[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B2SEVCQCSE5RRWSM40D77W":3,"skill-same:01M7B2SEVCQCSE5RRWSM40D77W":55},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7B2SEVCQCSE5RRWSM40D77W","authoring-skills-from-scratch",null,"Guides users through writing a strong skill: trigger conditions, core guidance, examples, anti-patterns.","gethamster\u002Fskills","gethamster","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F215697643?v=4","01M7B2R6PGB3SDZZ71E0WE2S74","Hamster","01M7B2R6Q21HWJRXZZWB78BNDG",4,"MIT","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.experimental\u002Fauthoring-skills-from-scratch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: authoring-skills-from-scratch\ndescription: \"Guides users through writing a strong skill: trigger conditions, core guidance, examples, anti-patterns.\"\nversion: \"1.0.0\"\ncategory: \"Ops\"\n---\n\n# Authoring Skills from Scratch\n\nA skill is behavioral guidance for the AI harness — domain-specific instructions loaded into context to shape how the harness approaches specific types of work.\n\n## What makes a strong skill?\n\n**When to use** — Trigger conditions: what types of tasks or code patterns activate this skill. Good: \"When creating or reviewing feature flags in PostHog or code.\" Bad: \"When working on the backend.\"\n\n**Core guidance** — Behavioral rules the harness should follow. Prescriptive, not suggestive. Good: \"Flag names follow the pattern `feature_\u003Cname>_\u003Cvariant>`.\" Bad: \"Consider using a consistent naming pattern.\"\n\n**Concrete examples** — Real code or configuration showing the pattern in action. 2–3 examples minimum. Good: `feature_passwordless_auth_alpha`. Bad: No examples, only prose.\n\n**Anti-patterns** — What NOT to do, with explanations of why. Often more valuable than positive guidance. Good: \"`ff_auth_v2` — too cryptic, doesn't follow naming pattern.\" Bad: Omitted.\n\n## How to write one\n\n1. **Define trigger conditions first:** What types of tasks or code patterns should activate this skill? Be specific — name the tools, file paths, or task types.\n2. **Write core guidance as prescriptive rules:** \"Always do X\" is better than \"consider doing X.\" Each rule should be a single, testable instruction.\n3. **Add 2–3 concrete examples:** Show the pattern in real code or configuration. Examples should be copy-pasteable and recognizable.\n4. **Document anti-patterns:** What should the harness NOT do? Why? For each anti-pattern, explain the failure mode it prevents.\n5. **Test the skill:** Load it and give the harness a task that should trigger it. Does it follow the guidance? If not, tighten the trigger conditions or rules.\n\nKeep the skill under ~2000 words. If it exceeds that, it's probably covering multiple domains — split it.\n\n## Common mistakes\n\n- Too long, covering multiple domains. A skill for \"all of backend development\" is too broad; create separate skills for \"NestJS patterns,\" \"BullMQ job queues,\" etc.\n- Vague guidance. \"Consider\" and \"think about\" are not instructions. Use \"always,\" \"never,\" \"must.\"\n- No examples. Without concrete examples, the harness applies the rules inconsistently.\n- Duplicating blueprint content. Skills guide behavior; blueprints describe state. A skill says \"follow this pattern when writing API routes.\" A blueprint says \"our API routes use this pattern because we decided X.\"\n- No trigger conditions. Without triggers, the harness doesn't know when to load the skill.\n\n## Prompts to get unstuck\n\n- \"What tasks should activate this skill?\"\n- \"What's the one rule the harness must follow?\"\n- \"Show me a real example of this pattern.\"\n- \"What mistake does the harness make without this skill?\"\n","# Authoring Skills from Scratch\n\nA skill is behavioral guidance for the AI harness — domain-specific instructions loaded into context to shape how the harness approaches specific types of work.\n\n## What makes a strong skill?\n\n**When to use** — Trigger conditions: what types of tasks or code patterns activate this skill. Good: \"When creating or reviewing feature flags in PostHog or code.\" Bad: \"When working on the backend.\"\n\n**Core guidance** — Behavioral rules the harness should follow. Prescriptive, not suggestive. Good: \"Flag names follow the pattern `feature_\u003Cname>_\u003Cvariant>`.\" Bad: \"Consider using a consistent naming pattern.\"\n\n**Concrete examples** — Real code or configuration showing the pattern in action. 2–3 examples minimum. Good: `feature_passwordless_auth_alpha`. Bad: No examples, only prose.\n\n**Anti-patterns** — What NOT to do, with explanations of why. Often more valuable than positive guidance. Good: \"`ff_auth_v2` — too cryptic, doesn't follow naming pattern.\" Bad: Omitted.\n\n## How to write one\n\n1. **Define trigger conditions first:** What types of tasks or code patterns should activate this skill? Be specific — name the tools, file paths, or task types.\n2. **Write core guidance as prescriptive rules:** \"Always do X\" is better than \"consider doing X.\" Each rule should be a single, testable instruction.\n3. **Add 2–3 concrete examples:** Show the pattern in real code or configuration. Examples should be copy-pasteable and recognizable.\n4. **Document anti-patterns:** What should the harness NOT do? Why? For each anti-pattern, explain the failure mode it prevents.\n5. **Test the skill:** Load it and give the harness a task that should trigger it. Does it follow the guidance? If not, tighten the trigger conditions or rules.\n\nKeep the skill under ~2000 words. If it exceeds that, it's probably covering multiple domains — split it.\n\n## Common mistakes\n\n- Too long, covering multiple domains. A skill for \"all of backend development\" is too broad; create separate skills for \"NestJS patterns,\" \"BullMQ job queues,\" etc.\n- Vague guidance. \"Consider\" and \"think about\" are not instructions. Use \"always,\" \"never,\" \"must.\"\n- No examples. Without concrete examples, the harness applies the rules inconsistently.\n- Duplicating blueprint content. Skills guide behavior; blueprints describe state. A skill says \"follow this pattern when writing API routes.\" A blueprint says \"our API routes use this pattern because we decided X.\"\n- No trigger conditions. Without triggers, the harness doesn't know when to load the skill.\n\n## Prompts to get unstuck\n\n- \"What tasks should activate this skill?\"\n- \"What's the one rule the harness must follow?\"\n- \"Show me a real example of this pattern.\"\n- \"What mistake does the harness make without this skill?\"\n",{"name":5,"version":24,"category":25,"description":7},"1.0.0","Ops","main","fe3bb1476c3ec23d8a366eac0fa8cd9f0852360a","skills\u002F.experimental\u002Fauthoring-skills-from-scratch",0,"https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills","https:\u002F\u002Fgithub.com\u002Fgethamster","https:\u002F\u002Ftryhamster.com","We're building the AI-native future of work, unlocking the promised acceleration for your whole team, from idea to impact.","2026-11-05 11:33:33",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add gethamster\u002Fskills --skill authoring-skills-from-scratch",{"tool":41,"command":42},"bunx","bunx skills add gethamster\u002Fskills --skill authoring-skills-from-scratch",{"tool":44,"command":45},"pnpm","pnpm dlx skills add gethamster\u002Fskills --skill authoring-skills-from-scratch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.experimental\u002Fauthoring-skills-from-scratch\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"notes\u002Fauthoring-skills.md","REFERENCE","参考文档",4046,"https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002F.experimental\u002Fauthoring-skills-from-scratch\u002Fnotes\u002Fauthoring-skills.md",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7B5MWYW0KE251276S56KQDZ","writing-waterfall-requirements-documents","Write a waterfall requirements document: elicit, structure and review testable, traceable requirements, then baseline the specification before design.","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-waterfall-requirements-documents\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7B5MRCXWWPKREPB1CHQ7H90","writing-vision-and-values-statements","Write a V2MOM vision a reader can test and a ranked list of values that settles real tradeoffs, so the rest of the document has a clear anchor.","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-vision-and-values-statements\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7B5MKH2CH22YZAHQW3080VQ","writing-system-prompts-for-claude","Write Claude prompts and CLAUDE.md files that supply exact inputs, scope the task, and define done so the first attempt can be checked.","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-system-prompts-for-claude\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7B5ME1Y3X9RNRKP5HKHKACZ","writing-page-specific-website-copy","Website copywriting by page type: write homepage, landing page, pricing page and feature page copy that fits each page's visitor and single job.","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-page-specific-website-copy\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7B5M8MQNM8MN8PYH6BVWJ2B","writing-internal-press-releases","How to write an internal press release: the one-page working backwards press release that opens a PR\u002FFAQ document before anything is built.","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-internal-press-releases\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7B5M3P3YH1XF37R8PWXXSBK","writing-email-sequences-that-sell","Email sequence copywriting for nurture and sales: give each email one job, write clear subject lines, and close with one specific call to action.","https:\u002F\u002Fgithub.com\u002Fgethamster\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-email-sequences-that-sell\u002FSKILL.md",[],[]]