[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70P13NB9YP7ACJR1S861CDS":3,"skill-same:01M70P13NB9YP7ACJR1S861CDS":87},{"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":28,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M70P13NB9YP7ACJR1S861CDS","zread",null,"Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `.\u002F.zread\u002Fwiki\u002F`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module\u002Fpackage explanations, or \"what does this repo do\"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread \u002F zread.ai directly. Also use it proactively before diving into a large unknown repo — if `.\u002F.zread\u002Fwiki\u002Fcurrent` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word \"zread\".","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[5,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"knowledge","project wiki","unknown","get","project","knowledge base","map","intent","generated","cli","explore","wiki","walkthrough","disk","code","run","generate","documentation","architecture","2026-11-10 10:12:30",false,"---\nname: zread\ndescription: Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `.\u002F.zread\u002Fwiki\u002F`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module\u002Fpackage explanations, or \"what does this repo do\"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread \u002F zread.ai directly. Also use it proactively before diving into a large unknown repo — if `.\u002F.zread\u002Fwiki\u002Fcurrent` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word \"zread\".\n---\n\n# zread skill\n\n`zread` is a CLI that generates wiki documentation from code in the current\nworkspace using an LLM. Output lives under `.\u002F.zread\u002Fwiki\u002F` in the workspace;\npublic repos can also be viewed at https:\u002F\u002Fzread.ai.\n\nThis skill is intended for agent use. Read generated files directly from disk,\nand use `--stdio` as the default mode for any zread command instead of trying\nto parse the human TUI.\n\n## On-disk layout (read these directly)\n\nAlways run `zread` from the workspace root. After a successful generation:\n\n- `.\u002F.zread\u002Fwiki\u002Fcurrent` — text file containing the active version id\n  (e.g. `2026-03-12-010203`).\n- `.\u002F.zread\u002Fwiki\u002Fversions\u002F\u003Cid>\u002Fwiki.json` — TOC: `{id, generated_at, language,\n  pages: [{slug, title, file, section, group, level}]}`.\n- `.\u002F.zread\u002Fwiki\u002Fversions\u002F\u003Cid>\u002F\u003Cfile>` — page markdown referenced by `pages[*].file`.\n- `.\u002F.zread\u002Fwiki\u002Fdrafts\u002F` — in-progress generation; presence means a previous\n  run did not finish. `drafts\u002Fwiki.json` exists once the catalog phase\n  completed.\n- `~\u002F.zread\u002Fconfig.yaml` — global config (LLM provider, language, concurrency).\n- `~\u002F.zread\u002Flogin.json` — presence indicates the user has logged in.\n\nTo answer questions about a codebase that already has zread output, read these\nfiles directly with the file tools — do not invoke `zread browse`.\n\n## Commands\n\n| Command | Purpose | Key flags |\n|---|---|---|\n| `zread generate` | Generate wiki for cwd | `-y\u002F--yes`, `--draft resume\\|clear\\|cancel`, `--skip-failed`, `--stdio` |\n| `zread browse` | Serve docs at http:\u002F\u002Flocalhost:9681+ and open browser | `--generate`, `--version \u003Cid>`, `--host`, `--port`, `--stdio` |\n| `zread login` | OAuth into BigModel\u002FZ.AI to obtain an API key | `--custom`, `--model`, `--stdio` |\n| `zread config` | Edit `~\u002F.zread\u002Fconfig.yaml` | `--stdio` |\n| `zread update` | Self-update CLI | `--stdio` |\n| `zread version` | Print version | `--stdio` |\n\n`--stdio` is supported on every command and turns the process into a JSON-line\nmachine protocol on stdin\u002Fstdout. See\n[references\u002Fstdio-protocol.md](.\u002Freferences\u002Fstdio-protocol.md) for the wire\nformat (events, `waiting_for`, `done`, `quit`). Load it whenever zread is\ninvoked from another program\u002Fagent.\n\n## Decision tree for an AI agent\n\n1. **User wants to read existing wiki content?**\n   - Check `.\u002F.zread\u002Fwiki\u002Fcurrent`. If present, read `wiki.json` and the page\n     markdown directly. No CLI invocation needed.\n   - For known *public* GitHub repos, prefer the `mcp__zread__*` tools\n     (`get_repo_structure`, `read_file`, `search_doc`) over running the CLI.\n\n2. **User wants to (re)generate docs?**\n   - Confirm with the user first — `generate` is long-running, calls an LLM,\n     and writes files. Get explicit consent in unfamiliar directories.\n   - Verify `~\u002F.zread\u002Flogin.json` exists or `~\u002F.zread\u002Fconfig.yaml` has an\n     `llm.api_key`. If neither, run `zread login` first.\n   - If `.\u002F.zread\u002Fwiki\u002Fdrafts\u002F` exists, decide:\n     - resume previous run → `zread generate --draft resume -y`\n     - throw away and start fresh → `zread generate --draft clear -y`\n   - Otherwise: `zread generate -y`.\n   - To not block on a few failing pages: add `--skip-failed`.\n\n3. **User wants to view docs in a browser?**\n   - `zread browse` (add `--generate` to bootstrap if no wiki exists yet).\n\n4. **User wants to script zread \u002F consume output programmatically?**\n   - Use `--stdio` and follow stdio-protocol.md. Do not screen-scrape the TUI.\n\n## Non-interactive invocation rules\n\n- Always pass `-y` to `generate` when running unattended; otherwise it stops\n  at a catalog confirmation gate.\n- Always set `--draft` explicitly when a draft may exist, so the command does\n  not prompt.\n- For any command run from another agent\u002Fscript, use `--stdio` so output is\n  parseable JSON instead of ANSI TUI frames.\n- `zread` writes logs to `~\u002F.zread\u002Flog\u002Fzread.log` — read this if a run fails\n  silently.\n\n## Safety \u002F blast radius\n\n- `generate` consumes LLM tokens (real cost) and can run for many minutes on\n  large repos. Confirm before launching.\n- `generate` writes only under `.\u002F.zread\u002F` and does not commit anything to\n  git. It is safe to delete `.\u002F.zread\u002Fwiki\u002Fdrafts\u002F` to recover from a stuck\n  state.\n- `update` replaces the zread binary in place and is hard to reverse — only\n  run it when the user explicitly asks.\n- `login` opens a browser for OAuth; do not run it in a non-interactive\n  context unless the user has asked for it.\n\n## Reference files\n\n- [references\u002Fstdio-protocol.md](.\u002Freferences\u002Fstdio-protocol.md) — JSON-line\n  wire protocol shared by every command's `--stdio` mode. Load when\n  programmatically driving zread.\n","# zread skill\n\n`zread` is a CLI that generates wiki documentation from code in the current\nworkspace using an LLM. Output lives under `.\u002F.zread\u002Fwiki\u002F` in the workspace;\npublic repos can also be viewed at https:\u002F\u002Fzread.ai.\n\nThis skill is intended for agent use. Read generated files directly from disk,\nand use `--stdio` as the default mode for any zread command instead of trying\nto parse the human TUI.\n\n## On-disk layout (read these directly)\n\nAlways run `zread` from the workspace root. After a successful generation:\n\n- `.\u002F.zread\u002Fwiki\u002Fcurrent` — text file containing the active version id\n  (e.g. `2026-03-12-010203`).\n- `.\u002F.zread\u002Fwiki\u002Fversions\u002F\u003Cid>\u002Fwiki.json` — TOC: `{id, generated_at, language,\n  pages: [{slug, title, file, section, group, level}]}`.\n- `.\u002F.zread\u002Fwiki\u002Fversions\u002F\u003Cid>\u002F\u003Cfile>` — page markdown referenced by `pages[*].file`.\n- `.\u002F.zread\u002Fwiki\u002Fdrafts\u002F` — in-progress generation; presence means a previous\n  run did not finish. `drafts\u002Fwiki.json` exists once the catalog phase\n  completed.\n- `~\u002F.zread\u002Fconfig.yaml` — global config (LLM provider, language, concurrency).\n- `~\u002F.zread\u002Flogin.json` — presence indicates the user has logged in.\n\nTo answer questions about a codebase that already has zread output, read these\nfiles directly with the file tools — do not invoke `zread browse`.\n\n## Commands\n\n| Command | Purpose | Key flags |\n|---|---|---|\n| `zread generate` | Generate wiki for cwd | `-y\u002F--yes`, `--draft resume\\|clear\\|cancel`, `--skip-failed`, `--stdio` |\n| `zread browse` | Serve docs at http:\u002F\u002Flocalhost:9681+ and open browser | `--generate`, `--version \u003Cid>`, `--host`, `--port`, `--stdio` |\n| `zread login` | OAuth into BigModel\u002FZ.AI to obtain an API key | `--custom`, `--model`, `--stdio` |\n| `zread config` | Edit `~\u002F.zread\u002Fconfig.yaml` | `--stdio` |\n| `zread update` | Self-update CLI | `--stdio` |\n| `zread version` | Print version | `--stdio` |\n\n`--stdio` is supported on every command and turns the process into a JSON-line\nmachine protocol on stdin\u002Fstdout. See\n[references\u002Fstdio-protocol.md](.\u002Freferences\u002Fstdio-protocol.md) for the wire\nformat (events, `waiting_for`, `done`, `quit`). Load it whenever zread is\ninvoked from another program\u002Fagent.\n\n## Decision tree for an AI agent\n\n1. **User wants to read existing wiki content?**\n   - Check `.\u002F.zread\u002Fwiki\u002Fcurrent`. If present, read `wiki.json` and the page\n     markdown directly. No CLI invocation needed.\n   - For known *public* GitHub repos, prefer the `mcp__zread__*` tools\n     (`get_repo_structure`, `read_file`, `search_doc`) over running the CLI.\n\n2. **User wants to (re)generate docs?**\n   - Confirm with the user first — `generate` is long-running, calls an LLM,\n     and writes files. Get explicit consent in unfamiliar directories.\n   - Verify `~\u002F.zread\u002Flogin.json` exists or `~\u002F.zread\u002Fconfig.yaml` has an\n     `llm.api_key`. If neither, run `zread login` first.\n   - If `.\u002F.zread\u002Fwiki\u002Fdrafts\u002F` exists, decide:\n     - resume previous run → `zread generate --draft resume -y`\n     - throw away and start fresh → `zread generate --draft clear -y`\n   - Otherwise: `zread generate -y`.\n   - To not block on a few failing pages: add `--skip-failed`.\n\n3. **User wants to view docs in a browser?**\n   - `zread browse` (add `--generate` to bootstrap if no wiki exists yet).\n\n4. **User wants to script zread \u002F consume output programmatically?**\n   - Use `--stdio` and follow stdio-protocol.md. Do not screen-scrape the TUI.\n\n## Non-interactive invocation rules\n\n- Always pass `-y` to `generate` when running unattended; otherwise it stops\n  at a catalog confirmation gate.\n- Always set `--draft` explicitly when a draft may exist, so the command does\n  not prompt.\n- For any command run from another agent\u002Fscript, use `--stdio` so output is\n  parseable JSON instead of ANSI TUI frames.\n- `zread` writes logs to `~\u002F.zread\u002Flog\u002Fzread.log` — read this if a run fails\n  silently.\n\n## Safety \u002F blast radius\n\n- `generate` consumes LLM tokens (real cost) and can run for many minutes on\n  large repos. Confirm before launching.\n- `generate` writes only under `.\u002F.zread\u002F` and does not commit anything to\n  git. It is safe to delete `.\u002F.zread\u002Fwiki\u002Fdrafts\u002F` to recover from a stuck\n  state.\n- `update` replaces the zread binary in place and is hard to reverse — only\n  run it when the user explicitly asks.\n- `login` opens a browser for OAuth; do not run it in a non-interactive\n  context unless the user has asked for it.\n\n## Reference files\n\n- [references\u002Fstdio-protocol.md](.\u002Freferences\u002Fstdio-protocol.md) — JSON-line\n  wire protocol shared by every command's `--stdio` mode. Load when\n  programmatically driving zread.\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fzread",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill zread",{"tool":69,"command":70},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill zread",{"tool":72,"command":73},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill zread","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002FSKILL.md",true,[77,83],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"README.md","REFERENCE","参考文档",3070,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002FREADME.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fstdio-protocol.md",13461,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002Freferences\u002Fstdio-protocol.md",[88,105,132,154,174,186],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":97,"publishedAt":48},"01M70P17DAD4C1C47NPH6A96EM","xiaolai-methodology","以李笑来(Li Xiaolai)的思考方式、方法论与表达风格,为用户做全方位 1-on-1 教练指导,覆盖创业、赚钱、投资、学习、自学、读书写作、用 AI、以及人生心态与自我管理。当用户提到 \"李笑来\"、\"笑来\"、\"笑来老师\"、\"扮演李笑来\"、\"找笑来聊聊\"、\"笑来怎么看\"、\"xiaolai\"、\"把时间当作朋友\"、\"通往财富自由之路\"、\"定投改变命运\"、\"韭菜的自我修养\"、\"自学是门手艺\"、\"让时间陪你慢慢变富\"、\"七年就是一辈子\"、\"元认知\"、\"活在未来\"、\"复利\u002F长期主义\"、\"践行\"、\"痴迷改进\"、\"个人商业模式\u002F出售时间\"、\"睡后收入\"、\"定投\"、\"财富自由\"、\"操作系统升级\"、\"最少必要知识\"、\"北极星提示词\"、\"用 AI 该怎么学\u002F思考\" 等任一触发词,或当用户带着关于创业\u002F赚钱\u002F投资\u002F学习\u002F职业\u002F重大人生决策的困惑、希望被人用笑来式的「逻辑 + 大白话 + 类比 + 重新定义 + 践行导向」来点醒和指导时,自动进入李笑来教练模式。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fxiaolai-methodology\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",[98,99,100,101,102,103,104],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":115,"publishedAt":48},"01M70P10S4SWMZQ8BJAFBFDRW3","youtube","Launch the YouTube Creator Agent to auto-generate videos.\nUse when: user types \u002Fyoutube, wants to create YouTube videos,\ngenerate video content, or upload to YouTube.\nKeywords: youtube, video, 视频, 创作视频, 发布视频","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[111,112],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":113,"categoryName":114,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[107,116,117,118,119,120,121,122,123,124,125,126,127,128,45,129,130,131],"use","auto","types","Video","when","creator","user","content","视频","创作","generate video","videos","launch","video content","create","upload",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":48},"01M70P0YE95D8BACZCGV8BK90K","youtube-script-sync","Sync, update, or optimize Tony's GetNote knowledge base `Youtube视频逐字稿` by turning each parent recording or first-person idea note into an idempotent child note containing a directly recordable YouTube long-video or Shorts script. Use when the user says “更新\u002F同步\u002F优化 Youtube视频逐字稿知识库”, or says “更新\u002F同步\u002F优化该知识库” while this knowledge base is the active context.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-script-sync\u002FSKILL.md",[138],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[140,141,107,142,143,144,145,146,147,148,149,34,150,120,116,29,151,152,153,119],"sync","script","youtube script sync","first","base","person","update","active","child","optimize","idempotent","long","shorts","recording",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":164,"publishedAt":48},"01M70P0WMV5XT0EEC0N445PW07","writing-skills","How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills\u002FSKILL.md",[160,161,162,163],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},{"categoryNo":113,"categoryName":114,"taxonomyType":26,"taxonomyTypeDesc":27},[165,103,166,167,168,169,170,43,120,116,171,172,173],"writing skills","trigger","write skill","teach","write","how","claude code skills","files","how to",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":182,"publishedAt":48},"01M70P0SJFR4YVJQBGMHKGSKXT","writing-rules","How to write .claude\u002Frules\u002F files that Claude actually follows. Use when creating, improving, or reviewing project rules.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-rules\u002FSKILL.md",[180,181],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":113,"categoryName":114,"taxonomyType":26,"taxonomyTypeDesc":27},[183,184,103,185,116,169,170,120,172,173,33],"writing rules","Rules","project rules",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":195,"publishedAt":48},"01M70P0PMKHA9P7J0RFZGNHW5C","writing-prompts","How to write effective system prompts for any LLM. Universal prompt engineering -- role clarity, structured output, injection resistance, few-shot examples. Use when writing prompts, system instructions, or AI configuration.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-prompts\u002FSKILL.md",[192,193,194],{"categoryNo":95,"categoryName":96,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":113,"categoryName":114,"taxonomyType":26,"taxonomyTypeDesc":27},[103,196,197,120,173,198,199,200,201,116,202,203,204,205,206,170,169,207,208,209],"writing prompts","prompts","few-shot","structured output","for","system","prompt engineering","system prompts","instructions","examples","output","clarity","injection","prompt"]