[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H83M1PXPVWSP2FND6YMANS":3,"skill-same:01M6H83M1PXPVWSP2FND6YMANS":69},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6H83M1PXPVWSP2FND6YMANS","find-skills",null,"Not for building skills — for finding them. Use when the intent is to discover, search, or inventory what agent skills already exist for a topic. The user wants to know \"what's out there for X\" rather than \"make me something.\" Triggers on: \"find a skill for X\", \"skill search: X\", \"what skills exist for X\", \"discover skills for X\", \"is there already a skill for X\", \"before I build this, has someone done it?\", or any pre-build audit. Also trigger proactively before any skill-creator session when the user hasn't searched yet — finding what exists prevents duplicate effort. Output is a ranked table plus a thematic synthesis document, never a new skill.","O-Marsters-1997\u002Fmy-claude-code","O-Marsters-1997","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72571979?v=4","01M6H800V7V9BSXYZKDM0JXTJ2","Olly Marsters","01M6H800ZYDJR42TNRH0E6ZVZ7",0,"MIT","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fmeta\u002Ffind-skills\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"find","find skills","me","new","when","skill-creator","for","discover skills","building skills","output","duplicate","trigger","triggers","discover","done","intent","build","document","never","use","session","inventory","search","2026-11-10 10:12:30",false,"---\nname: find-skills\ndescription: >\n  Not for building skills — for finding them. Use when the intent is to discover, search,\n  or inventory what agent skills already exist for a topic. The user wants to know \"what's\n  out there for X\" rather than \"make me something.\" Triggers on: \"find a skill for X\",\n  \"skill search: X\", \"what skills exist for X\", \"discover skills for X\", \"is there already\n  a skill for X\", \"before I build this, has someone done it?\", or any pre-build audit.\n  Also trigger proactively before any skill-creator session when the user hasn't searched\n  yet — finding what exists prevents duplicate effort. Output is a ranked table plus a\n  thematic synthesis document, never a new skill.\n---\n\n# Find Skills\n\nYou've been asked to find existing skills relevant to a description. Search the sources below in order, rank by relevance and quality, produce a discovery document, then hand off to skill-creator on confirmation.\n\n## Sources\n\nWork through these in order — earlier sources carry richer quality signals:\n\n| # | Source | How |\n|---|--------|-----|\n| 1 | **skills.sh** (SkillsMP) | Fetch `https:\u002F\u002Fskills.sh\u002F` and search the leaderboard; this is the primary marketplace with install counts |\n| 2 | **Skills CLI** | Run `bunx skills find {keywords}` (fall back to `npx skills find {keywords}` if Bun isn't available) |\n| 3 | **GitHub code search** | `WebSearch` for `site:github.com filename:SKILL.md {keywords}` — finds skills not yet in the marketplace |\n| 4 | **GitHub collections** | `WebSearch` known skill collections: `ComposioHQ\u002Fawesome-claude-skills`, `vercel-labs\u002Fagent-skills`, `xixu-me\u002Fskills`, `openai\u002Fskills` |\n| 5 | **Local** | Scan installed skills in `~\u002F.claude\u002Fskills\u002F`, `.claude\u002Fskills\u002F`, and the project's `skills\u002F` directory |\n\nFrom each skill found, extract:\n- **name** — skill identifier from frontmatter\n- **author** — publisher, GitHub org, or username\n- **url** — skills.sh page or direct link to SKILL.md\n- **installs** — from skills.sh if available, otherwise N\u002FA\n- **description** — one sentence from frontmatter `description:` field\n\n## Quality signals\n\nUse these to rank, not to hard-exclude:\n- **Install count** — prefer 1K+; flag anything under 100 as low-confidence\n- **Publisher reputation** — known publishers (vercel-labs, anthropics, openai, microsoft, xixu-me) rank higher\n- **Repository quality** — check GitHub stars; treat skills from repos with \u003C100 stars with skepticism\n\nA niche but highly relevant skill from a small repo beats a popular but off-topic one.\n\n## Ranking\n\nScore each candidate against the user's description. Weight:\n1. Relevance to the task domain (highest weight)\n2. Quality signals above\n3. Breadth — broader coverage is more reusable\n\nPick the top 10. If fewer than 10 exist, include all.\n\n## Output\n\n### 1. Write the discovery document\n\nWrite to `.\u002Fdocs\u002Fskill-discovery.md` (create `.\u002Fdocs\u002F` if needed):\n\n```markdown\n# Skill Discovery: {user's description}\n\n_Sources: skills.sh · Skills CLI · GitHub code search · GitHub collections · Local_  \n_Add comments anywhere in this file, then reply \"build it\" to proceed._\n\n---\n\n## Top 10 Relevant Skills\n\n| # | Skill | Author | Source | Installs | Description |\n|---|-------|--------|--------|----------|-------------|\n| 1 | [skill-name](url) | Author | skills.sh \u002F GitHub \u002F Local | 12K \u002F N\u002FA | One sentence |\n...\n\n---\n\n## Synthesis\n\n[3–5 thematic paragraphs in the style of a literature review. Group skills by what they\nemphasise rather than listing them one by one. Note variation in approach, scope, or\nworkflow philosophy across the set. Write in flowing prose — no sub-headers, no bullets,\nno gaps or recommendation section. The goal is a readable overview of the landscape.]\n\n---\n\n## Your notes\n\n\u003C!-- Add comments here, or inline above any row in the table -->\n_Nothing yet._\n```\n\n### 2. Tell the user\n\n- Confirm the file was saved\n- Name the top 3 picks with one sentence each in the conversation\n- Say: \"Full table and synthesis in `.\u002Fdocs\u002Fskill-discovery.md` — add notes directly there, then reply **build it** to hand off to skill-creator.\"\n\n## On confirmation\n\nWhen the user replies \"build it\" (or equivalent):\n\n1. Re-read `.\u002Fdocs\u002Fskill-discovery.md` to pick up any notes they added\n2. Build a skill-creator prompt from:\n   - The original description\n   - Patterns and approaches from the synthesis worth borrowing\n   - Specific techniques to adopt, with source URLs\n   - Any user notes from the document\n\nHandoff prompt structure:\n```\nBuild a skill for: {description}\n\nPatterns worth borrowing from existing skills:\n- {pattern} — from [{skill-name}]({url})\n\nUser notes: {anything from the discovery document}\n```\n\n3. Invoke `\u002Fskill-creator` with that prompt.\n\n## What not to do\n\n- Don't skip skills.sh — install counts are the strongest signal of real-world adoption.\n- Don't run `bunx skills add` — this skill only discovers; the user decides what to install.\n- Don't fabricate URLs — if a URL can't be confirmed, mark it `(unverified)`.\n- Don't make the synthesis a disguised bullet list or a rehash of the table — it should surface patterns that only emerge when you read the skills as a set.\n","# Find Skills\n\nYou've been asked to find existing skills relevant to a description. Search the sources below in order, rank by relevance and quality, produce a discovery document, then hand off to skill-creator on confirmation.\n\n## Sources\n\nWork through these in order — earlier sources carry richer quality signals:\n\n| # | Source | How |\n|---|--------|-----|\n| 1 | **skills.sh** (SkillsMP) | Fetch `https:\u002F\u002Fskills.sh\u002F` and search the leaderboard; this is the primary marketplace with install counts |\n| 2 | **Skills CLI** | Run `bunx skills find {keywords}` (fall back to `npx skills find {keywords}` if Bun isn't available) |\n| 3 | **GitHub code search** | `WebSearch` for `site:github.com filename:SKILL.md {keywords}` — finds skills not yet in the marketplace |\n| 4 | **GitHub collections** | `WebSearch` known skill collections: `ComposioHQ\u002Fawesome-claude-skills`, `vercel-labs\u002Fagent-skills`, `xixu-me\u002Fskills`, `openai\u002Fskills` |\n| 5 | **Local** | Scan installed skills in `~\u002F.claude\u002Fskills\u002F`, `.claude\u002Fskills\u002F`, and the project's `skills\u002F` directory |\n\nFrom each skill found, extract:\n- **name** — skill identifier from frontmatter\n- **author** — publisher, GitHub org, or username\n- **url** — skills.sh page or direct link to SKILL.md\n- **installs** — from skills.sh if available, otherwise N\u002FA\n- **description** — one sentence from frontmatter `description:` field\n\n## Quality signals\n\nUse these to rank, not to hard-exclude:\n- **Install count** — prefer 1K+; flag anything under 100 as low-confidence\n- **Publisher reputation** — known publishers (vercel-labs, anthropics, openai, microsoft, xixu-me) rank higher\n- **Repository quality** — check GitHub stars; treat skills from repos with \u003C100 stars with skepticism\n\nA niche but highly relevant skill from a small repo beats a popular but off-topic one.\n\n## Ranking\n\nScore each candidate against the user's description. Weight:\n1. Relevance to the task domain (highest weight)\n2. Quality signals above\n3. Breadth — broader coverage is more reusable\n\nPick the top 10. If fewer than 10 exist, include all.\n\n## Output\n\n### 1. Write the discovery document\n\nWrite to `.\u002Fdocs\u002Fskill-discovery.md` (create `.\u002Fdocs\u002F` if needed):\n\n```markdown\n# Skill Discovery: {user's description}\n\n_Sources: skills.sh · Skills CLI · GitHub code search · GitHub collections · Local_  \n_Add comments anywhere in this file, then reply \"build it\" to proceed._\n\n---\n\n## Top 10 Relevant Skills\n\n| # | Skill | Author | Source | Installs | Description |\n|---|-------|--------|--------|----------|-------------|\n| 1 | [skill-name](url) | Author | skills.sh \u002F GitHub \u002F Local | 12K \u002F N\u002FA | One sentence |\n...\n\n---\n\n## Synthesis\n\n[3–5 thematic paragraphs in the style of a literature review. Group skills by what they\nemphasise rather than listing them one by one. Note variation in approach, scope, or\nworkflow philosophy across the set. Write in flowing prose — no sub-headers, no bullets,\nno gaps or recommendation section. The goal is a readable overview of the landscape.]\n\n---\n\n## Your notes\n\n\u003C!-- Add comments here, or inline above any row in the table -->\n_Nothing yet._\n```\n\n### 2. Tell the user\n\n- Confirm the file was saved\n- Name the top 3 picks with one sentence each in the conversation\n- Say: \"Full table and synthesis in `.\u002Fdocs\u002Fskill-discovery.md` — add notes directly there, then reply **build it** to hand off to skill-creator.\"\n\n## On confirmation\n\nWhen the user replies \"build it\" (or equivalent):\n\n1. Re-read `.\u002Fdocs\u002Fskill-discovery.md` to pick up any notes they added\n2. Build a skill-creator prompt from:\n   - The original description\n   - Patterns and approaches from the synthesis worth borrowing\n   - Specific techniques to adopt, with source URLs\n   - Any user notes from the document\n\nHandoff prompt structure:\n```\nBuild a skill for: {description}\n\nPatterns worth borrowing from existing skills:\n- {pattern} — from [{skill-name}]({url})\n\nUser notes: {anything from the discovery document}\n```\n\n3. Invoke `\u002Fskill-creator` with that prompt.\n\n## What not to do\n\n- Don't skip skills.sh — install counts are the strongest signal of real-world adoption.\n- Don't run `bunx skills add` — this skill only discovers; the user decides what to install.\n- Don't fabricate URLs — if a URL can't be confirmed, mark it `(unverified)`.\n- Don't make the synthesis a disguised bullet list or a rehash of the table — it should surface patterns that only emerge when you read the skills as a set.\n",{"name":5,"description":7},"main","aede9f7bc29a2d9127fa7ce29682c242596c7759","skills\u002Fmeta\u002Ffind-skills","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997","https:\u002F\u002Fpersonal-portfolio-v2-phi.vercel.app","Go & TypeScript developer building tooling for AI-assisted development: git worktree workflows, Claude Code skills and agent orchestration.","2026-11-11 22:26:34",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add O-Marsters-1997\u002Fmy-claude-code --skill find-skills",{"tool":61,"command":62},"bunx","bunx skills add O-Marsters-1997\u002Fmy-claude-code --skill find-skills",{"tool":64,"command":65},"pnpm","pnpm dlx skills add O-Marsters-1997\u002Fmy-claude-code --skill find-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fmeta\u002Ffind-skills\u002FSKILL.md",true,[],[70,78,85,111,138,164],{"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":77},"01M745F5J4Z2W32G4QXESCN5PM","vault-recall","Answer the user's conceptual or technical question using their Obsidian vault as well as general knowledge. Use when the user asks a question (not a task) whose topic appears in the vault MOC digest from session start. Not for task instructions, not mid-task, and not for writing to the vault (that is to-vault).","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fvault-recall\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":77},"01M745EW5W0A7K9016Z54A4KG2","ingest","Ingest one external source (an article, course lesson, doc, PDF or URL) into the user's Obsidian vault: save the original to raw\u002F, then build wiki\u002F pages per the vault's § Ingest. Use when the user types \u002Fingest, or says \"ingest this\", \"add this source to my wiki\", \"put this article\u002Flesson in the vault as a wiki page\". Works from any repo. Routing rule: someone else's words go to wiki\u002F (this skill); the user's own learnings and decisions go to notes\u002F (\u002Fto-vault).","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fproductivity\u002Fingest\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":42},"01M6H88J6TYRV9T8RKWW569YM8","to-tickets","Breaks a source into independently-grabbable GitHub tickets. For a code feature the source is the plan (`docs\u002Fplans\u002F\u003Cfeature>.md`, from \u002Fto-plan) and every new or changed symbol lands in exactly one ticket, its signatures copied into the ticket body; a non-code feature is cut from the PRD's slices. Cuts tickets for one feature per run. If a code feature has no approved plan, offers \u002Fto-plan instead of cutting from prose. In a repo that runs command-centre, also emits `[[task]]` blocks into its config; in a plain treepad repo, emits a Batch Manifest instead so the tickets materialise as stacked worktrees.","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Fto-tickets\u002FSKILL.md",[],[92,93,22,94,95,96,97,98,99,100,101,102,103,104,105,25,106,107,108,109,110],"tickets","to tickets","signatures","github","plan","batch","task","code","manifest","plans","true","ticket","command","repo","feature","run","worktrees","as","cut",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":122,"publishedAt":42},"01M6H88E98X9KGGYBGSVDS1E8H","to-seams","Records an agreed-but-unlanded cross-repo interface as a seam: the file a consumer's agent gets pasted into its prompt as ground truth, plus the `[[seam]]` block command-centre reads for the retirement pointer. Use when two repos need to build against an interface neither has landed yet — \"record a seam for X\", \"we agreed on this schema, seam it\", \"add a seam so Y can build against Z's new field\". Halts for approval before writing either file.","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Fto-seams\u002FSKILL.md",[117],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[123,124,22,125,126,127,128,129,130,38,131,23,132,102,133,134,135,105,25,35,136,137,109,104],"to seams","schema","neither","it","but","file","prompt","either","writing","interface","repos","block","records","can","record",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":149,"publishedAt":42},"01M6H889PSQM2E1ATS2JC10QRV","to-roadmap","Prioritises settled features into a Now \u002F Next \u002F Later kanban board, rendered as a self-contained .\u002Fideas\u002Froadmap.html. Each card is a feature, not a ticket — one card later becomes several tickets via \u002Fto-prd -> \u002Fto-plan -> \u002Fto-tickets. Boards the features in .\u002Fdocs\u002Fapproach.md, or the \"## Accepted ideas\" in .\u002Fideas\u002FCONTEXT.md when there is no approach doc. The approach doc is settled truth: this assigns tiers and reasons about ordering, it never re-litigates what was decided.","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Fto-roadmap\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[150,151,37,109,106,152,153,23,154,155,156,92,157,158,96,159,160,102,103,161,162,163],"to roadmap","roadmap","via","features","doc","board","about","next","later","self","now","card","re","ideas",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":42},"01M6H885QAK839Q771ZBKBK1KA","to-prd","Turns one feature idea into a PRD built on journeys: a one-line problem, journeys (each ending in an observable state) and delivery slices that say what is usable after each. Interviews, explores the codebase, and saves to docs\u002Fprds\u002F\u003Cfeature>.md. Covers exactly one feature: given a multi-feature source, ask which one. Reads any approach doc or ideate report as priors so it doesn't re-ask what's settled, but needs none. Starts the per-feature spine (\u002Fto-prd -> \u002Fto-plan -> \u002Fto-tickets).","https:\u002F\u002Fgithub.com\u002FO-Marsters-1997\u002Fmy-claude-code\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002Fto-prd\u002FSKILL.md",[170],{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},[172,173,174,175,176,177,178,179,92,180,96,181,182,183,102,162,106,184,185,109],"prd","to prd","say","interviews","codebase","report","line","delivery","spine","state","multi","ask","problem","which"]