[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZG4STQ8R15F6HFT5BE98J":3,"skill-same:01M6CZG4STQ8R15F6HFT5BE98J":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":13,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6CZG4STQ8R15F6HFT5BE98J","telegram-formatting",null,"Telegram HTML and MarkdownV2 formatting reference for clawq message code","clankercode\u002Fclawq","clankercode","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269201082?v=4","01M6CZFKG57M58N3F63P2H9742","01M6CZFKMHDHR7D6ADH22V9T11",0,"Unlicense","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelegram-formatting\u002FSKILL.md",[],[18,19,20,21,22,23,24],"telegram","telegram formatting","code","html","reference","message","clawq","2026-11-10 10:12:30",false,"---\nname: telegram-formatting\ndescription: Telegram HTML and MarkdownV2 formatting reference for clawq message code\n---\n\n# Telegram Formatting Skill\n\nUse this skill when writing or modifying code that produces Telegram-formatted messages in clawq.\n\n## HTML Mode (preferred for structured output)\n\n### Tags\n- `\u003Cb>bold\u003C\u002Fb>`, `\u003Ci>italic\u003C\u002Fi>`, `\u003Cu>underline\u003C\u002Fu>`, `\u003Cs>strikethrough\u003C\u002Fs>`\n- `\u003Ccode>inline code\u003C\u002Fcode>`, `\u003Cpre>code block\u003C\u002Fpre>`\n- `\u003Cpre>\u003Ccode class=\"language-python\">highlighted\u003C\u002Fcode>\u003C\u002Fpre>`\n- `\u003Ca href=\"URL\">link text\u003C\u002Fa>`\n- `\u003Cblockquote>quote\u003C\u002Fblockquote>`, `\u003Cblockquote expandable>collapsible\u003C\u002Fblockquote>`\n- `\u003Ctg-spoiler>hidden\u003C\u002Ftg-spoiler>`\n\n### Escaping (outside tags)\n- `\u003C` → `<`, `>` → `>`, `&` → `&`\n\n## MarkdownV2 Mode (used for agent responses)\n\n### Syntax\n- Bold: `*text*`, Italic: `_text_`, Code: `` `text` ``\n- Code block: ` ```lang\\n...\\n``` `\n- Quote: `>line` (per line), Expandable: `**>line||` (per line)\n\n### Must-escape characters\n```\n_ * [ ] ( ) ~ ` > # + - = | { } . !\n```\n\n## Expandable Blockquote Pattern\n\nBest practice for fitting large content into a single message:\n\n```html\n\u003Cb>Result:\u003C\u002Fb> Brief summary here.\n\u003Cblockquote expandable>\n1. Step one details\n2. Step two details\n3. Step three details\n\u003C\u002Fblockquote>\n```\n\n## clawq Conventions\n\n- Max message length: 4096 chars (split via `chunk_text` in `telegram.ml`)\n- `send_chunked` — sends with optional `?parse_mode`, splits automatically\n- `send_chunked_html_with_fallback` — sends as HTML, falls back to plain text per chunk on error\n- `telegram_delegate_prompt` — wraps user prompt with HTML formatting instructions for delegate\u002Ffork\n- `telegram_format.ml` — MarkdownV2 escaping helpers (`escape_mdv2`, `bold`, `italic`, `code_block`, etc.)\n- `\u002Ftools` uses HTML mode with `\u003Cblockquote expandable>` for tool listings\n- Agent chat responses use MarkdownV2 via `telegram_format.ml`\n- Delegate\u002Ffork responses use HTML with fallback\n","# Telegram Formatting Skill\n\nUse this skill when writing or modifying code that produces Telegram-formatted messages in clawq.\n\n## HTML Mode (preferred for structured output)\n\n### Tags\n- `\u003Cb>bold\u003C\u002Fb>`, `\u003Ci>italic\u003C\u002Fi>`, `\u003Cu>underline\u003C\u002Fu>`, `\u003Cs>strikethrough\u003C\u002Fs>`\n- `\u003Ccode>inline code\u003C\u002Fcode>`, `\u003Cpre>code block\u003C\u002Fpre>`\n- `\u003Cpre>\u003Ccode class=\"language-python\">highlighted\u003C\u002Fcode>\u003C\u002Fpre>`\n- `\u003Ca href=\"URL\">link text\u003C\u002Fa>`\n- `\u003Cblockquote>quote\u003C\u002Fblockquote>`, `\u003Cblockquote expandable>collapsible\u003C\u002Fblockquote>`\n- `\u003Ctg-spoiler>hidden\u003C\u002Ftg-spoiler>`\n\n### Escaping (outside tags)\n- `\u003C` → `<`, `>` → `>`, `&` → `&`\n\n## MarkdownV2 Mode (used for agent responses)\n\n### Syntax\n- Bold: `*text*`, Italic: `_text_`, Code: `` `text` ``\n- Code block: ` ```lang\\n...\\n``` `\n- Quote: `>line` (per line), Expandable: `**>line||` (per line)\n\n### Must-escape characters\n```\n_ * [ ] ( ) ~ ` > # + - = | { } . !\n```\n\n## Expandable Blockquote Pattern\n\nBest practice for fitting large content into a single message:\n\n```html\n\u003Cb>Result:\u003C\u002Fb> Brief summary here.\n\u003Cblockquote expandable>\n1. Step one details\n2. Step two details\n3. Step three details\n\u003C\u002Fblockquote>\n```\n\n## clawq Conventions\n\n- Max message length: 4096 chars (split via `chunk_text` in `telegram.ml`)\n- `send_chunked` — sends with optional `?parse_mode`, splits automatically\n- `send_chunked_html_with_fallback` — sends as HTML, falls back to plain text per chunk on error\n- `telegram_delegate_prompt` — wraps user prompt with HTML formatting instructions for delegate\u002Ffork\n- `telegram_format.ml` — MarkdownV2 escaping helpers (`escape_mdv2`, `bold`, `italic`, `code_block`, etc.)\n- `\u002Ftools` uses HTML mode with `\u003Cblockquote expandable>` for tool listings\n- Agent chat responses use MarkdownV2 via `telegram_format.ml`\n- Delegate\u002Ffork responses use HTML with fallback\n",{"name":5,"description":7},"master","7c87c0cf8d869c392efbe4b2f0065c85657bf969",".claude\u002Fskills\u002Ftelegram-formatting","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq","https:\u002F\u002Fclawq.org\u002F","https:\u002F\u002Fgithub.com\u002Fclankercode","xk.io","2026-11-12 11:53:34",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add clankercode\u002Fclawq --skill telegram-formatting",{"tool":44,"command":45},"bunx","bunx skills add clankercode\u002Fclawq --skill telegram-formatting",{"tool":47,"command":48},"pnpm","pnpm dlx skills add clankercode\u002Fclawq --skill telegram-formatting","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Ftelegram-formatting\u002FSKILL.md",true,[],[53,85,113,123,143,154],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":64,"publishedAt":25},"01M6CZGG2GJZ7PGVTZSG8NDB2R","run-task","Runs a backlog item (bug, feature, task, epic, milestone, phase) end-to-end by gathering context, constructing a startup prompt, spawning a worktree-backed subagent, and managing the claim\u002Fdone\u002Freview cycle. Use when the user wants to execute a backlog target like B123, F456, P2.M4.E3, etc.","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002Fdocs\u002Fbuiltin-skills\u002Frun-task\u002FSKILL.md",[59],{"categoryNo":60,"categoryName":61,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"run task","run","task","backlog","review cycle","review","feature","done","worktree","startup","subagent","extra","prompt","user","execute","use","bug","cycle","milestone","claim",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":94,"publishedAt":25},"01M6CZGD2YWGXTV25FM004F7ZM","pipeline-designer","Design and create structured output pipelines. Gathers requirements, designs step sequences with output schemas, generates valid YAML pipeline definitions, and validates them.","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002Fdocs\u002Fbuiltin-skills\u002Fpipeline-designer\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000015","视觉设计",[95,96,97,23,98,99,100,78,101,102,103,104,105,106,107,108,109,110,111,112],"pipeline","designer","pipeline designer","what the","do","pipelines","write","read","question","ask","shell","structured","requirements","file","create","valid","design","yaml",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":25},"01M6CZGAY23A6HQS1G7JK7WQGM","idea","Log a planning idea to the backlog. Use when the user has a feature idea, enhancement suggestion, or brainstorm they want tracked.","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002Fdocs\u002Fbuiltin-skills\u002Fidea\u002FSKILL.md",[],[115,71,78,68,120,80,121,122],"log","brainstorm","planning",{"skillNo":124,"name":71,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":129,"publishedAt":25},"01M6CZG7S5TSVHB6S8YA3JMGFJ","Automate the creation of a new feature for clawq. Gathers requirements, discovers existing capabilities, decomposes into implementation layers, gates risky work behind approval, and delegates implementation. Prefers skills\u002Frigs\u002Fcron\u002Ftemplates over OCaml code changes.","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002Fdocs\u002Fbuiltin-skills\u002Ffeature\u002FSKILL.md",[128],{"categoryNo":60,"categoryName":61,"taxonomyType":62,"taxonomyTypeDesc":63},[71,20,130,131,132,133,134,135,136,137,138,24,139,140,107,141,142],"implementation","approval","new feature","work","automate","cron","templates","capabilities","ocaml","creation","gates","natural language","language",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":25},"01M6CZG2ZASD966C153XZY3BQ1","pag-review-via-team","review work using teams + review-and-fix","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fpag-review-via-team\u002FSKILL.md",[],[150,151,70,152,133,153],"pag review via team","team","fix","teams",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":25},"01M6CZG02S14BW5NN1P2F2PN7Q","clawq-version-bump","Bump clawq version, commit, tag, push, and create a GitHub release","https:\u002F\u002Fgithub.com\u002Fclankercode\u002Fclawq\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fclawq-version-bump\u002FSKILL.md",[],[24,161,162,163,164,165,166,167,109,168,169],"clawq version bump","version bump","bump","version","github release","push","release","commit","github"]