[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-anthropic-compose-outreach":3,"mdc-rgunht-key":40,"related-repo-anthropic-compose-outreach":457,"related-org-anthropic-compose-outreach":572},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":35,"sourceUrl":38,"mdContent":39},"compose-outreach","draft personalized outreach messages","Generate personalized outreach messages using Common Room signals. Triggers on 'draft outreach to [person]', 'write an email to [name]', 'compose a message for [contact]', or any outreach drafting request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"anthropic","Anthropic","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fanthropic.png","anthropics",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"CRM","crm","tag",{"name":18,"slug":19,"type":16},"Sales","sales",{"name":21,"slug":22,"type":16},"Outreach","outreach",{"name":24,"slug":25,"type":16},"Email","email",{"name":27,"slug":28,"type":16},"Common Room","common-room",22885,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins","2026-04-06T18:00:19.597601",null,2736,[],{"repoUrl":30,"stars":29,"forks":33,"topics":36,"description":37},[],"Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fknowledge-work-plugins\u002Ftree\u002FHEAD\u002Fpartner-built\u002Fcommon-room\u002Fskills\u002Fcompose-outreach","---\nname: compose-outreach\ndescription: \"Generate personalized outreach messages using Common Room signals. Triggers on 'draft outreach to [person]', 'write an email to [name]', 'compose a message for [contact]', or any outreach drafting request.\"\n---\n\n# Compose Outreach\n\nGenerate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.\n\n## Outreach Process\n\n### Step 1: Look Up the Target\n\nUse Common Room MCP tools to find and retrieve data for the target (company and\u002For specific contact). Pull:\n- Recent product activity and engagement signals\n- Community activity (posts, questions, reactions)\n- 3rd-party intent signals (job postings, news, funding)\n- Relationship history (prior contact, meetings, email opens)\n\nIf the user specified a person, run contact-level research. If only a company was given, identify the best contact to target based on title, engagement, and role.\n\n### Step 2: Web Search for External Hooks (If CR Signals Are Thin)\n\nIf CR returned strong signals (recent activity, engagement, product usage), those should drive personalization — skip web search. If CR signals are thin or the prospect has little CR activity, run a web search for external hooks:\n\n**What to search:**\n- `\"[company name]\" funding OR acquisition OR launch OR announcement` — last 30 days\n- `\"[contact full name]\" \"[company name]\"` — look for recent articles, interviews, LinkedIn posts, or conference talks\n\n**Prioritize external hooks that are:**\n- Very recent (\u003C 2 weeks) — the prospect is likely still thinking about it\n- Publicly visible — they know you could have seen it\n- Change-signaling — growth, new role, new product, new market\n\nIf the user explicitly asks for web search or external hooks, run it regardless of CR signal richness.\n\n### Step 3: Spark Enrichment (If Available)\n\nIf Spark is available, run enrichment on the target contact to get persona classification, background, and influence signals. Use this to calibrate tone and message angle.\n\n### Step 4: Identify the Best Hooks\n\nFrom the signal data, identify the 1–3 strongest personalization hooks. Rank by:\n1. **Recency** — happened in the last 7–14 days\n2. **Specificity** — a concrete action they took, not a general trend\n3. **Relevance** — connects directly to a value your product delivers\n\nGood hooks: posted a question in the community about X, just hired 5 engineers, recently started using [feature], company just raised Series B, trial nearing expiration, champion just changed jobs.\n\nBad hooks: \"I noticed you're a customer\" or generic industry trends.\n\n### Step 5: Generate All Three Formats\n\nUse the strongest hooks to write all three formats. Each format has different constraints and conventions — follow the format-specific guidelines in `references\u002Foutreach-formats-guide.md`.\n\nAlways produce all three, clearly labeled.\n\nWhen the user's company context is available (see `references\u002Fmy-company-context.md`), ground the value bridge and pitch in the user's specific product and positioning.\n\n### Step 6: Annotate Your Choices\n\nAfter the three drafts, include a brief note (2–4 sentences) explaining:\n- Which signals were used and why they were chosen\n- Any assumptions made (e.g., inferred call objective)\n- Alternative angles if the primary hook doesn't land\n\n## Output Format\n\n```\n## Outreach for [Name \u002F Company]\n\n### 📧 Email\n\n**Subject:** [Subject line]\n\n[Email body — 3–5 sentences]\n\n---\n\n### 📞 Call Script\n\n**Opening:**\n[Opening line — conversational, 1–2 sentences]\n\n**Value Bridge:**\n[Why you're calling and why now — 2–3 sentences tied to a signal]\n\n**Ask:**\n[Single, low-friction ask — e.g., 15-minute call, specific question]\n\n---\n\n### 💼 LinkedIn Message\n\n[Under 300 characters. Warm, personal, no pitch.]\n\n---\n\n### Signal Notes\n[2–4 sentences: which signals were used, why, and any alternative angles]\n```\n\n## When Signal Data Is Sparse\n\nIf Common Room returns minimal data on the target (e.g., just name, title, tags — no activity, no scores, no Spark):\n\n1. **Do not draft outreach from thin air.** Outreach grounded in fabricated signals is worse than no outreach.\n2. **Run web search first** — this becomes your primary personalization source. Look for recent news, LinkedIn posts, conference talks, company announcements.\n3. **If web search also returns little**, present what you have honestly and ask the user for context:\n\n```\n## Outreach for [Name \u002F Company] — Limited Data\n\n**What I found:**\n[Only the real data from CR and web search]\n\n**I don't have enough signal to draft personalized outreach yet.** To write something strong, I'd need:\n- Recent activity or engagement signals\n- Context you have from prior conversations\n- A specific reason for reaching out now\n\nCan you share any of the above?\n```\n\n## Quality Standards\n\n- Every message must reference something specific — generic outreach is not acceptable output\n- Match tone to context: warm and conversational for inbound\u002Fcommunity signals; more formal for cold\u002Fexecutive outreach\n- The LinkedIn message must be under 300 characters — no exceptions\n- The call script must be speakable naturally — read it aloud mentally to check rhythm\n- **Never fabricate signals** — only reference data retrieved from Common Room or web search\n\n## Reference Files\n\n- **`references\u002Foutreach-formats-guide.md`** — detailed format rules, examples, and tone guidelines for each channel\n",{"data":41,"body":42},{"name":4,"description":6},{"type":43,"children":44},"root",[45,53,59,66,73,78,103,108,114,119,128,154,162,180,185,191,196,202,207,241,254,259,265,278,283,296,302,307,325,331,343,349,354,387,396,402,435,441],{"type":46,"tag":47,"props":48,"children":49},"element","h1",{"id":4},[50],{"type":51,"value":52},"text","Compose Outreach",{"type":46,"tag":54,"props":55,"children":56},"p",{},[57],{"type":51,"value":58},"Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.",{"type":46,"tag":60,"props":61,"children":63},"h2",{"id":62},"outreach-process",[64],{"type":51,"value":65},"Outreach Process",{"type":46,"tag":67,"props":68,"children":70},"h3",{"id":69},"step-1-look-up-the-target",[71],{"type":51,"value":72},"Step 1: Look Up the Target",{"type":46,"tag":54,"props":74,"children":75},{},[76],{"type":51,"value":77},"Use Common Room MCP tools to find and retrieve data for the target (company and\u002For specific contact). Pull:",{"type":46,"tag":79,"props":80,"children":81},"ul",{},[82,88,93,98],{"type":46,"tag":83,"props":84,"children":85},"li",{},[86],{"type":51,"value":87},"Recent product activity and engagement signals",{"type":46,"tag":83,"props":89,"children":90},{},[91],{"type":51,"value":92},"Community activity (posts, questions, reactions)",{"type":46,"tag":83,"props":94,"children":95},{},[96],{"type":51,"value":97},"3rd-party intent signals (job postings, news, funding)",{"type":46,"tag":83,"props":99,"children":100},{},[101],{"type":51,"value":102},"Relationship history (prior contact, meetings, email opens)",{"type":46,"tag":54,"props":104,"children":105},{},[106],{"type":51,"value":107},"If the user specified a person, run contact-level research. If only a company was given, identify the best contact to target based on title, engagement, and role.",{"type":46,"tag":67,"props":109,"children":111},{"id":110},"step-2-web-search-for-external-hooks-if-cr-signals-are-thin",[112],{"type":51,"value":113},"Step 2: Web Search for External Hooks (If CR Signals Are Thin)",{"type":46,"tag":54,"props":115,"children":116},{},[117],{"type":51,"value":118},"If CR returned strong signals (recent activity, engagement, product usage), those should drive personalization — skip web search. If CR signals are thin or the prospect has little CR activity, run a web search for external hooks:",{"type":46,"tag":54,"props":120,"children":121},{},[122],{"type":46,"tag":123,"props":124,"children":125},"strong",{},[126],{"type":51,"value":127},"What to search:",{"type":46,"tag":79,"props":129,"children":130},{},[131,143],{"type":46,"tag":83,"props":132,"children":133},{},[134,141],{"type":46,"tag":135,"props":136,"children":138},"code",{"className":137},[],[139],{"type":51,"value":140},"\"[company name]\" funding OR acquisition OR launch OR announcement",{"type":51,"value":142}," — last 30 days",{"type":46,"tag":83,"props":144,"children":145},{},[146,152],{"type":46,"tag":135,"props":147,"children":149},{"className":148},[],[150],{"type":51,"value":151},"\"[contact full name]\" \"[company name]\"",{"type":51,"value":153}," — look for recent articles, interviews, LinkedIn posts, or conference talks",{"type":46,"tag":54,"props":155,"children":156},{},[157],{"type":46,"tag":123,"props":158,"children":159},{},[160],{"type":51,"value":161},"Prioritize external hooks that are:",{"type":46,"tag":79,"props":163,"children":164},{},[165,170,175],{"type":46,"tag":83,"props":166,"children":167},{},[168],{"type":51,"value":169},"Very recent (\u003C 2 weeks) — the prospect is likely still thinking about it",{"type":46,"tag":83,"props":171,"children":172},{},[173],{"type":51,"value":174},"Publicly visible — they know you could have seen it",{"type":46,"tag":83,"props":176,"children":177},{},[178],{"type":51,"value":179},"Change-signaling — growth, new role, new product, new market",{"type":46,"tag":54,"props":181,"children":182},{},[183],{"type":51,"value":184},"If the user explicitly asks for web search or external hooks, run it regardless of CR signal richness.",{"type":46,"tag":67,"props":186,"children":188},{"id":187},"step-3-spark-enrichment-if-available",[189],{"type":51,"value":190},"Step 3: Spark Enrichment (If Available)",{"type":46,"tag":54,"props":192,"children":193},{},[194],{"type":51,"value":195},"If Spark is available, run enrichment on the target contact to get persona classification, background, and influence signals. Use this to calibrate tone and message angle.",{"type":46,"tag":67,"props":197,"children":199},{"id":198},"step-4-identify-the-best-hooks",[200],{"type":51,"value":201},"Step 4: Identify the Best Hooks",{"type":46,"tag":54,"props":203,"children":204},{},[205],{"type":51,"value":206},"From the signal data, identify the 1–3 strongest personalization hooks. Rank by:",{"type":46,"tag":208,"props":209,"children":210},"ol",{},[211,221,231],{"type":46,"tag":83,"props":212,"children":213},{},[214,219],{"type":46,"tag":123,"props":215,"children":216},{},[217],{"type":51,"value":218},"Recency",{"type":51,"value":220}," — happened in the last 7–14 days",{"type":46,"tag":83,"props":222,"children":223},{},[224,229],{"type":46,"tag":123,"props":225,"children":226},{},[227],{"type":51,"value":228},"Specificity",{"type":51,"value":230}," — a concrete action they took, not a general trend",{"type":46,"tag":83,"props":232,"children":233},{},[234,239],{"type":46,"tag":123,"props":235,"children":236},{},[237],{"type":51,"value":238},"Relevance",{"type":51,"value":240}," — connects directly to a value your product delivers",{"type":46,"tag":54,"props":242,"children":243},{},[244,246,252],{"type":51,"value":245},"Good hooks: posted a question in the community about X, just hired 5 engineers, recently started using ",{"type":46,"tag":247,"props":248,"children":249},"span",{},[250],{"type":51,"value":251},"feature",{"type":51,"value":253},", company just raised Series B, trial nearing expiration, champion just changed jobs.",{"type":46,"tag":54,"props":255,"children":256},{},[257],{"type":51,"value":258},"Bad hooks: \"I noticed you're a customer\" or generic industry trends.",{"type":46,"tag":67,"props":260,"children":262},{"id":261},"step-5-generate-all-three-formats",[263],{"type":51,"value":264},"Step 5: Generate All Three Formats",{"type":46,"tag":54,"props":266,"children":267},{},[268,270,276],{"type":51,"value":269},"Use the strongest hooks to write all three formats. Each format has different constraints and conventions — follow the format-specific guidelines in ",{"type":46,"tag":135,"props":271,"children":273},{"className":272},[],[274],{"type":51,"value":275},"references\u002Foutreach-formats-guide.md",{"type":51,"value":277},".",{"type":46,"tag":54,"props":279,"children":280},{},[281],{"type":51,"value":282},"Always produce all three, clearly labeled.",{"type":46,"tag":54,"props":284,"children":285},{},[286,288,294],{"type":51,"value":287},"When the user's company context is available (see ",{"type":46,"tag":135,"props":289,"children":291},{"className":290},[],[292],{"type":51,"value":293},"references\u002Fmy-company-context.md",{"type":51,"value":295},"), ground the value bridge and pitch in the user's specific product and positioning.",{"type":46,"tag":67,"props":297,"children":299},{"id":298},"step-6-annotate-your-choices",[300],{"type":51,"value":301},"Step 6: Annotate Your Choices",{"type":46,"tag":54,"props":303,"children":304},{},[305],{"type":51,"value":306},"After the three drafts, include a brief note (2–4 sentences) explaining:",{"type":46,"tag":79,"props":308,"children":309},{},[310,315,320],{"type":46,"tag":83,"props":311,"children":312},{},[313],{"type":51,"value":314},"Which signals were used and why they were chosen",{"type":46,"tag":83,"props":316,"children":317},{},[318],{"type":51,"value":319},"Any assumptions made (e.g., inferred call objective)",{"type":46,"tag":83,"props":321,"children":322},{},[323],{"type":51,"value":324},"Alternative angles if the primary hook doesn't land",{"type":46,"tag":60,"props":326,"children":328},{"id":327},"output-format",[329],{"type":51,"value":330},"Output Format",{"type":46,"tag":332,"props":333,"children":337},"pre",{"className":334,"code":336,"language":51},[335],"language-text","## Outreach for [Name \u002F Company]\n\n### 📧 Email\n\n**Subject:** [Subject line]\n\n[Email body — 3–5 sentences]\n\n---\n\n### 📞 Call Script\n\n**Opening:**\n[Opening line — conversational, 1–2 sentences]\n\n**Value Bridge:**\n[Why you're calling and why now — 2–3 sentences tied to a signal]\n\n**Ask:**\n[Single, low-friction ask — e.g., 15-minute call, specific question]\n\n---\n\n### 💼 LinkedIn Message\n\n[Under 300 characters. Warm, personal, no pitch.]\n\n---\n\n### Signal Notes\n[2–4 sentences: which signals were used, why, and any alternative angles]\n",[338],{"type":46,"tag":135,"props":339,"children":341},{"__ignoreMap":340},"",[342],{"type":51,"value":336},{"type":46,"tag":60,"props":344,"children":346},{"id":345},"when-signal-data-is-sparse",[347],{"type":51,"value":348},"When Signal Data Is Sparse",{"type":46,"tag":54,"props":350,"children":351},{},[352],{"type":51,"value":353},"If Common Room returns minimal data on the target (e.g., just name, title, tags — no activity, no scores, no Spark):",{"type":46,"tag":208,"props":355,"children":356},{},[357,367,377],{"type":46,"tag":83,"props":358,"children":359},{},[360,365],{"type":46,"tag":123,"props":361,"children":362},{},[363],{"type":51,"value":364},"Do not draft outreach from thin air.",{"type":51,"value":366}," Outreach grounded in fabricated signals is worse than no outreach.",{"type":46,"tag":83,"props":368,"children":369},{},[370,375],{"type":46,"tag":123,"props":371,"children":372},{},[373],{"type":51,"value":374},"Run web search first",{"type":51,"value":376}," — this becomes your primary personalization source. Look for recent news, LinkedIn posts, conference talks, company announcements.",{"type":46,"tag":83,"props":378,"children":379},{},[380,385],{"type":46,"tag":123,"props":381,"children":382},{},[383],{"type":51,"value":384},"If web search also returns little",{"type":51,"value":386},", present what you have honestly and ask the user for context:",{"type":46,"tag":332,"props":388,"children":391},{"className":389,"code":390,"language":51},[335],"## Outreach for [Name \u002F Company] — Limited Data\n\n**What I found:**\n[Only the real data from CR and web search]\n\n**I don't have enough signal to draft personalized outreach yet.** To write something strong, I'd need:\n- Recent activity or engagement signals\n- Context you have from prior conversations\n- A specific reason for reaching out now\n\nCan you share any of the above?\n",[392],{"type":46,"tag":135,"props":393,"children":394},{"__ignoreMap":340},[395],{"type":51,"value":390},{"type":46,"tag":60,"props":397,"children":399},{"id":398},"quality-standards",[400],{"type":51,"value":401},"Quality Standards",{"type":46,"tag":79,"props":403,"children":404},{},[405,410,415,420,425],{"type":46,"tag":83,"props":406,"children":407},{},[408],{"type":51,"value":409},"Every message must reference something specific — generic outreach is not acceptable output",{"type":46,"tag":83,"props":411,"children":412},{},[413],{"type":51,"value":414},"Match tone to context: warm and conversational for inbound\u002Fcommunity signals; more formal for cold\u002Fexecutive outreach",{"type":46,"tag":83,"props":416,"children":417},{},[418],{"type":51,"value":419},"The LinkedIn message must be under 300 characters — no exceptions",{"type":46,"tag":83,"props":421,"children":422},{},[423],{"type":51,"value":424},"The call script must be speakable naturally — read it aloud mentally to check rhythm",{"type":46,"tag":83,"props":426,"children":427},{},[428,433],{"type":46,"tag":123,"props":429,"children":430},{},[431],{"type":51,"value":432},"Never fabricate signals",{"type":51,"value":434}," — only reference data retrieved from Common Room or web search",{"type":46,"tag":60,"props":436,"children":438},{"id":437},"reference-files",[439],{"type":51,"value":440},"Reference Files",{"type":46,"tag":79,"props":442,"children":443},{},[444],{"type":46,"tag":83,"props":445,"children":446},{},[447,455],{"type":46,"tag":123,"props":448,"children":449},{},[450],{"type":46,"tag":135,"props":451,"children":453},{"className":452},[],[454],{"type":51,"value":275},{"type":51,"value":456}," — detailed format rules, examples, and tone guidelines for each channel",{"items":458,"total":571},[459,475,487,503,521,540,556],{"slug":460,"name":460,"fn":461,"description":462,"org":463,"tags":464,"stars":29,"repoUrl":30,"updatedAt":474},"accessibility-review","run WCAG accessibility audits","Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with \"audit accessibility\", \"check a11y\", \"is this accessible?\", or when reviewing a design for color contrast, keyboard navigation, touch target size, or screen reader behavior before handoff.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[465,468,471],{"name":466,"slug":467,"type":16},"Accessibility","accessibility",{"name":469,"slug":470,"type":16},"Design","design",{"name":472,"slug":473,"type":16},"WCAG","wcag","2026-04-06T17:58:05.682394",{"slug":476,"name":476,"fn":477,"description":478,"org":479,"tags":480,"stars":29,"repoUrl":30,"updatedAt":486},"account-research","research accounts for sales intel","Research a company or person and get actionable sales intel. Works standalone with web search, supercharged when you connect enrichment tools or your CRM. Trigger with \"research [company]\", \"look up [person]\", \"intel on [prospect]\", \"who is [name] at [company]\", or \"tell me about [company]\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[481,482,485],{"name":14,"slug":15,"type":16},{"name":483,"slug":484,"type":16},"Research","research",{"name":18,"slug":19,"type":16},"2026-04-06T17:56:41.410418",{"slug":488,"name":488,"fn":489,"description":490,"org":491,"tags":492,"stars":29,"repoUrl":30,"updatedAt":502},"analyze","answer data questions and run analyses","Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[493,496,499],{"name":494,"slug":495,"type":16},"Analytics","analytics",{"name":497,"slug":498,"type":16},"Data Analysis","data-analysis",{"name":500,"slug":501,"type":16},"SQL","sql","2026-04-06T17:57:21.593647",{"slug":504,"name":504,"fn":505,"description":506,"org":507,"tags":508,"stars":29,"repoUrl":30,"updatedAt":520},"architecture","create and evaluate architecture decision records","Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[509,512,514,517],{"name":510,"slug":511,"type":16},"ADR","adr",{"name":513,"slug":504,"type":16},"Architecture",{"name":515,"slug":516,"type":16},"Documentation","documentation",{"name":518,"slug":519,"type":16},"Engineering","engineering","2026-04-06T17:57:49.26444",{"slug":522,"name":522,"fn":523,"description":524,"org":525,"tags":526,"stars":29,"repoUrl":30,"updatedAt":539},"audit-support","support SOX 404 control testing","Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[527,530,533,536],{"name":528,"slug":529,"type":16},"Audit","audit",{"name":531,"slug":532,"type":16},"Finance","finance",{"name":534,"slug":535,"type":16},"Regulatory Compliance","regulatory-compliance",{"name":537,"slug":538,"type":16},"SOX","sox","2026-04-06T17:57:36.714815",{"slug":541,"name":541,"fn":542,"description":543,"org":544,"tags":545,"stars":29,"repoUrl":30,"updatedAt":555},"brand-review","review content against brand voice","Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before\u002Fafter fixes. Use when checking a draft before it ships, when auditing copy for voice consistency and terminology, or when screening for unsubstantiated claims, missing disclaimers, and other legal flags.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[546,549,552],{"name":547,"slug":548,"type":16},"Branding","branding",{"name":550,"slug":551,"type":16},"Marketing","marketing",{"name":553,"slug":554,"type":16},"Writing","writing","2026-04-06T17:58:19.548331",{"slug":557,"name":557,"fn":558,"description":559,"org":560,"tags":561,"stars":29,"repoUrl":30,"updatedAt":570},"brand-voice-enforcement","enforce brand voice in content","This skill applies brand guidelines to content creation. It should be used when the user asks to \"write an email\", \"draft a proposal\", \"create a pitch deck\", \"write a LinkedIn post\", \"draft a presentation\", \"write a Slack message\", \"draft sales content\", or any content creation request where brand voice should be applied. Also triggers on \"on-brand\", \"brand voice\", \"enforce voice\", \"apply brand guidelines\", \"brand-aligned content\", \"write in our voice\", \"use our brand tone\", \"make this sound like us\", \"rewrite this in our tone\", or \"this doesn't sound on-brand\". Not for generating guidelines from scratch (use guideline-generation) or discovering brand materials (use discover-brand).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[562,563,566,569],{"name":547,"slug":548,"type":16},{"name":564,"slug":565,"type":16},"Communications","communications",{"name":567,"slug":568,"type":16},"Content Creation","content-creation",{"name":553,"slug":554,"type":16},"2026-04-06T18:00:23.528956",200,{"items":573,"total":750},[574,593,605,617,636,647,668,688,698,713,721,734],{"slug":575,"name":575,"fn":576,"description":577,"org":578,"tags":579,"stars":590,"repoUrl":591,"updatedAt":592},"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},[580,583,584,587],{"name":581,"slug":582,"type":16},"Creative","creative",{"name":469,"slug":470,"type":16},{"name":585,"slug":586,"type":16},"Generative Art","generative-art",{"name":588,"slug":589,"type":16},"JavaScript","javascript",161831,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills","2026-04-06T17:56:15.455818",{"slug":594,"name":594,"fn":595,"description":596,"org":597,"tags":598,"stars":590,"repoUrl":591,"updatedAt":604},"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},[599,600,601],{"name":547,"slug":548,"type":16},{"name":469,"slug":470,"type":16},{"name":602,"slug":603,"type":16},"Typography","typography","2026-04-06T17:56:05.042852",{"slug":606,"name":606,"fn":607,"description":608,"org":609,"tags":610,"stars":590,"repoUrl":591,"updatedAt":616},"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},[611,612,613],{"name":581,"slug":582,"type":16},{"name":469,"slug":470,"type":16},{"name":614,"slug":615,"type":16},"PDF","pdf","2026-04-06T17:56:03.794732",{"slug":618,"name":618,"fn":619,"description":620,"org":621,"tags":622,"stars":590,"repoUrl":591,"updatedAt":635},"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},[623,626,627,630,632],{"name":624,"slug":625,"type":16},"Agents","agents",{"name":9,"slug":8,"type":16},{"name":628,"slug":629,"type":16},"Anthropic SDK","anthropic-sdk",{"name":631,"slug":618,"type":16},"Claude API",{"name":633,"slug":634,"type":16},"LLM","llm","2026-07-28T05:36:08.213335",{"slug":637,"name":637,"fn":638,"description":639,"org":640,"tags":641,"stars":590,"repoUrl":591,"updatedAt":646},"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},[642,643],{"name":515,"slug":516,"type":16},{"name":644,"slug":645,"type":16},"Technical Writing","technical-writing","2026-04-06T17:56:14.18897",{"slug":648,"name":648,"fn":649,"description":650,"org":651,"tags":652,"stars":590,"repoUrl":591,"updatedAt":667},"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},[653,656,658,661,664],{"name":654,"slug":655,"type":16},"Documents","documents",{"name":657,"slug":648,"type":16},"DOCX",{"name":659,"slug":660,"type":16},"Office","office",{"name":662,"slug":663,"type":16},"Templates","templates",{"name":665,"slug":666,"type":16},"Word","word","2026-07-18T05:16:23.136271",{"slug":669,"name":669,"fn":670,"description":671,"org":672,"tags":673,"stars":590,"repoUrl":591,"updatedAt":687},"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},[674,675,678,681,684],{"name":469,"slug":470,"type":16},{"name":676,"slug":677,"type":16},"Frontend","frontend",{"name":679,"slug":680,"type":16},"React","react",{"name":682,"slug":683,"type":16},"Tailwind CSS","tailwind-css",{"name":685,"slug":686,"type":16},"UI Components","ui-components","2026-04-06T17:56:16.723469",{"slug":689,"name":689,"fn":690,"description":691,"org":692,"tags":693,"stars":590,"repoUrl":591,"updatedAt":697},"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},[694,695,696],{"name":564,"slug":565,"type":16},{"name":662,"slug":663,"type":16},{"name":553,"slug":554,"type":16},"2026-04-06T17:56:20.695522",{"slug":699,"name":699,"fn":700,"description":701,"org":702,"tags":703,"stars":590,"repoUrl":591,"updatedAt":712},"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},[704,705,708,709],{"name":624,"slug":625,"type":16},{"name":706,"slug":707,"type":16},"API Development","api-development",{"name":633,"slug":634,"type":16},{"name":710,"slug":711,"type":16},"MCP","mcp","2026-04-06T17:56:10.357665",{"slug":615,"name":615,"fn":714,"description":715,"org":716,"tags":717,"stars":590,"repoUrl":591,"updatedAt":720},"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},[718,719],{"name":654,"slug":655,"type":16},{"name":614,"slug":615,"type":16},"2026-04-06T17:56:02.483316",{"slug":722,"name":722,"fn":723,"description":724,"org":725,"tags":726,"stars":590,"repoUrl":591,"updatedAt":733},"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},[727,730],{"name":728,"slug":729,"type":16},"PowerPoint","powerpoint",{"name":731,"slug":732,"type":16},"Presentations","presentations","2026-07-18T05:16:24.1471",{"slug":735,"name":735,"fn":736,"description":737,"org":738,"tags":739,"stars":590,"repoUrl":591,"updatedAt":749},"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},[740,741,742,745,748],{"name":624,"slug":625,"type":16},{"name":515,"slug":516,"type":16},{"name":743,"slug":744,"type":16},"Evals","evals",{"name":746,"slug":747,"type":16},"Performance","performance",{"name":644,"slug":645,"type":16},"2026-04-19T06:45:40.804",490]