[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XD295XPXA1VPBNZX8MTCNK":3,"skill-same:01M6XD295XPXA1VPBNZX8MTCNK":68},{"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":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6XD295XPXA1VPBNZX8MTCNK","create-inspection",null,"Investigate a specific problem and surface viable fix paths with trade-offs, saved to docs\u002Finspections\u002F. Triggers on: \"how should I fix\", \"what are my options\", \"investigate before I touch\".","kaiohenricunha\u002Fdotbabel","kaiohenricunha","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F69804490?v=4","01M6XCZD37W0KPCDGEA40Y610V","Kaio Cunha","01M6XCZD7SX714D114H3ZPNW09",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fcreate-inspection\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"create","create inspection","triggers","docs","trade-offs","my","saved","with","touch","paths","problem","investigate","trade","options","fix","write","read","grep","Bash","how","2026-11-10 10:12:30",false,"---\n# dotbabel:generated projection=sha256:45665346f453304ad7169c602c67d9b66eb80fdb49d2006e36df4101ea5c0bb8 source=skills\u002Fcreate-inspection\u002FSKILL.md — do not edit directly\nallowed-tools: Read Grep Glob Bash Write\nargument-hint: \"[problem]\"\ndescription: |\n  Investigate a specific problem and surface viable fix paths with trade-offs, saved to docs\u002Finspections\u002F. Triggers on: \"how should I fix\", \"what are my options\", \"investigate before I touch\".\nname: create-inspection\n---\n\nInvestigate a specific problem and produce a structured fix-path document saved to the project's `docs\u002Finspections\u002F` directory.\n\nTrigger: when the user asks \"how should I fix X\", \"what are my options for Y\", \"investigate Z before I touch it\", or triggers directly via `\u002Fcreate-inspection`. Also useful before invoking the `\u002Ffix-with-evidence` skill to pre-evaluate approaches.\n\nArguments: `$ARGUMENTS` — a description of the problem or subject to inspect (e.g. \"auth token refresh race condition\", \"N+1 queries in \u002Fapi\u002Fdashboard\", \"flaky E2E login test\"). Required — if empty, ask the user.\n\n## Purpose\n\n`\u002Fcreate-inspection` is **not** an audit (it doesn't enumerate all issues) and **not** a fix (it doesn't implement anything). Its output is a **decision document**: here is what is broken, here are the viable paths to fix it, here is a recommended approach with rationale. Sits between the `\u002Fcreate-audit` skill (find problems) and the `\u002Ffix-with-evidence` skill (implement the fix).\n\n## Steps\n\n1. **Parse the subject** from `$ARGUMENTS`. If empty or vague, ask the user to describe the symptom or problem.\n\n2. **Locate the problem in the codebase.** Use `Grep`, `Glob`, and `Read` to find the relevant files, functions, configs, and tests. Do not guess — verify every claim with a `file:line` citation.\n\n3. **Diagnose root cause.** Read enough code to understand _why_ the problem occurs, not just _where_. If there are tests, run them to observe the failure. If the issue is behavioural (performance, flakiness), read logs or run diagnostic commands.\n\n4. **Generate at least 2 fix options.** For each option:\n   - Describe the approach concisely\n   - List the files\u002Fcomponents touched\n   - State the trade-offs (complexity, blast radius, test surface, reversibility)\n   - Estimate effort: `low` (\u003C 1 hr), `medium` (1–4 hrs), `high` (> 4 hrs)\n   - Assess risk: `low`, `medium`, `high`\n\n5. **Pick a recommended option** and explain why it best balances correctness, risk, and effort. If options are genuinely tied, say so and flag the deciding factor for the user.\n\n6. **Generate the inspection document** with this structure:\n\n   ```markdown\n   # Inspection: \u003CSubject> — \u003CYYYY-MM-DD>\n\n   \u003COne-sentence description of the problem and its impact.>\n\n   ## Root Cause\n\n   \u003CEvidence-backed explanation of why the problem occurs. Include file:line citations.>\n\n   ## Scope\n\n   Files and components relevant to this problem.\n\n   | File \u002F Component | Role in the problem |\n   | ---------------- | ------------------- |\n   | ...              | ...                 |\n\n   ## Fix Options\n\n   ### Option 1: \u003CName>\n\n   **Approach:** \u003Cdescription>\n   **Files touched:** \u003Clist>\n   **Effort:** low | medium | high\n   **Risk:** low | medium | high\n   **Trade-offs:** \u003Cpros and cons>\n\n   ### Option 2: \u003CName>\n\n   ...\n\n   ## Recommendation\n\n   **Use Option N: \u003CName>**\n\n   \u003C2-3 sentences explaining why this option is best for the current situation.\n   Call out any assumptions (e.g. \"assumes test coverage exists for the path\").>\n\n   ## Next Step\n\n   Run `\u002Ffix-with-evidence \u003Csubject>` using the recommended option,\n   or proceed manually using the approach above.\n   ```\n\n7. **Generate a filename** in the format: `\u003Ctopic-slug>-\u003CYYYY-MM-DD>.md` (e.g. `auth-refresh-race-2026-04-14.md`). Use lowercase kebab-case.\n\n8. **Write the file** to `docs\u002Finspections\u002F\u003Cfilename>`. Create the `docs\u002Finspections\u002F` directory if it doesn't exist.\n\n9. **Report to the user**: show the file path, the root cause in one sentence, and the recommended option. Do not dump the full document into chat.\n\n## Rules\n\n- Every root-cause claim must be backed by a `file:line` citation or command output. No assumptions.\n- Always provide at least 2 distinct fix options. Single-option \"inspections\" are just instructions.\n- Never implement a fix. Surface options and recommend. The user decides.\n- Do not commit the inspection file. Leave it untracked for the user to review.\n- If the problem cannot be localized (e.g. no repro, insufficient context), state that clearly and list what additional information is needed rather than producing a speculative document.\n- Keep the document concise. Tables over prose where possible. No filler.\n","Investigate a specific problem and produce a structured fix-path document saved to the project's `docs\u002Finspections\u002F` directory.\n\nTrigger: when the user asks \"how should I fix X\", \"what are my options for Y\", \"investigate Z before I touch it\", or triggers directly via `\u002Fcreate-inspection`. Also useful before invoking the `\u002Ffix-with-evidence` skill to pre-evaluate approaches.\n\nArguments: `$ARGUMENTS` — a description of the problem or subject to inspect (e.g. \"auth token refresh race condition\", \"N+1 queries in \u002Fapi\u002Fdashboard\", \"flaky E2E login test\"). Required — if empty, ask the user.\n\n## Purpose\n\n`\u002Fcreate-inspection` is **not** an audit (it doesn't enumerate all issues) and **not** a fix (it doesn't implement anything). Its output is a **decision document**: here is what is broken, here are the viable paths to fix it, here is a recommended approach with rationale. Sits between the `\u002Fcreate-audit` skill (find problems) and the `\u002Ffix-with-evidence` skill (implement the fix).\n\n## Steps\n\n1. **Parse the subject** from `$ARGUMENTS`. If empty or vague, ask the user to describe the symptom or problem.\n\n2. **Locate the problem in the codebase.** Use `Grep`, `Glob`, and `Read` to find the relevant files, functions, configs, and tests. Do not guess — verify every claim with a `file:line` citation.\n\n3. **Diagnose root cause.** Read enough code to understand _why_ the problem occurs, not just _where_. If there are tests, run them to observe the failure. If the issue is behavioural (performance, flakiness), read logs or run diagnostic commands.\n\n4. **Generate at least 2 fix options.** For each option:\n   - Describe the approach concisely\n   - List the files\u002Fcomponents touched\n   - State the trade-offs (complexity, blast radius, test surface, reversibility)\n   - Estimate effort: `low` (\u003C 1 hr), `medium` (1–4 hrs), `high` (> 4 hrs)\n   - Assess risk: `low`, `medium`, `high`\n\n5. **Pick a recommended option** and explain why it best balances correctness, risk, and effort. If options are genuinely tied, say so and flag the deciding factor for the user.\n\n6. **Generate the inspection document** with this structure:\n\n   ```markdown\n   # Inspection: \u003CSubject> — \u003CYYYY-MM-DD>\n\n   \u003COne-sentence description of the problem and its impact.>\n\n   ## Root Cause\n\n   \u003CEvidence-backed explanation of why the problem occurs. Include file:line citations.>\n\n   ## Scope\n\n   Files and components relevant to this problem.\n\n   | File \u002F Component | Role in the problem |\n   | ---------------- | ------------------- |\n   | ...              | ...                 |\n\n   ## Fix Options\n\n   ### Option 1: \u003CName>\n\n   **Approach:** \u003Cdescription>\n   **Files touched:** \u003Clist>\n   **Effort:** low | medium | high\n   **Risk:** low | medium | high\n   **Trade-offs:** \u003Cpros and cons>\n\n   ### Option 2: \u003CName>\n\n   ...\n\n   ## Recommendation\n\n   **Use Option N: \u003CName>**\n\n   \u003C2-3 sentences explaining why this option is best for the current situation.\n   Call out any assumptions (e.g. \"assumes test coverage exists for the path\").>\n\n   ## Next Step\n\n   Run `\u002Ffix-with-evidence \u003Csubject>` using the recommended option,\n   or proceed manually using the approach above.\n   ```\n\n7. **Generate a filename** in the format: `\u003Ctopic-slug>-\u003CYYYY-MM-DD>.md` (e.g. `auth-refresh-race-2026-04-14.md`). Use lowercase kebab-case.\n\n8. **Write the file** to `docs\u002Finspections\u002F\u003Cfilename>`. Create the `docs\u002Finspections\u002F` directory if it doesn't exist.\n\n9. **Report to the user**: show the file path, the root cause in one sentence, and the recommended option. Do not dump the full document into chat.\n\n## Rules\n\n- Every root-cause claim must be backed by a `file:line` citation or command output. No assumptions.\n- Always provide at least 2 distinct fix options. Single-option \"inspections\" are just instructions.\n- Never implement a fix. Surface options and recommend. The user decides.\n- Do not commit the inspection file. Leave it untracked for the user to review.\n- If the problem cannot be localized (e.g. no repro, insufficient context), state that clearly and list what additional information is needed rather than producing a speculative document.\n- Keep the document concise. Tables over prose where possible. No filler.\n",{"name":5,"description":44,"allowed-tools":45,"argument-hint":46},"Investigate a specific problem and surface viable fix paths with trade-offs, saved to docs\u002Finspections\u002F. Triggers on: \"how should I fix\", \"what are my options\", \"investigate before I touch\".\n","Read Grep Glob Bash Write","[problem]","main","91c337164997b99943fbcc64e8e362577b67bc81","examples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fcreate-inspection","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha","I'm a Platform\u002FInfra engineer who happens to work in cybersec and write Go code.","2026-10-26 14:12:51",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add kaiohenricunha\u002Fdotbabel --skill create-inspection",{"tool":60,"command":61},"bunx","bunx skills add kaiohenricunha\u002Fdotbabel --skill create-inspection",{"tool":63,"command":64},"pnpm","pnpm dlx skills add kaiohenricunha\u002Fdotbabel --skill create-inspection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fcreate-inspection\u002FSKILL.md",true,[],[69,100,133,154,176,198],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":80,"publishedAt":39},"01M6XDQ7QMASPFZ355MYKCD06T","yolo","Start temporary autonomy for the current task or an explicit scope with a required --for expiry. Codex permits scoped pushes, merges, deploys, and releases after strict testing and validation; Full access is a separate runtime setting. Claude Code uses a session permission hook with a protected-action denylist.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fyolo\u002FSKILL.md",[75],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[71,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"testing","merge","code","start","access","session","ops","autonomy","releases","permission","full","runtime","scope","devex","hook","true","action","for","scoped",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":114,"publishedAt":39},"01M6XDQ1N21VE4KH98JWGZ7GN9","veracity-audit","Audit a data pipeline for Veracity and Value. Dispatches data-scientist, compliance-auditor, and data-engineer agents with project context injected at dispatch time. All source paths are supplied via flags — no defaults, no project assumptions. Subcommands: audit (full pipeline walk), score-check (scoring math only), gate-check (gate coverage only), source-trace \u003Clabel> (single source end-to-end). Invoke when: \"audit pipeline\", \"veracity check\", \"scoring math correct?\", \"check gates\", \"trace source\", \"verify quality gates\", \"formula correct?\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fveracity-audit\u002FSKILL.md",[106,111],{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":112,"categoryName":113,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000037","律师与法务",[115,116,81,117,118,119,37,120,121,122,123,124,125,126,127,128,129,130,131,132],"audit","veracity audit","review","data pipeline","pipeline","math","coverage","only","engineer","formula","scoring","time","project","worker","end","at","invoke","when",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":39},"01M6XDPVDKBR376C06CEK9BC5S","validate-spec","Audit an already-implemented spec against the codebase. Walks each constraint (ARCH-N, PERF-N, KD-N, etc.) and acceptance criterion, grounds findings in file:line evidence, runs the spec.json acceptance_commands, and writes a single audit doc to docs\u002Faudits\u002F. Use whenever the user asks to \"validate a spec\", \"audit a spec\", \"check if spec is implemented\", \"verify the spec is done\", \"is this spec really done\", or otherwise wants closure on spec-driven work. Read-only against the spec — produces an audit, never modifies the spec itself.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-spec\u002FSKILL.md",[],[140,141,142,81,117,143,144,115,37,145,35,146,122,147,148,149,150,151,152,153],"spec","validate","validate spec","run","acceptance","work","never","max","done","arch","line","2025","spec-driven","closure",{"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":163,"publishedAt":39},"01M6XDPMMECH82RAW553Y94HDS","terragrunt-specialist","Deep-dive Terragrunt hierarchy review, DRY pattern audits, and run-all orchestration analysis. Use for structured investigations of multi-environment Terragrunt layouts, dependency graphs, remote state config, and hook correctness. Triggers on: \"Terragrunt audit\", \"run-all review\", \"dependency block\", \"DRY pattern review\", \"env hierarchy audit\", \"mock_outputs\", \"terragrunt hooks\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fterragrunt-specialist\u002FSKILL.md",[160],{"categoryNo":161,"categoryName":162,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000011","运维与部署",[164,165,166,117,167,168,143,115,169,37,35,170,171,147,172,173,151,174,130,175],"terragrunt","specialist","terragrunt specialist","orchestration","debugging","analysis","dependency","hooks","deep","dry","remote","hierarchy",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":189,"publishedAt":39},"01M6XDPFJS2HGSE13RXF1HV8S7","terraform-specialist","Deep-dive Terraform architecture review, module design, state management, and migration. Use for structured investigations of Terraform workspaces, provider configuration, module coupling, import workflows, and test coverage. Triggers on: \"Terraform audit\", \"module review\", \"state management\", \"Terraform import\", \"workspace design\", \"provider config review\", \"Terraform testing\".","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-specialist\u002FSKILL.md",[182,185,186],{"categoryNo":183,"categoryName":184,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":161,"categoryName":162,"taxonomyType":109,"taxonomyTypeDesc":110},{"categoryNo":187,"categoryName":188,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000015","视觉设计",[190,191,165,81,192,117,193,194,195,168,115,37,35,121,196,197,172,29,151,130],"terraform","terraform specialist","design","workflows","architecture","architecture review","test coverage","workspaces",{"skillNo":199,"name":140,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":207,"publishedAt":39},"01M6XDP7V6H8WYPSXVEKYE6HJ6","Create structured engineering specs through interactive pairing. Use when the user wants to create a spec, design doc, technical specification, architecture document, RFC, or engineering plan. Triggers on \"let's spec this out\", \"create a spec\", \"design doc\", \"write a technical plan\", \"plan the architecture\". Works for greenfield and brownfield projects. Outputs to docs\u002Fspecs\u002F.","https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fspec\u002FSKILL.md",[203,204],{"categoryNo":187,"categoryName":188,"taxonomyType":109,"taxonomyTypeDesc":110},{"categoryNo":205,"categoryName":206,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000032","设计师",[140,192,208,194,19,209,210,34,211,212,213,214,21,215,216,98,23,217,218,219],"component","plan","projects","interactive","use","document","specification","opus","technical specification","technical plan","outputs","frontier"]