type":43,"tag":79,"props":320,"children":322},{"className":321},[],[323],{"type":48,"value":22},{"type":48,"value":325},", ",{"type":43,"tag":79,"props":327,"children":329},{"className":328},[],[330],{"type":48,"value":331},"sales:kids-room",{"type":48,"value":325},{"type":43,"tag":79,"props":334,"children":336},{"className":335},[],[337],{"type":48,"value":338},"conversion_rate",{"type":48,"value":340},"). A single date's value, a difference between two series, and a projection are not picks; they belong in the text.",{"type":43,"tag":73,"props":342,"children":343},{},[344,346,351],{"type":48,"value":345},"When a ",{"type":43,"tag":79,"props":347,"children":349},{"className":348},[],[350],{"type":48,"value":188},{"type":48,"value":352}," call is refused as ungrounded, present the retrieved series again with the picks corrected to names the tools returned.",{"type":43,"tag":73,"props":354,"children":355},{},[356],{"type":48,"value":357},"Before the component, give the takeaway with its baseline (\"sales are down 12% on the prior week, and one category is 9 of those points\"), the comparison used, and the one caveat that changes how to read the figures.",{"type":43,"tag":73,"props":359,"children":360},{},[361],{"type":48,"value":362},"When the movement traces to something operational, make the last chip the hand-off to the flow that acts on it.",{"items":364,"total":478},[365,384,401,416,431,444,461],{"slug":366,"name":366,"fn":367,"description":368,"org":369,"tags":370,"stars":26,"repoUrl":27,"updatedAt":383},"catalog-listings","create and improve e-commerce listing content","Creating and improving listing content, covering titles, descriptions, attribute completeness, categorization fixes, image callouts written as text, edits written from material the operator supplies, and content-quality audits and bulk fixes across many listings. Not needed for questions about how a listing is performing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[371,374,377,380],{"name":372,"slug":373,"type":16},"Content Creation","content-creation",{"name":375,"slug":376,"type":16},"Content Strategy","content-strategy",{"name":378,"slug":379,"type":16},"E-commerce","e-commerce",{"name":381,"slug":382,"type":16},"Marketing","marketing","2026-09-04T08:00:35.843558",{"slug":385,"name":385,"fn":386,"description":387,"org":388,"tags":389,"stars":26,"repoUrl":27,"updatedAt":400},"commerce-architecture","design and review commerce agent architecture","How the reference commerce agents of either role are structured, covering the loop, where each rule lives, skills, the backend interface, delegates, and model fields. Load when designing or reviewing the structure of a shopping or merchant agent.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[390,393,396,397],{"name":391,"slug":392,"type":16},"Agents","agents",{"name":394,"slug":395,"type":16},"Architecture","architecture",{"name":378,"slug":379,"type":16},{"name":398,"slug":399,"type":16},"Engineering","engineering","2026-09-04T08:00:39.152322",{"slug":402,"name":402,"fn":403,"description":404,"org":405,"tags":406,"stars":26,"repoUrl":27,"updatedAt":415},"commerce-evals","run behavioral evals for commerce agents","Authoring and running behavioral evals for a shopping or merchant agent, covering the case shape, authoring rules, code graders and judges, the run pattern, and poisoned fixtures. Load when writing eval cases or rubrics or deciding how a suite runs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[407,408,409,412],{"name":391,"slug":392,"type":16},{"name":378,"slug":379,"type":16},{"name":410,"slug":411,"type":16},"Evals","evals",{"name":413,"slug":414,"type":16},"Testing","testing","2026-09-04T08:00:36.204114",{"slug":417,"name":417,"fn":418,"description":419,"org":420,"tags":421,"stars":26,"repoUrl":27,"updatedAt":430},"commerce-merchant-operations","manage merchant operations and store rules","The reference merchant agent, covering its flows, staged changes and host approval, metrics grounding, the analysis delegate, store memory, components, and marketplace rules. Load when building or reviewing an agent for the operators of a store, property, subscriber base, or venue.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[422,423,424,427],{"name":391,"slug":392,"type":16},{"name":378,"slug":379,"type":16},{"name":425,"slug":426,"type":16},"Management","management",{"name":428,"slug":429,"type":16},"Operations","operations","2026-09-04T08:00:35.464555",{"slug":432,"name":432,"fn":433,"description":434,"org":435,"tags":436,"stars":26,"repoUrl":27,"updatedAt":443},"commerce-prompt-caching","configure commerce agent prompt caching","The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are prompt bytes, and verification. Load when writing or reviewing a commerce agent's prompt assembly, when cache reads are zero, or when a turn's latency or cost is the question.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[437,438,439,440],{"name":391,"slug":392,"type":16},{"name":378,"slug":379,"type":16},{"name":14,"slug":15,"type":16},{"name":441,"slug":442,"type":16},"Prompt Engineering","prompt-engineering","2026-09-04T08:00:39.50364",{"slug":445,"name":445,"fn":446,"description":447,"org":448,"tags":449,"stars":26,"repoUrl":27,"updatedAt":460},"commerce-trust-safety","enforce trust and safety rules","The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules. Load when handling untrusted tool results, guarding a write tool, or scoping what an agent remembers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[450,451,454,457],{"name":391,"slug":392,"type":16},{"name":452,"slug":453,"type":16},"Compliance","compliance",{"name":455,"slug":456,"type":16},"Memory","memory",{"name":458,"slug":459,"type":16},"Security","security","2026-09-04T08:00:42.609563",{"slug":462,"name":462,"fn":463,"description":464,"org":465,"tags":466,"stars":26,"repoUrl":27,"updatedAt":477},"commerce-ui-tools","implement commerce agent UI components","The reference presentation-tool contract, covering server-side enrichment, suggestion chips, the event stream, progressive rendering, both roles' built-in components, and adding a vertical component. Load when building or reviewing how a commerce agent's output reaches a frontend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[467,470,471,474],{"name":468,"slug":469,"type":16},"Design","design",{"name":378,"slug":379,"type":16},{"name":472,"slug":473,"type":16},"Frontend","frontend",{"name":475,"slug":476,"type":16},"UI Components","ui-components","2026-09-04T08:00:38.801247",16,{"items":480,"total":658},[481,497,514,528,540,557,573,584,605,621,635,650],{"slug":482,"name":482,"fn":483,"description":484,"org":485,"tags":486,"stars":494,"repoUrl":495,"updatedAt":496},"academy-guide","recommend Claude Academy resources","Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: \"how do I\", \"how can I\", \"getting started with\", \"what can Claude do\", \"teach me\", \"learn to use\"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[487,488,491],{"name":9,"slug":8,"type":16},{"name":489,"slug":490,"type":16},"Documentation","documentation",{"name":492,"slug":493,"type":16},"Education","education",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-08-19T03:59:01.021254",{"slug":498,"name":498,"fn":499,"description":500,"org":501,"tags":502,"stars":494,"repoUrl":495,"updatedAt":513},"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},[503,506,507,510],{"name":504,"slug":505,"type":16},"Creative","creative",{"name":468,"slug":469,"type":16},{"name":508,"slug":509,"type":16},"Generative Art","generative-art",{"name":511,"slug":512,"type":16},"JavaScript","javascript","2026-04-06T17:56:15.455818",{"slug":515,"name":515,"fn":516,"description":517,"org":518,"tags":519,"stars":494,"repoUrl":495,"updatedAt":527},"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},[520,523,524],{"name":521,"slug":522,"type":16},"Branding","branding",{"name":468,"slug":469,"type":16},{"name":525,"slug":526,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":529,"name":529,"fn":530,"description":531,"org":532,"tags":533,"stars":494,"repoUrl":495,"updatedAt":539},"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},[534,535,536],{"name":504,"slug":505,"type":16},{"name":468,"slug":469,"type":16},{"name":537,"slug":538,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":541,"name":541,"fn":542,"description":543,"org":544,"tags":545,"stars":494,"repoUrl":495,"updatedAt":556},"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},[546,547,548,551,553],{"name":391,"slug":392,"type":16},{"name":9,"slug":8,"type":16},{"name":549,"slug":550,"type":16},"Anthropic SDK","anthropic-sdk",{"name":552,"slug":541,"type":16},"Claude API",{"name":554,"slug":555,"type":16},"LLM","llm","2026-09-04T07:28:24.898544",{"slug":558,"name":558,"fn":559,"description":560,"org":561,"tags":562,"stars":494,"repoUrl":495,"updatedAt":572},"discernment-nudge","provide discernment nudges for user decisions","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[563,566,569],{"name":564,"slug":565,"type":16},"Coaching","coaching",{"name":567,"slug":568,"type":16},"Productivity","productivity",{"name":570,"slug":571,"type":16},"Strategy","strategy","2026-08-19T03:59:01.539281",{"slug":574,"name":574,"fn":575,"description":576,"org":577,"tags":578,"stars":494,"repoUrl":495,"updatedAt":583},"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},[579,580],{"name":489,"slug":490,"type":16},{"name":581,"slug":582,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":494,"repoUrl":495,"updatedAt":604},"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},[590,593,595,598,601],{"name":591,"slug":592,"type":16},"Documents","documents",{"name":594,"slug":585,"type":16},"DOCX",{"name":596,"slug":597,"type":16},"Office","office",{"name":599,"slug":600,"type":16},"Templates","templates",{"name":602,"slug":603,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":606,"name":606,"fn":607,"description":608,"org":609,"tags":610,"stars":494,"repoUrl":495,"updatedAt":620},"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},[611,612,613,616,619],{"name":468,"slug":469,"type":16},{"name":472,"slug":473,"type":16},{"name":614,"slug":615,"type":16},"React","react",{"name":617,"slug":618,"type":16},"Tailwind CSS","tailwind-css",{"name":475,"slug":476,"type":16},"2026-09-04T07:28:23.795756",{"slug":622,"name":622,"fn":623,"description":624,"org":625,"tags":626,"stars":494,"repoUrl":495,"updatedAt":634},"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},[627,630,631],{"name":628,"slug":629,"type":16},"Communications","communications",{"name":599,"slug":600,"type":16},{"name":632,"slug":633,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":636,"name":636,"fn":637,"description":638,"org":639,"tags":640,"stars":494,"repoUrl":495,"updatedAt":649},"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},[641,642,645,646],{"name":391,"slug":392,"type":16},{"name":643,"slug":644,"type":16},"API Development","api-development",{"name":554,"slug":555,"type":16},{"name":647,"slug":648,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":538,"name":538,"fn":651,"description":652,"org":653,"tags":654,"stars":494,"repoUrl":495,"updatedAt":657},"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},[655,656],{"name":591,"slug":592,"type":16},{"name":537,"slug":538,"type":16},"2026-04-06T17:56:02.483316",521]