[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75WT5PR9SNPKCYA703E1BN9":3,"skill-same:01M75WT5PR9SNPKCYA703E1BN9":44},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75WT5PR9SNPKCYA703E1BN9","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\".","Wifabric\u002FAISC","Wifabric","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F330220688?v=4","01M75WHNJBRX6BCM6XZKHHFC16","01M75WHNJZSW18JZJBRAPZJ5RV",7,"MIT","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002F_bundle\u002Fplugins\u002Fmarketplaces\u002Fcaveman\u002F.kiro\u002Fskills\u002Fcavecrew\u002FSKILL.md",[],[],"2026-11-12 13:55:43",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},"main","1c39903dc146e00ac5b7d92c8bd48433a3d4a7f5","container\u002F_bundle\u002Fplugins\u002Fmarketplaces\u002Fcaveman\u002F.kiro\u002Fskills\u002Fcavecrew",0,"https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC","https:\u002F\u002Fgithub.com\u002FWifabric","2026-11-09 21:53:05",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add Wifabric\u002FAISC --skill cavecrew",{"tool":36,"command":37},"bunx","bunx skills add Wifabric\u002FAISC --skill cavecrew",{"tool":39,"command":40},"pnpm","pnpm dlx skills add Wifabric\u002FAISC --skill cavecrew","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002F_bundle\u002Fplugins\u002Fmarketplaces\u002Fcaveman\u002F.kiro\u002Fskills\u002Fcavecrew\u002FSKILL.md",true,[],[45,52,59,66,74,82],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M75WYM5HQ22465HVJ6FQW8ES","topic-workshop","围绕用户选定的主题，把资料、沟通、实践与反馈沉淀为可执行的主题手册，并记录迭代依据。用于建立或接续长期主题工作、从实践完善手册、分析流程改进；单次问答、纯文件摘要和普通代码修改不自动启动本流程。","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fsrc\u002Faisc\u002F_topic_skill\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M75WYJGGHSD17YXV881RZVE9","aisc-development","推进 AISC 已确认版本的功能开发、Issue 修复、贡献者 PR 集成与统一 Preview 交付。用于本仓库开发协作，不用于平台内安装扩展技能或替用户批准产品与正式发布。","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fskills\u002Faisc-development\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M75WYGD0HHMQYJTEV1KKV2FX","karpathy-guidelines","Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002Fcc-switch-skills\u002Fkarpathy-guidelines\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M75WYE09NJ4SP850F7J29Z37","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002Fcc-switch-skills\u002Fgrilling\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002Fcc-switch-skills\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M75WYC9X05NCDDTYVGB7S0WN","grill-me","A relentless one-question-at-a-time interview to sharpen a plan, decision, or design.","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002Fcc-switch-skills\u002Fgrill-me\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002Fcc-switch-skills\u002Fgrill-me\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M75WYAC1WNGS5J0VYSXNG591","document-skills","Create and edit documents, spreadsheets, presentations, PDFs, and other business artifacts using the bundled Anthropic document skills.","https:\u002F\u002Fgithub.com\u002FWifabric\u002FAISC\u002Fblob\u002Fmain\u002Fcontainer\u002Fcc-switch-skills\u002Fdocument-skills\u002FSKILL.md",[],[]]