[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-purchase-research":3,"mdc--g5gqq5-key":34,"related-repo-anthropic-purchase-research":242,"related-org-anthropic-purchase-research":360},{"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},"purchase-research","guide customers through product research","Teaching a customer how to choose before any candidates appear, when they ask what matters in a category, how two approaches to it differ, or where to begin. Not needed once the customer has named the thing they want, however considered the purchase (that is search work), nor for outfitting a space or an event (planning-goals).",{"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},"Research","research","tag",{"name":18,"slug":19,"type":16},"Customer Support","customer-support",{"name":21,"slug":22,"type":16},"Sales","sales",1735,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fcommerce-agents","2026-09-04T08:00:32.349783",null,277,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"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\u002Fshopping-agent\u002Fskills\u002Fpurchase-research","---\nname: purchase-research\ndescription: Teaching a customer how to choose before any candidates appear, when they ask what matters in a category, how two approaches to it differ, or where to begin. Not needed once the customer has named the thing they want, however considered the purchase (that is search work), nor for outfitting a space or an event (planning-goals).\n---\n\n# Purchase research\n\nBelow, \"category\" means a kind of whatever this store sells: products, stays, plans, or seating.\n\nThe customer has a category in mind and no criteria yet. Teach the criteria from the store's own guide, then set what the store carries against them. The choice, and anything that touches the cart, stays with the customer.\n\n## Ask once or not at all\n\n- When the deciding facts are open (who it is for, how many, what for, a firm budget), spend one turn on two or three short questions in one message, each with its likely answers as chips; ask only what the profile you were given leaves open. This intake happens once.\n- Whatever comes back closes intake: answers, a request to get on with it, or a question of their own. Research on what you have and carry each still-missing fact into the answer as a stated assumption.\n- When the request already names the people, the purpose, and the limits, skip the questions and research.\n- The customer sees either the questions or the answer; do not describe the intake decision or the research work.\n\n## Where the criteria and the products come from\n\n- Open every research turn with one round of calls: `search_policies` for the store's buying guide on the category, `search_products` for what it carries, and one or two `web_search` calls on the category where that tool is registered. Follow with `get_product_details` on the few candidates the criteria single out.\n- Read the guide even for a familiar category; it is the advice the store puts its name to. Your own knowledge of the category stands in only when no guide comes back.\n- Use web material for the category side only (criteria, terminology, how the trade-off works), restated in your own words. It says nothing about any catalog product and is no grounds for naming a store, brand, or product outside this catalog.\n- List in `sources` what you retrieved, the store's guides and any web pages used, and nothing when neither came back. Leave out a criterion none of the retrieved guides or records support.\n\n## Shape of the answer\n\n- After an intake turn, answer whole: the criteria and the store's options against them in one turn.\n- For a broad ask with no intake, answer in two steps: `present_guide` with three to five sections of one criterion each and chips for saying which criteria weigh most, then the shortlist next turn, filtered by their choice. Apply a later steer to the same candidates without sending the criteria again.\n- For a narrow ask whose wording already fixes the top criterion or two, answer in one turn: a compact criteria section, then the options against those criteria, in `present_comparison` for two to four real candidates and `present_products` otherwise.\n- Show the store's real position. Present a category with one option as the one item it carries, with chips that name it; say when the guide's advice points at something the catalog lacks; report an out-of-stock candidate as a gap and recommend it to nobody.\n- Name the pick with the criterion that decided it, in one clause. Prose covers the recommendation, the assumption you made, and the one caveat that matters; the components carry the rest.\n\n## Scope\n\n- Research turns read and recommend. Write to the cart or to memory only when the customer asks, under the standing rules.\n- Where the category borders on health, safety, or a licensed profession, keep the criteria about which product to buy.\n- Add a purchase chip only once the customer has seen the criteria.\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,47,53,58,65,90,96,160,166,218,224],{"type":40,"tag":41,"props":42,"children":43},"element","h1",{"id":4},[44],{"type":45,"value":46},"text","Purchase research",{"type":40,"tag":48,"props":49,"children":50},"p",{},[51],{"type":45,"value":52},"Below, \"category\" means a kind of whatever this store sells: products, stays, plans, or seating.",{"type":40,"tag":48,"props":54,"children":55},{},[56],{"type":45,"value":57},"The customer has a category in mind and no criteria yet. Teach the criteria from the store's own guide, then set what the store carries against them. The choice, and anything that touches the cart, stays with the customer.",{"type":40,"tag":59,"props":60,"children":62},"h2",{"id":61},"ask-once-or-not-at-all",[63],{"type":45,"value":64},"Ask once or not at all",{"type":40,"tag":66,"props":67,"children":68},"ul",{},[69,75,80,85],{"type":40,"tag":70,"props":71,"children":72},"li",{},[73],{"type":45,"value":74},"When the deciding facts are open (who it is for, how many, what for, a firm budget), spend one turn on two or three short questions in one message, each with its likely answers as chips; ask only what the profile you were given leaves open. This intake happens once.",{"type":40,"tag":70,"props":76,"children":77},{},[78],{"type":45,"value":79},"Whatever comes back closes intake: answers, a request to get on with it, or a question of their own. Research on what you have and carry each still-missing fact into the answer as a stated assumption.",{"type":40,"tag":70,"props":81,"children":82},{},[83],{"type":45,"value":84},"When the request already names the people, the purpose, and the limits, skip the questions and research.",{"type":40,"tag":70,"props":86,"children":87},{},[88],{"type":45,"value":89},"The customer sees either the questions or the answer; do not describe the intake decision or the research work.",{"type":40,"tag":59,"props":91,"children":93},{"id":92},"where-the-criteria-and-the-products-come-from",[94],{"type":45,"value":95},"Where the criteria and the products come from",{"type":40,"tag":66,"props":97,"children":98},{},[99,137,142,147],{"type":40,"tag":70,"props":100,"children":101},{},[102,104,111,113,119,121,127,129,135],{"type":45,"value":103},"Open every research turn with one round of calls: ",{"type":40,"tag":105,"props":106,"children":108},"code",{"className":107},[],[109],{"type":45,"value":110},"search_policies",{"type":45,"value":112}," for the store's buying guide on the category, ",{"type":40,"tag":105,"props":114,"children":116},{"className":115},[],[117],{"type":45,"value":118},"search_products",{"type":45,"value":120}," for what it carries, and one or two ",{"type":40,"tag":105,"props":122,"children":124},{"className":123},[],[125],{"type":45,"value":126},"web_search",{"type":45,"value":128}," calls on the category where that tool is registered. Follow with ",{"type":40,"tag":105,"props":130,"children":132},{"className":131},[],[133],{"type":45,"value":134},"get_product_details",{"type":45,"value":136}," on the few candidates the criteria single out.",{"type":40,"tag":70,"props":138,"children":139},{},[140],{"type":45,"value":141},"Read the guide even for a familiar category; it is the advice the store puts its name to. Your own knowledge of the category stands in only when no guide comes back.",{"type":40,"tag":70,"props":143,"children":144},{},[145],{"type":45,"value":146},"Use web material for the category side only (criteria, terminology, how the trade-off works), restated in your own words. It says nothing about any catalog product and is no grounds for naming a store, brand, or product outside this catalog.",{"type":40,"tag":70,"props":148,"children":149},{},[150,152,158],{"type":45,"value":151},"List in ",{"type":40,"tag":105,"props":153,"children":155},{"className":154},[],[156],{"type":45,"value":157},"sources",{"type":45,"value":159}," what you retrieved, the store's guides and any web pages used, and nothing when neither came back. Leave out a criterion none of the retrieved guides or records support.",{"type":40,"tag":59,"props":161,"children":163},{"id":162},"shape-of-the-answer",[164],{"type":45,"value":165},"Shape of the answer",{"type":40,"tag":66,"props":167,"children":168},{},[169,174,187,208,213],{"type":40,"tag":70,"props":170,"children":171},{},[172],{"type":45,"value":173},"After an intake turn, answer whole: the criteria and the store's options against them in one turn.",{"type":40,"tag":70,"props":175,"children":176},{},[177,179,185],{"type":45,"value":178},"For a broad ask with no intake, answer in two steps: ",{"type":40,"tag":105,"props":180,"children":182},{"className":181},[],[183],{"type":45,"value":184},"present_guide",{"type":45,"value":186}," with three to five sections of one criterion each and chips for saying which criteria weigh most, then the shortlist next turn, filtered by their choice. Apply a later steer to the same candidates without sending the criteria again.",{"type":40,"tag":70,"props":188,"children":189},{},[190,192,198,200,206],{"type":45,"value":191},"For a narrow ask whose wording already fixes the top criterion or two, answer in one turn: a compact criteria section, then the options against those criteria, in ",{"type":40,"tag":105,"props":193,"children":195},{"className":194},[],[196],{"type":45,"value":197},"present_comparison",{"type":45,"value":199}," for two to four real candidates and ",{"type":40,"tag":105,"props":201,"children":203},{"className":202},[],[204],{"type":45,"value":205},"present_products",{"type":45,"value":207}," otherwise.",{"type":40,"tag":70,"props":209,"children":210},{},[211],{"type":45,"value":212},"Show the store's real position. Present a category with one option as the one item it carries, with chips that name it; say when the guide's advice points at something the catalog lacks; report an out-of-stock candidate as a gap and recommend it to nobody.",{"type":40,"tag":70,"props":214,"children":215},{},[216],{"type":45,"value":217},"Name the pick with the criterion that decided it, in one clause. Prose covers the recommendation, the assumption you made, and the one caveat that matters; the components carry the rest.",{"type":40,"tag":59,"props":219,"children":221},{"id":220},"scope",[222],{"type":45,"value":223},"Scope",{"type":40,"tag":66,"props":225,"children":226},{},[227,232,237],{"type":40,"tag":70,"props":228,"children":229},{},[230],{"type":45,"value":231},"Research turns read and recommend. Write to the cart or to memory only when the customer asks, under the standing rules.",{"type":40,"tag":70,"props":233,"children":234},{},[235],{"type":45,"value":236},"Where the category borders on health, safety, or a licensed profession, keep the criteria about which product to buy.",{"type":40,"tag":70,"props":238,"children":239},{},[240],{"type":45,"value":241},"Add a purchase chip only once the customer has seen the criteria.",{"items":243,"total":359},[244,263,280,295,310,325,342],{"slug":245,"name":245,"fn":246,"description":247,"org":248,"tags":249,"stars":23,"repoUrl":24,"updatedAt":262},"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},[250,253,256,259],{"name":251,"slug":252,"type":16},"Content Creation","content-creation",{"name":254,"slug":255,"type":16},"Content Strategy","content-strategy",{"name":257,"slug":258,"type":16},"E-commerce","e-commerce",{"name":260,"slug":261,"type":16},"Marketing","marketing","2026-09-04T08:00:35.843558",{"slug":264,"name":264,"fn":265,"description":266,"org":267,"tags":268,"stars":23,"repoUrl":24,"updatedAt":279},"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},[269,272,275,276],{"name":270,"slug":271,"type":16},"Agents","agents",{"name":273,"slug":274,"type":16},"Architecture","architecture",{"name":257,"slug":258,"type":16},{"name":277,"slug":278,"type":16},"Engineering","engineering","2026-09-04T08:00:39.152322",{"slug":281,"name":281,"fn":282,"description":283,"org":284,"tags":285,"stars":23,"repoUrl":24,"updatedAt":294},"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},[286,287,288,291],{"name":270,"slug":271,"type":16},{"name":257,"slug":258,"type":16},{"name":289,"slug":290,"type":16},"Evals","evals",{"name":292,"slug":293,"type":16},"Testing","testing","2026-09-04T08:00:36.204114",{"slug":296,"name":296,"fn":297,"description":298,"org":299,"tags":300,"stars":23,"repoUrl":24,"updatedAt":309},"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},[301,302,303,306],{"name":270,"slug":271,"type":16},{"name":257,"slug":258,"type":16},{"name":304,"slug":305,"type":16},"Management","management",{"name":307,"slug":308,"type":16},"Operations","operations","2026-09-04T08:00:35.464555",{"slug":311,"name":311,"fn":312,"description":313,"org":314,"tags":315,"stars":23,"repoUrl":24,"updatedAt":324},"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},[316,317,318,321],{"name":270,"slug":271,"type":16},{"name":257,"slug":258,"type":16},{"name":319,"slug":320,"type":16},"Performance","performance",{"name":322,"slug":323,"type":16},"Prompt Engineering","prompt-engineering","2026-09-04T08:00:39.50364",{"slug":326,"name":326,"fn":327,"description":328,"org":329,"tags":330,"stars":23,"repoUrl":24,"updatedAt":341},"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},[331,332,335,338],{"name":270,"slug":271,"type":16},{"name":333,"slug":334,"type":16},"Compliance","compliance",{"name":336,"slug":337,"type":16},"Memory","memory",{"name":339,"slug":340,"type":16},"Security","security","2026-09-04T08:00:42.609563",{"slug":343,"name":343,"fn":344,"description":345,"org":346,"tags":347,"stars":23,"repoUrl":24,"updatedAt":358},"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},[348,351,352,355],{"name":349,"slug":350,"type":16},"Design","design",{"name":257,"slug":258,"type":16},{"name":353,"slug":354,"type":16},"Frontend","frontend",{"name":356,"slug":357,"type":16},"UI Components","ui-components","2026-09-04T08:00:38.801247",16,{"items":361,"total":539},[362,378,395,409,421,438,454,465,486,502,516,531],{"slug":363,"name":363,"fn":364,"description":365,"org":366,"tags":367,"stars":375,"repoUrl":376,"updatedAt":377},"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},[368,369,372],{"name":9,"slug":8,"type":16},{"name":370,"slug":371,"type":16},"Documentation","documentation",{"name":373,"slug":374,"type":16},"Education","education",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-08-19T03:59:01.021254",{"slug":379,"name":379,"fn":380,"description":381,"org":382,"tags":383,"stars":375,"repoUrl":376,"updatedAt":394},"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},[384,387,388,391],{"name":385,"slug":386,"type":16},"Creative","creative",{"name":349,"slug":350,"type":16},{"name":389,"slug":390,"type":16},"Generative Art","generative-art",{"name":392,"slug":393,"type":16},"JavaScript","javascript","2026-04-06T17:56:15.455818",{"slug":396,"name":396,"fn":397,"description":398,"org":399,"tags":400,"stars":375,"repoUrl":376,"updatedAt":408},"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},[401,404,405],{"name":402,"slug":403,"type":16},"Branding","branding",{"name":349,"slug":350,"type":16},{"name":406,"slug":407,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":410,"name":410,"fn":411,"description":412,"org":413,"tags":414,"stars":375,"repoUrl":376,"updatedAt":420},"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},[415,416,417],{"name":385,"slug":386,"type":16},{"name":349,"slug":350,"type":16},{"name":418,"slug":419,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":422,"name":422,"fn":423,"description":424,"org":425,"tags":426,"stars":375,"repoUrl":376,"updatedAt":437},"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},[427,428,429,432,434],{"name":270,"slug":271,"type":16},{"name":9,"slug":8,"type":16},{"name":430,"slug":431,"type":16},"Anthropic SDK","anthropic-sdk",{"name":433,"slug":422,"type":16},"Claude API",{"name":435,"slug":436,"type":16},"LLM","llm","2026-09-04T07:28:24.898544",{"slug":439,"name":439,"fn":440,"description":441,"org":442,"tags":443,"stars":375,"repoUrl":376,"updatedAt":453},"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},[444,447,450],{"name":445,"slug":446,"type":16},"Coaching","coaching",{"name":448,"slug":449,"type":16},"Productivity","productivity",{"name":451,"slug":452,"type":16},"Strategy","strategy","2026-08-19T03:59:01.539281",{"slug":455,"name":455,"fn":456,"description":457,"org":458,"tags":459,"stars":375,"repoUrl":376,"updatedAt":464},"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},[460,461],{"name":370,"slug":371,"type":16},{"name":462,"slug":463,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":466,"name":466,"fn":467,"description":468,"org":469,"tags":470,"stars":375,"repoUrl":376,"updatedAt":485},"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},[471,474,476,479,482],{"name":472,"slug":473,"type":16},"Documents","documents",{"name":475,"slug":466,"type":16},"DOCX",{"name":477,"slug":478,"type":16},"Office","office",{"name":480,"slug":481,"type":16},"Templates","templates",{"name":483,"slug":484,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":487,"name":487,"fn":488,"description":489,"org":490,"tags":491,"stars":375,"repoUrl":376,"updatedAt":501},"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},[492,493,494,497,500],{"name":349,"slug":350,"type":16},{"name":353,"slug":354,"type":16},{"name":495,"slug":496,"type":16},"React","react",{"name":498,"slug":499,"type":16},"Tailwind CSS","tailwind-css",{"name":356,"slug":357,"type":16},"2026-09-04T07:28:23.795756",{"slug":503,"name":503,"fn":504,"description":505,"org":506,"tags":507,"stars":375,"repoUrl":376,"updatedAt":515},"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},[508,511,512],{"name":509,"slug":510,"type":16},"Communications","communications",{"name":480,"slug":481,"type":16},{"name":513,"slug":514,"type":16},"Writing","writing","2026-04-06T17:56:20.695522",{"slug":517,"name":517,"fn":518,"description":519,"org":520,"tags":521,"stars":375,"repoUrl":376,"updatedAt":530},"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},[522,523,526,527],{"name":270,"slug":271,"type":16},{"name":524,"slug":525,"type":16},"API Development","api-development",{"name":435,"slug":436,"type":16},{"name":528,"slug":529,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":419,"name":419,"fn":532,"description":533,"org":534,"tags":535,"stars":375,"repoUrl":376,"updatedAt":538},"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},[536,537],{"name":472,"slug":473,"type":16},{"name":418,"slug":419,"type":16},"2026-04-06T17:56:02.483316",521]