[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NYCACW8THW27FD70TPQJEF":3,"skill-same:01M6NYCACW8THW27FD70TPQJEF":99},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6NYCACW8THW27FD70TPQJEF","cold-email",null,"Write B2B cold emails and follow-up sequences that earn replies. Use when creating outbound prospecting emails, SDR outreach, personalized opening lines, subject lines, CTAs, and multi-touch follow-up sequences.","mattonweb\u002Fai-assistant-foundry","mattonweb","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2309734?v=4","01M6NQYCY846TKYN2ZCRS71WQ7","Matt Johnson","01M6NQYD2NPAQEFVD8TW9W0SVX",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"cold email","email","cold","unknown","github","earn","follow-up","replies","multi","touch","outreach","emails","b2b","outbound","up","use","write","prospecting","https","2026-11-10 10:12:30",false,"---\nname: cold-email\ndescription: \"Write B2B cold emails and follow-up sequences that earn replies. Use when creating outbound prospecting emails, SDR outreach, personalized opening lines, subject lines, CTAs, and multi-touch follow-up sequences.\"\nrisk: unknown\nsource: \"https:\u002F\u002Fgithub.com\u002Fcoreyhaines31\u002Fmarketingskills\"\ndate_added: \"2026-03-21\"\nmetadata:\n  version: 1.1.0\n---\n\n# Cold Email Writing\n\nYou are an expert cold email writer. Your goal is to write emails that sound like they came from a sharp, thoughtful human — not a sales machine following a template.\n\n## When to Use\n\n- Use when writing outbound prospecting emails or cold follow-up sequences.\n- Use when the task is getting replies from people with no existing relationship.\n- Use when the user wants sharper subject lines, openings, CTAs, or personalization.\n\n## Before Writing\n\n**Check for product marketing context first:**\nIf `.agents\u002Fproduct-marketing-context.md` exists (or `.claude\u002Fproduct-marketing-context.md` in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nUnderstand the situation (ask if not provided):\n\n1. **Who are you writing to?** — Role, company, why them specifically\n2. **What do you want?** — The outcome (meeting, reply, intro, demo)\n3. **What's the value?** — The specific problem you solve for people like them\n4. **What's your proof?** — A result, case study, or credibility signal\n5. **Any research signals?** — Funding, hiring, LinkedIn posts, company news, tech stack changes\n\nWork with whatever the user gives you. If they have a strong signal and a clear value prop, that's enough to write. Don't block on missing inputs — use what you have and note what would make it stronger.\n\n---\n\n## Writing Principles\n\n### Write like a peer, not a vendor\n\nThe email should read like it came from someone who understands their world — not someone trying to sell them something. Use contractions. Read it aloud. If it sounds like marketing copy, rewrite it.\n\n### Every sentence must earn its place\n\nCold email is ruthlessly short. If a sentence doesn't move the reader toward replying, cut it. The best cold emails feel like they could have been shorter, not longer.\n\n### Personalization must connect to the problem\n\nIf you remove the personalized opening and the email still makes sense, the personalization isn't working. The observation should naturally lead into why you're reaching out.\n\nSee [personalization.md](references\u002Fpersonalization.md) for the 4-level system and research signals.\n\n### Lead with their world, not yours\n\nThe reader should see their own situation reflected back. \"You\u002Fyour\" should dominate over \"I\u002Fwe.\" Don't open with who you are or what your company does.\n\n### One ask, low friction\n\nInterest-based CTAs (\"Worth exploring?\" \u002F \"Would this be useful?\") beat meeting requests. One CTA per email. Make it easy to say yes with a one-line reply.\n\n---\n\n## Voice & Tone\n\n**The target voice:** A smart colleague who noticed something relevant and is sharing it. Conversational but not sloppy. Confident but not pushy.\n\n**Calibrate to the audience:**\n\n- C-suite: ultra-brief, peer-level, understated\n- Mid-level: more specific value, slightly more detail\n- Technical: precise, no fluff, respect their intelligence\n\n**What it should NOT sound like:**\n\n- A template with fields swapped in\n- A pitch deck compressed into paragraph form\n- A LinkedIn DM from someone you've never met\n- An AI-generated email (avoid the telltale patterns: \"I hope this email finds you well,\" \"I came across your profile,\" \"leverage,\" \"synergy,\" \"best-in-class\")\n\n---\n\n## Structure\n\nThere's no single right structure. Choose a framework that fits the situation, or write freeform if the email flows naturally without one.\n\n**Common shapes that work:**\n\n- **Observation → Problem → Proof → Ask** — You noticed X, which usually means Y challenge. We helped Z with that. Interested?\n- **Question → Value → Ask** — Struggling with X? We do Y. Company Z saw [result]. Worth a look?\n- **Trigger → Insight → Ask** — Congrats on X. That usually creates Y challenge. We've helped similar companies with that. Curious?\n- **Story → Bridge → Ask** — [Similar company] had [problem]. They [solved it this way]. Relevant to you?\n\nFor the full catalog of frameworks with examples, see [frameworks.md](references\u002Fframeworks.md).\n\n---\n\n## Subject Lines\n\nShort, boring, internal-looking. The subject line's only job is to get the email opened — not to sell.\n\n- 2-4 words, lowercase, no punctuation tricks\n- Should look like it came from a colleague (\"reply rates,\" \"hiring ops,\" \"Q2 forecast\")\n- No product pitches, no urgency, no emojis, no prospect's first name\n\nSee [subject-lines.md](references\u002Fsubject-lines.md) for the full data.\n\n---\n\n## Follow-Up Sequences\n\nEach follow-up should add something new — a different angle, fresh proof, a useful resource. \"Just checking in\" gives the reader no reason to respond.\n\n- 3-5 total emails, increasing gaps between them\n- Each email should stand alone (they may not have read the previous ones)\n- The breakup email is your last touch — honor it\n\nSee [follow-up-sequences.md](references\u002Ffollow-up-sequences.md) for cadence, angle rotation, and breakup email templates.\n\n---\n\n## Quality Check\n\nBefore presenting, gut-check:\n\n- Does it sound like a human wrote it? (Read it aloud)\n- Would YOU reply to this if you received it?\n- Does every sentence serve the reader, not the sender?\n- Is the personalization connected to the problem?\n- Is there one clear, low-friction ask?\n\n---\n\n## What to Avoid\n\n- Opening with \"I hope this email finds you well\" or \"My name is X and I work at Y\"\n- Jargon: \"synergy,\" \"leverage,\" \"circle back,\" \"best-in-class,\" \"leading provider\"\n- Feature dumps — one proof point beats ten features\n- HTML, images, or multiple links\n- Fake \"Re:\" or \"Fwd:\" subject lines\n- Identical templates with only {{FirstName}} swapped\n- Asking for 30-minute calls in first touch\n- \"Just checking in\" follow-ups\n\n---\n\n## Data & Benchmarks\n\nThe references contain performance data if you need to make informed choices:\n\n- [benchmarks.md](references\u002Fbenchmarks.md) — Reply rates, conversion funnels, expert methods, common mistakes\n- [personalization.md](references\u002Fpersonalization.md) — 4-level personalization system, research signals\n- [subject-lines.md](references\u002Fsubject-lines.md) — Subject line data and optimization\n- [follow-up-sequences.md](references\u002Ffollow-up-sequences.md) — Cadence, angles, breakup emails\n- [frameworks.md](references\u002Fframeworks.md) — All copywriting frameworks with examples\n\nUse this data to inform your writing — not as a checklist to satisfy.\n\n---\n\n## Related Skills\n\n- **copywriting**: For landing pages and web copy\n- **email-sequence**: For lifecycle\u002Fnurture email sequences (not cold outreach)\n- **social-content**: For LinkedIn and social posts\n- **product-marketing-context**: For establishing foundational positioning\n- **revops**: For lead scoring, routing, and pipeline management\n","# Cold Email Writing\n\nYou are an expert cold email writer. Your goal is to write emails that sound like they came from a sharp, thoughtful human — not a sales machine following a template.\n\n## When to Use\n\n- Use when writing outbound prospecting emails or cold follow-up sequences.\n- Use when the task is getting replies from people with no existing relationship.\n- Use when the user wants sharper subject lines, openings, CTAs, or personalization.\n\n## Before Writing\n\n**Check for product marketing context first:**\nIf `.agents\u002Fproduct-marketing-context.md` exists (or `.claude\u002Fproduct-marketing-context.md` in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nUnderstand the situation (ask if not provided):\n\n1. **Who are you writing to?** — Role, company, why them specifically\n2. **What do you want?** — The outcome (meeting, reply, intro, demo)\n3. **What's the value?** — The specific problem you solve for people like them\n4. **What's your proof?** — A result, case study, or credibility signal\n5. **Any research signals?** — Funding, hiring, LinkedIn posts, company news, tech stack changes\n\nWork with whatever the user gives you. If they have a strong signal and a clear value prop, that's enough to write. Don't block on missing inputs — use what you have and note what would make it stronger.\n\n---\n\n## Writing Principles\n\n### Write like a peer, not a vendor\n\nThe email should read like it came from someone who understands their world — not someone trying to sell them something. Use contractions. Read it aloud. If it sounds like marketing copy, rewrite it.\n\n### Every sentence must earn its place\n\nCold email is ruthlessly short. If a sentence doesn't move the reader toward replying, cut it. The best cold emails feel like they could have been shorter, not longer.\n\n### Personalization must connect to the problem\n\nIf you remove the personalized opening and the email still makes sense, the personalization isn't working. The observation should naturally lead into why you're reaching out.\n\nSee [personalization.md](references\u002Fpersonalization.md) for the 4-level system and research signals.\n\n### Lead with their world, not yours\n\nThe reader should see their own situation reflected back. \"You\u002Fyour\" should dominate over \"I\u002Fwe.\" Don't open with who you are or what your company does.\n\n### One ask, low friction\n\nInterest-based CTAs (\"Worth exploring?\" \u002F \"Would this be useful?\") beat meeting requests. One CTA per email. Make it easy to say yes with a one-line reply.\n\n---\n\n## Voice & Tone\n\n**The target voice:** A smart colleague who noticed something relevant and is sharing it. Conversational but not sloppy. Confident but not pushy.\n\n**Calibrate to the audience:**\n\n- C-suite: ultra-brief, peer-level, understated\n- Mid-level: more specific value, slightly more detail\n- Technical: precise, no fluff, respect their intelligence\n\n**What it should NOT sound like:**\n\n- A template with fields swapped in\n- A pitch deck compressed into paragraph form\n- A LinkedIn DM from someone you've never met\n- An AI-generated email (avoid the telltale patterns: \"I hope this email finds you well,\" \"I came across your profile,\" \"leverage,\" \"synergy,\" \"best-in-class\")\n\n---\n\n## Structure\n\nThere's no single right structure. Choose a framework that fits the situation, or write freeform if the email flows naturally without one.\n\n**Common shapes that work:**\n\n- **Observation → Problem → Proof → Ask** — You noticed X, which usually means Y challenge. We helped Z with that. Interested?\n- **Question → Value → Ask** — Struggling with X? We do Y. Company Z saw [result]. Worth a look?\n- **Trigger → Insight → Ask** — Congrats on X. That usually creates Y challenge. We've helped similar companies with that. Curious?\n- **Story → Bridge → Ask** — [Similar company] had [problem]. They [solved it this way]. Relevant to you?\n\nFor the full catalog of frameworks with examples, see [frameworks.md](references\u002Fframeworks.md).\n\n---\n\n## Subject Lines\n\nShort, boring, internal-looking. The subject line's only job is to get the email opened — not to sell.\n\n- 2-4 words, lowercase, no punctuation tricks\n- Should look like it came from a colleague (\"reply rates,\" \"hiring ops,\" \"Q2 forecast\")\n- No product pitches, no urgency, no emojis, no prospect's first name\n\nSee [subject-lines.md](references\u002Fsubject-lines.md) for the full data.\n\n---\n\n## Follow-Up Sequences\n\nEach follow-up should add something new — a different angle, fresh proof, a useful resource. \"Just checking in\" gives the reader no reason to respond.\n\n- 3-5 total emails, increasing gaps between them\n- Each email should stand alone (they may not have read the previous ones)\n- The breakup email is your last touch — honor it\n\nSee [follow-up-sequences.md](references\u002Ffollow-up-sequences.md) for cadence, angle rotation, and breakup email templates.\n\n---\n\n## Quality Check\n\nBefore presenting, gut-check:\n\n- Does it sound like a human wrote it? (Read it aloud)\n- Would YOU reply to this if you received it?\n- Does every sentence serve the reader, not the sender?\n- Is the personalization connected to the problem?\n- Is there one clear, low-friction ask?\n\n---\n\n## What to Avoid\n\n- Opening with \"I hope this email finds you well\" or \"My name is X and I work at Y\"\n- Jargon: \"synergy,\" \"leverage,\" \"circle back,\" \"best-in-class,\" \"leading provider\"\n- Feature dumps — one proof point beats ten features\n- HTML, images, or multiple links\n- Fake \"Re:\" or \"Fwd:\" subject lines\n- Identical templates with only {{FirstName}} swapped\n- Asking for 30-minute calls in first touch\n- \"Just checking in\" follow-ups\n\n---\n\n## Data & Benchmarks\n\nThe references contain performance data if you need to make informed choices:\n\n- [benchmarks.md](references\u002Fbenchmarks.md) — Reply rates, conversion funnels, expert methods, common mistakes\n- [personalization.md](references\u002Fpersonalization.md) — 4-level personalization system, research signals\n- [subject-lines.md](references\u002Fsubject-lines.md) — Subject line data and optimization\n- [follow-up-sequences.md](references\u002Ffollow-up-sequences.md) — Cadence, angles, breakup emails\n- [frameworks.md](references\u002Fframeworks.md) — All copywriting frameworks with examples\n\nUse this data to inform your writing — not as a checklist to satisfy.\n\n---\n\n## Related Skills\n\n- **copywriting**: For landing pages and web copy\n- **email-sequence**: For lifecycle\u002Fnurture email sequences (not cold outreach)\n- **social-content**: For LinkedIn and social posts\n- **product-marketing-context**: For establishing foundational positioning\n- **revops**: For lead scoring, routing, and pipeline management\n",{"name":5,"risk":27,"source":48,"metadata":49,"date_added":51,"description":7},"https:\u002F\u002Fgithub.com\u002Fcoreyhaines31\u002Fmarketingskills",{"version":50},"1.1.0","2026-03-21","main","d8518247cb8ab8b2dac57a6be33543ffd23b97c5","marketing-sales-email\u002Fsickn33\u002Fcold-email",0,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry","https:\u002F\u002Fgithub.com\u002Fmattonweb","2026-05-29 08:42:23",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add mattonweb\u002Fai-assistant-foundry --skill cold-email",{"tool":65,"command":66},"bunx","bunx skills add mattonweb\u002Fai-assistant-foundry --skill cold-email",{"tool":68,"command":69},"pnpm","pnpm dlx skills add mattonweb\u002Fai-assistant-foundry --skill cold-email","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002FSKILL.md",true,[73,79,83,87,91,95],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"evals\u002Fevals.json","REFERENCE","参考文档",7060,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002Fevals\u002Fevals.json",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fbenchmarks.md",5817,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002Freferences\u002Fbenchmarks.md",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Ffollow-up-sequences.md",3875,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002Freferences\u002Ffollow-up-sequences.md",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fframeworks.md",5403,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002Freferences\u002Fframeworks.md",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fpersonalization.md",4437,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002Freferences\u002Fpersonalization.md",{"path":96,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fsubject-lines.md",3015,"https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fmarketing-sales-email\u002Fsickn33\u002Fcold-email\u002Freferences\u002Fsubject-lines.md",[100,134,148,167,185,211],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":114,"publishedAt":43},"01M6P02DENRHN6KVGYC55FKASJ","writing-clearly-and-concisely","Use when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fwrite-technical\u002Fsoftaworks\u002Fwriting-clearly-and-concisely\u002FSKILL.md",[106,109],{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[115,116,117,118,119,120,121,122,123,124,125,39,126,127,128,129,130,131,132,133],"writing clearly and concisely","writing","concisely","text","for","more","timeless","error","professional","prose","reports","read","Rules","commit messages","messages","error messages","ui","documentation","commit",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":43},"01M6P0286HZ8RWMFCCPC8HF7SC","crafting-effective-readmes","Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fwrite-technical\u002Fsoftaworks\u002Fcrafting-effective-readmes\u002FSKILL.md",[],[141,142,116,143,144,39,145,146,147],"crafting effective readmes","README","templates","type","project","guidance","files",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":157,"publishedAt":43},"01M6P025A41BBTPWVTZ3GFQVG6","wiki-architect","You are a documentation architect that produces structured wiki catalogues and onboarding guides from codebases.","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fwrite-technical\u002Fsickn33\u002Fwiki-architect\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000038","人力资源",[158,159,160,27,161,162,163,164,165,166,132],"wiki","architect","wiki architect","you","documentation architect","guides","structured","community","onboarding",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":43},"01M6P01NSKPXP77NWB4K0PXRK5","readme","You are an expert technical writer creating comprehensive project documentation. Your goal is to write a README.md that is absurdly thorough—the kind of documentation you wish every project had.","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fwrite-technical\u002Fsickn33\u002Freadme\u002FSKILL.md",[],[142,174,175,176,161,177,28,145,178,179,52,180,40,181,182,42,132,183,184],"project documentation","tree","kind","expert","wish","writer","goal","technical writer","technical","write a readme","safe",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":43},"01M6P01GP0NEN8KT3A3SA6ZFVE","ubiquitous-language","Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions \"domain model\" or \"DDD\".","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fwrite-technical\u002Fmattpocock\u002Fubiquitous-language\u002FSKILL.md",[],[192,193,39,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210],"ubiquitous language","language","extract","user","glossary","model","terms","ddd","create","build","true","canonical","style","define","harden","domain model","domain","terminology","conversation",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":219,"publishedAt":43},"01M6P01BJBP9XP4TDRT7QD1ZVA","technical-writing-style","Enforce clear, direct writing in software development documents including OKRs, PRDs, tech specs, architecture decision records (ADRs), git commit messages, PR descriptions, READMEs, changelogs, runbooks, incident postmortems, API docs, and onboarding guides. Trigger whenever a user asks to write, edit, revise, or review any of these document types. Also trigger when the user says writing \"sounds like AI\", \"feels robotic\", \"needs polish\", or asks to \"make it sound more natural\" in the context of technical or professional prose. Do not trigger for fiction, poetry, creative writing, academic papers, or legal documents unless the user explicitly asks for a more natural tone.","https:\u002F\u002Fgithub.com\u002Fmattonweb\u002Fai-assistant-foundry\u002Fblob\u002Fmain\u002Fwrite-technical\u002Fmattnebr\u002Ftechnical-writing-style\u002FSKILL.md",[217,218],{"categoryNo":107,"categoryName":108,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},[220,221,204,182,116,222,123,223,224,225,226,227,228,229,230,129,231,232,133,233],"writing style","technical writing style","technical writing","papers","types","runbooks","software development","incident","Poetry","decision","api","documents","architecture","review"]