[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71FR98QWRQ3CQGZ5BV53S6A":3,"skill-same:01M71FR98QWRQ3CQGZ5BV53S6A":65},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":37,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M71FR98QWRQ3CQGZ5BV53S6A","delegate-to-aside",null,"Delegates a side question to the `aside` subagent with a properly composed prompt so the main chat context stays clean. Use when the user says \"ask aside\", \"side question\", \"delegate this\", \"run in a subagent\", or otherwise signals they want the question answered in isolated context. Also use proactively when a request is clearly off the current work thread (research, lookups, \"how does X work?\") and would bloat the main context.","crestreach\u002Fcyncia","crestreach","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F169358583?v=4","01M71FR759G1CF6T5BAPQ1XKJ4","CrestReach","01M71FR7663FW7N09D3DSZRWJG",1,"MIT","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002F.agent-config\u002Fskills\u002Fdelegate-to-aside\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"delegate to aside","delegate","request","run","how","delegates","signals","research","work","with","chat","subagent","ask","when","prompt","thread","use","question","main","clean","2026-11-10 10:12:30",false,"---\nname: delegate-to-aside\ndescription: Delegates a side question to the `aside` subagent with a properly composed prompt so the main chat context stays clean. Use when the user says \"ask aside\", \"side question\", \"delegate this\", \"run in a subagent\", or otherwise signals they want the question answered in isolated context. Also use proactively when a request is clearly off the current work thread (research, lookups, \"how does X work?\") and would bloat the main context.\n---\n\n# Delegate to the `aside` Subagent\n\nThe user has an `aside` subagent at `~\u002F.cursor\u002Fagents\u002Faside.md` that answers side questions in an isolated context.\nOnly its final message returns here, so intermediate tool output does not pollute this chat.\n\nThis skill covers **how to invoke `aside` with a proper brief** instead of forwarding the user's raw words.\n\n## When to apply\n\nApply when the user:\n\n- Says \"ask aside\", \"side question\", \"delegate this\", \"run in a subagent\", or similar natural-language cues.\n- Types `\u002Faside \u003Cquestion>` at the start of a message.\n  Despite the slash, this is **not** a hard system-level bypass — the message is routed to you (the main agent), and you should delegate.\n  Treat it as an explicit cue to invoke the subagent.\n  You may (and should) still enrich the prompt with conversation context per the recipe below.\n- Asks something clearly tangential to the current work (research, lookups, comparisons, \"how does X work?\") that would bloat the main context.\n\nDo **not** apply when:\n\n- They want the answer inline in the main thread.\n- The question is trivially answerable from existing context.\n\n## How to invoke\n\nUse the Task tool with `subagent_type: \"aside\"` (or the equivalent subagent invocation in this session).\nCompose a brief; do not forward the raw question.\n\n## Prompt recipe\n\nBuild the subagent prompt with these sections, in order.\nOmit any that don't apply; do not pad.\n\n```\n## Question\n\u003CUser's question, restated cleanly. Resolve pronouns like \"this\",\n\"that file\", \"the function we discussed\" to concrete names.>\n\n## Context from the current conversation\n\u003C2–8 terse bullets: what the user is working on, prior decisions,\nconstraints, project-specific vocabulary. Briefing, not transcript.>\n\n## Relevant files \u002F symbols\n\u003CPaths, line ranges, symbol names. Prefer pointers over pasted\ncontent — the subagent has Read\u002FGrep\u002FGlob. Paste only small, central\nsnippets.>\n\n## What the user wants back\n\u003C1–2 lines on depth, format, citations, code vs. prose, etc.>\n\n## Out of scope\n\u003COptional. Guard against scope creep, e.g. \"do not propose code changes\".>\n```\n\n## Context selection rules\n\n- **Include**: decisions made, files touched, errors hit, constraints stated, project-specific vocabulary.\n- **Exclude**: earlier unrelated tangents, your own prior reasoning, tool output transcripts, anything trivially rediscovered by reading a file.\n- When in doubt, point to a path instead of pasting content.\n  Summarize long histories.\n\n## Example\n\n**User says:** \"Ask aside how retries work in `src\u002Fnet\u002Fclient.ts`, I want to know before I change this.\"\n\n**Delegation prompt:**\n\n```\n## Question\nHow does the retry logic in `src\u002Fnet\u002Fclient.ts` work? What triggers a\nretry, how is backoff computed, and is there a cap?\n\n## Context from the current conversation\n- User is about to modify `src\u002Fnet\u002Fclient.ts` to add a new endpoint.\n- They want to understand existing retry behavior first.\n\n## Relevant files \u002F symbols\n- `src\u002Fnet\u002Fclient.ts` (primary)\n- Helpers it imports — discover via grep.\n- `src\u002Fnet\u002Fconfig.ts` may hold retry tunables.\n\n## What the user wants back\nShort explanation with file:line citations. No code changes.\n\n## Out of scope\nDo not suggest changes to the retry logic.\n```\n\nFor self-contained research questions (\"what's the difference between X and Y?\"), omit the conversation-context and files sections.\n\n## After the subagent returns\n\n- Pass its final message through to the user.\n  Add at most a one-line note.\n- Do **not** re-explain or expand the answer — that defeats context isolation.\n- If it said it lacked information, ask the user (or offer a follow-up delegation with more context) rather than answering from memory.\n","# Delegate to the `aside` Subagent\n\nThe user has an `aside` subagent at `~\u002F.cursor\u002Fagents\u002Faside.md` that answers side questions in an isolated context.\nOnly its final message returns here, so intermediate tool output does not pollute this chat.\n\nThis skill covers **how to invoke `aside` with a proper brief** instead of forwarding the user's raw words.\n\n## When to apply\n\nApply when the user:\n\n- Says \"ask aside\", \"side question\", \"delegate this\", \"run in a subagent\", or similar natural-language cues.\n- Types `\u002Faside \u003Cquestion>` at the start of a message.\n  Despite the slash, this is **not** a hard system-level bypass — the message is routed to you (the main agent), and you should delegate.\n  Treat it as an explicit cue to invoke the subagent.\n  You may (and should) still enrich the prompt with conversation context per the recipe below.\n- Asks something clearly tangential to the current work (research, lookups, comparisons, \"how does X work?\") that would bloat the main context.\n\nDo **not** apply when:\n\n- They want the answer inline in the main thread.\n- The question is trivially answerable from existing context.\n\n## How to invoke\n\nUse the Task tool with `subagent_type: \"aside\"` (or the equivalent subagent invocation in this session).\nCompose a brief; do not forward the raw question.\n\n## Prompt recipe\n\nBuild the subagent prompt with these sections, in order.\nOmit any that don't apply; do not pad.\n\n```\n## Question\n\u003CUser's question, restated cleanly. Resolve pronouns like \"this\",\n\"that file\", \"the function we discussed\" to concrete names.>\n\n## Context from the current conversation\n\u003C2–8 terse bullets: what the user is working on, prior decisions,\nconstraints, project-specific vocabulary. Briefing, not transcript.>\n\n## Relevant files \u002F symbols\n\u003CPaths, line ranges, symbol names. Prefer pointers over pasted\ncontent — the subagent has Read\u002FGrep\u002FGlob. Paste only small, central\nsnippets.>\n\n## What the user wants back\n\u003C1–2 lines on depth, format, citations, code vs. prose, etc.>\n\n## Out of scope\n\u003COptional. Guard against scope creep, e.g. \"do not propose code changes\".>\n```\n\n## Context selection rules\n\n- **Include**: decisions made, files touched, errors hit, constraints stated, project-specific vocabulary.\n- **Exclude**: earlier unrelated tangents, your own prior reasoning, tool output transcripts, anything trivially rediscovered by reading a file.\n- When in doubt, point to a path instead of pasting content.\n  Summarize long histories.\n\n## Example\n\n**User says:** \"Ask aside how retries work in `src\u002Fnet\u002Fclient.ts`, I want to know before I change this.\"\n\n**Delegation prompt:**\n\n```\n## Question\nHow does the retry logic in `src\u002Fnet\u002Fclient.ts` work? What triggers a\nretry, how is backoff computed, and is there a cap?\n\n## Context from the current conversation\n- User is about to modify `src\u002Fnet\u002Fclient.ts` to add a new endpoint.\n- They want to understand existing retry behavior first.\n\n## Relevant files \u002F symbols\n- `src\u002Fnet\u002Fclient.ts` (primary)\n- Helpers it imports — discover via grep.\n- `src\u002Fnet\u002Fconfig.ts` may hold retry tunables.\n\n## What the user wants back\nShort explanation with file:line citations. No code changes.\n\n## Out of scope\nDo not suggest changes to the retry logic.\n```\n\nFor self-contained research questions (\"what's the difference between X and Y?\"), omit the conversation-context and files sections.\n\n## After the subagent returns\n\n- Pass its final message through to the user.\n  Add at most a one-line note.\n- Do **not** re-explain or expand the answer — that defeats context isolation.\n- If it said it lacked information, ask the user (or offer a follow-up delegation with more context) rather than answering from memory.\n",{"name":5,"description":7},"f2834ae3a8d2b768340afe3edecf03e345e49171",".agent-config\u002Fskills\u002Fdelegate-to-aside","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia","https:\u002F\u002Fwww.cyncia.net","https:\u002F\u002Fgithub.com\u002Fcrestreach","http:\u002F\u002Fwww.crestreach.com","2026-07-11 02:00:30",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add crestreach\u002Fcyncia --skill delegate-to-aside",{"tool":57,"command":58},"bunx","bunx skills add crestreach\u002Fcyncia --skill delegate-to-aside",{"tool":60,"command":61},"pnpm","pnpm dlx skills add crestreach\u002Fcyncia --skill delegate-to-aside","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002F.agent-config\u002Fskills\u002Fdelegate-to-aside\u002FSKILL.md",true,[],[66,76,84,112,128],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":39},"01M71FRNND0JMSB7KJ25NG3BKV","beta","Second test skill.","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Ftwo-skills\u002Fskills\u002Fbeta\u002FSKILL.md",[],[68,73,74,75],"Test Skill","second","test",{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":39},"01M71FRN094CDHGCEJNA2ZQD67","alpha","First test skill.","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Ftwo-skills\u002Fskills\u002Falpha\u002FSKILL.md",[],[78,73,75,83],"first",{"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":95,"publishedAt":39},"01M71FRH7T0N6NANFPM85NPVAQ","agent-conf-sync","Runs the cyncia batch script (`sync-all`) to regenerate Cursor, Claude Code, GitHub Copilot, VS Code, JetBrains Junie, and Codex configuration from a generic source tree. Use when the user asks to \"sync agent config\", \"regenerate rules\u002Fskills\u002Fagents\u002Fmcp\", \"update .cursor \u002F .claude \u002F .github \u002F .junie \u002F .vscode \u002F .codex \u002F .agents from source\", \"run sync-all\", or similar — so they don't have to assemble CLI flags or pick Windows vs Unix scripts themselves. The skill detects the OS, finds the script, and infers `-i` \u002F `-o` \u002F `--tools` \u002F `--items` \u002F `--clean` from the natural-language request.","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002Fskills\u002Fagent-conf-sync\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[96,97,98,99,100,38,101,32,102,103,104,105,106,107,22,21,108,109,110,111],"conf","sync","agent conf sync","pick","copilot","MCP","code","natural-language","batch","jetbrains","cli","assemble","update","scripts","unix","github copilot",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":39},"01M71FREXPPVZB51AV724KMPRP","pirate-java-comments","Write code comments like a pirate, but only in Java files.","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002Fexamples\u002Fskills\u002Fpirate-java-comments\u002FSKILL.md",[],[119,120,121,122,123,124,125,102,126,127],"java","comments","pirate","pirate java comments","only","files","code comments","but","write",{"skillNo":129,"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":130,"categories":131,"keywords":132,"publishedAt":39},"01M71FRC45A867X4D111HMD5RB","https:\u002F\u002Fgithub.com\u002Fcrestreach\u002Fcyncia\u002Fblob\u002Fmain\u002Fexamples\u002Fskills\u002Fdelegate-to-aside\u002FSKILL.md",[],[19,20,26,38,37,36,35,34,33,32,31,30,29,28,27,25,24,23,22,21]]