[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PDKAW3D7SSQMPAEAJ3KW47":3,"skill-same:01M6PDKAW3D7SSQMPAEAJ3KW47":82},{"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":35,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6PDKAW3D7SSQMPAEAJ3KW47","cavecrew",null,"Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: \"delegate to subagent\", \"use cavecrew\", \"spawn investigator\u002Fbuilder\u002Freviewer\", \"save context\", \"compressed agent output\".","stevesolun\u002Fctx","stevesolun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1304538?v=4","01M6PDDJQ35XAXMPJQP8YG3P2X","Steve Solun","01M6PDDJVJ663A3CMV7XQN9XAY",593,"MIT","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fimported-skills\u002Fjulius-caveman\u002Fskills\u002Fcavecrew\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],"context","result","inline","investigator","across","back","main","builder","guide","spawn","review","edit","delegate","work","reviewer","decision","subagent","explore","code","2026-11-10 10:12:30",false,"---\nname: cavecrew\ndescription: >\n  Decision guide for delegating to caveman-style subagents. Tells the main\n  thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder`\n  (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the\n  work inline or using vanilla `Explore`. Subagent output is caveman-compressed\n  so the tool-result injected back into main context is ~60% smaller — main\n  context lasts longer across long sessions.\n  Trigger: \"delegate to subagent\", \"use cavecrew\", \"spawn investigator\u002Fbuilder\u002Freviewer\",\n  \"save context\", \"compressed agent output\".\n---\n\nCavecrew = three subagent presets that emit caveman output. Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.\n\n## When to use cavecrew vs alternatives\n\n| Task | Use |\n|---|---|\n| \"Where is X defined \u002F what calls Y \u002F list uses of Z\" | `cavecrew-investigator` |\n| Same but you also want suggestions\u002Farchitecture commentary | `Explore` (vanilla) |\n| Surgical edit, ≤2 files, scope obvious | `cavecrew-builder` |\n| New feature \u002F 3+ files \u002F cross-cutting refactor | Main thread or `feature-dev:code-architect` |\n| Review diff, branch, or file for bugs | `cavecrew-reviewer` |\n| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) |\n| One-line answer you already know | Main thread, no subagent |\n\nRule of thumb: **if you'd want the subagent's output in 1\u002F3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.**\n\n## Why this exists (the real win)\n\nSubagent tool results get injected into main context verbatim. A vanilla `Explore` that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from `cavecrew-investigator` returns ~700 tokens. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.\n\n## Output contracts\n\nWhat main thread can rely on per agent:\n\n**`cavecrew-investigator`**\n```\n\u003CHeader>:\n- path:line — `symbol` — short note\ntotals: \u003Ccounts>.\n```\nOr `No match.` Always file-path-first, line-number-attached, backticked symbols. Safe to grep with `path:\\d+`.\n\n**`cavecrew-builder`**\n```\n\u003Cpath:line-range> — \u003Cchange ≤10 words>.\nverified: \u003Cre-read OK | mismatch @ path:line>.\n```\nOr one of: `too-big.` \u002F `needs-confirm.` \u002F `ambiguous.` \u002F `regressed.` (terminal first token).\n\n**`cavecrew-reviewer`**\n```\npath:line: \u003Cemoji> \u003Cseverity>: \u003Cproblem>. \u003Cfix>.\ntotals: N? N? N? N❓\n```\nOr `No issues.` Findings sorted file → line ascending.\n\n## Chaining patterns\n\n**Locate → fix → verify** (most common):\n1. `cavecrew-investigator` returns site list.\n2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`.\n3. `cavecrew-reviewer` audits the diff.\n\n**Parallel scout** (when investigation is broad):\nSpawn 2-3 `cavecrew-investigator` calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.\n\n**Single-shot edit** (when site is already known):\nSkip investigator. Hand exact path:line to `cavecrew-builder` directly.\n\n## What NOT to do\n\n- Don't use `cavecrew-builder` when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.\n- Don't chain `cavecrew-investigator → cavecrew-builder` for a 5-file refactor. Builder will return `too-big.` and you'll have wasted a turn.\n- Don't ask `cavecrew-reviewer` for \"general feedback\" — it returns findings only, no architecture opinions. Use `Code Reviewer` for that.\n- Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.\n\n## Auto-clarity (inherited)\n\nSubagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.\n","Cavecrew = three subagent presets that emit caveman output. Same job as Anthropic defaults (`Explore`, edit-style agents, reviewer); difference is the tool-result they return is compressed, so main context shrinks per delegation.\n\n## When to use cavecrew vs alternatives\n\n| Task | Use |\n|---|---|\n| \"Where is X defined \u002F what calls Y \u002F list uses of Z\" | `cavecrew-investigator` |\n| Same but you also want suggestions\u002Farchitecture commentary | `Explore` (vanilla) |\n| Surgical edit, ≤2 files, scope obvious | `cavecrew-builder` |\n| New feature \u002F 3+ files \u002F cross-cutting refactor | Main thread or `feature-dev:code-architect` |\n| Review diff, branch, or file for bugs | `cavecrew-reviewer` |\n| Deep code review with rationale + alternatives | `Code Reviewer` (vanilla) |\n| One-line answer you already know | Main thread, no subagent |\n\nRule of thumb: **if you'd want the subagent's output in 1\u002F3 the tokens, pick cavecrew. If you'd want prose, pick vanilla.**\n\n## Why this exists (the real win)\n\nSubagent tool results get injected into main context verbatim. A vanilla `Explore` that returns 2k tokens of prose costs 2k tokens of main-context budget every time. The same finding from `cavecrew-investigator` returns ~700 tokens. Across 20 delegations in one session that's the difference between context exhaustion and finishing the task.\n\n## Output contracts\n\nWhat main thread can rely on per agent:\n\n**`cavecrew-investigator`**\n```\n\u003CHeader>:\n- path:line — `symbol` — short note\ntotals: \u003Ccounts>.\n```\nOr `No match.` Always file-path-first, line-number-attached, backticked symbols. Safe to grep with `path:\\d+`.\n\n**`cavecrew-builder`**\n```\n\u003Cpath:line-range> — \u003Cchange ≤10 words>.\nverified: \u003Cre-read OK | mismatch @ path:line>.\n```\nOr one of: `too-big.` \u002F `needs-confirm.` \u002F `ambiguous.` \u002F `regressed.` (terminal first token).\n\n**`cavecrew-reviewer`**\n```\npath:line: \u003Cemoji> \u003Cseverity>: \u003Cproblem>. \u003Cfix>.\ntotals: N? N? N? N❓\n```\nOr `No issues.` Findings sorted file → line ascending.\n\n## Chaining patterns\n\n**Locate → fix → verify** (most common):\n1. `cavecrew-investigator` returns site list.\n2. Main thread picks 1-2 sites, hands paths to `cavecrew-builder`.\n3. `cavecrew-reviewer` audits the diff.\n\n**Parallel scout** (when investigation is broad):\nSpawn 2-3 `cavecrew-investigator` calls in one message (different angles: defs vs callers vs tests). Aggregate in main thread.\n\n**Single-shot edit** (when site is already known):\nSkip investigator. Hand exact path:line to `cavecrew-builder` directly.\n\n## What NOT to do\n\n- Don't use `cavecrew-builder` when you don't already know the file. Spawn investigator first or main thread will eat tokens passing context.\n- Don't chain `cavecrew-investigator → cavecrew-builder` for a 5-file refactor. Builder will return `too-big.` and you'll have wasted a turn.\n- Don't ask `cavecrew-reviewer` for \"general feedback\" — it returns findings only, no architecture opinions. Use `Code Reviewer` for that.\n- Don't expect prose. Cavecrew output is structured, sometimes terse to the point of cryptic. If a human will read it directly, paraphrase.\n\n## Auto-clarity (inherited)\n\nSubagents drop caveman → normal English for security warnings, irreversible-action confirmations, and any output where fragment ambiguity could be misread. Resume caveman after.\n",{"name":5,"description":7},"11b582a7cd4d549f1e83c412e04421bcc9c3fc28","imported-skills\u002Fjulius-caveman\u002Fskills\u002Fcavecrew",69,"https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx","https:\u002F\u002Fstevesolun.github.io\u002Fctx\u002F","https:\u002F\u002Fgithub.com\u002Fstevesolun","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fsolunsteve\u002F","High motivated, dedicated, fast learner data scientist and enthusiastic researcher.","2026-10-15 03:55:28",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add stevesolun\u002Fctx --skill cavecrew",{"tool":68,"command":69},"bunx","bunx skills add stevesolun\u002Fctx --skill cavecrew",{"tool":71,"command":72},"pnpm","pnpm dlx skills add stevesolun\u002Fctx --skill cavecrew","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fimported-skills\u002Fjulius-caveman\u002Fskills\u002Fcavecrew\u002FSKILL.md",true,[76],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"README.md","REFERENCE","参考文档",2009,"https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fimported-skills\u002Fjulius-caveman\u002Fskills\u002Fcavecrew\u002FREADME.md",[83,108,127,153,175,195],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":48},"01M6PDTT7F6Z9T6G6H92845RNC","toolbox","Pre\u002Fpost dev toolbox — named bundles of skills\u002Fagents loaded before development work and councils of experts invoked after. Run \u002Ftoolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing toolboxes with a team.","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fskills\u002Ftoolbox\u002FSKILL.md",[],[85,90,91,92,93,94,42,95,96,97,98,99,100,101,102,103,104,105,106,107],"cli","development","run","start","team","list","initialize","export","up","activate","feature","end","new repo","false","import","experts","at","invoke",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":115,"publishedAt":48},"01M6PDTNZ10BAW6VY49S40NCBB","skill-router","Alive skill router — reads the current project's stack and loads\u002Funloads skills dynamically. Invoke at session start or when project context changes.","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fskills\u002Fskill-router\u002FSKILL.md",[114],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[116,117,93,118,119,29,120,121,122,123,124,125,106,126,107],"router","skill router","Meta","stack","session","project context","project","loads","session start","true","changes",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":48},"01M6PDTGVDG503T4QNX64KJMAC","repo-stats-autoupdate","Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes\u002Fedges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fskills\u002Frepo-stats-autoupdate\u002FSKILL.md",[133],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,103,150,151,152,31],"stats","repo","repo stats autoupdate","test","commit","sync","release","git","graph","pre-commit","inventory","README","use","publishing","communities","with","hook","number",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":161,"publishedAt":48},"01M6PDTC3AB7H4NXJFS3SDKQG9","find-skills","Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add\u002Fupdate a skill, or needs a repeatable procedure for finding candidate skills safely.","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fskills\u002Ffind-skills\u002FSKILL.md",[159,160],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[162,163,90,164,165,166,167,168,147,65,169,170,171,172,173,174],"find skills","find","update","search","api","user","catalog","discover","add","skills cli","for","candidate","ctx",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":48},"01M6PDT6ETDH54GGY7K8E29Y9V","no-mistakes","Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fimported-skills\u002Fno-mistakes\u002Fskills\u002Fno-mistakes\u002FSKILL.md",[],[182,39,138,183,184,185,92,186,187,188,189,190,191,192,147,193,194,100,125,126],"no mistakes","change","validate","pr","lint","push","ci","pipeline","ship","rebase","branch","intent","upstream",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":203,"publishedAt":48},"01M6PDT18DD3HETZF1CF39CT8J","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fstevesolun\u002Fctx\u002Fblob\u002Fmain\u002Fimported-skills\u002Fmattpocock\u002Fzoom-out\u002FSKILL.md",[201,202],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[204,205,47,206,29,147,207,208,150,209,210,125,211,212],"zoom out","zoom","how","it","understand","you","re","perspective","section"]