[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XDG1PXM4CKF3VS0P1VDJ5S":3,"skill-same:01M6XDG1PXM4CKF3VS0P1VDJ5S":83},{"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":62,"commitSha":63,"skillDirectory":64,"forksCount":14,"repositoryHtmlUrl":65,"repositoryHomepageUrl":6,"ownerHtmlUrl":66,"ownerBlogUrl":6,"ownerDescription":67,"updatedAt":68,"install":69,"resources":82},"01M6XDG1PXM4CKF3VS0P1VDJ5S","audit-and-fix",null,"Run an audit-then-implement pipeline: produce an audit, cluster findings into PR-sized chunks, and spawn parallel subagents to implement fixes as draft PRs. Triggers on: \"audit and fix\", \"clean up domain\", \"overnight cleanup\".","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\u002Fskills\u002Faudit-and-fix\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"audit and fix","audit","fix","subagents","chunks","overnight","opus","2025","devex","wed","clean","up","review","spawn","read","Bash","pipeline","run","cleanup","debugging","2026-11-10 10:12:30",false,"---\nid: audit-and-fix\nname: audit-and-fix\ntype: skill\nversion: 1.0.0\ndomain:\n  - devex\nplatform:\n  - none\ntask:\n  - review\n  - debugging\nmaturity: validated\nowner: \"@kaiohenricunha\"\ncreated: 2025-01-01T00:00:00.000Z\nupdated: 2026-04-17T00:00:00.000Z\ndescription: |\n  Run an audit-then-implement pipeline: produce an audit, cluster findings into PR-sized chunks, and spawn parallel subagents to implement fixes as draft PRs. Triggers on: \"audit and fix\", \"clean up domain\", \"overnight cleanup\".\nargument-hint: \"[domain]\"\ntools: Read, Grep, Glob, Bash\nmodel: opus\ndotbabel:\n  compute:\n    mode: floor\n    requirement: frontier\n    binding: consumer\n---\n\nRun a long-horizon audit-then-implement pipeline: produce a structured audit, cluster findings into PR-sized chunks, and spawn parallel subagents to implement fixes as draft PRs.\n\nTrigger: when the user asks for \"audit and fix\", wants to clean up a domain, or kicks off an overnight cleanup run. Also triggered directly via `\u002Faudit-and-fix \u003Cdomain>`.\n\nArguments: `$ARGUMENTS` — the audit domain (e.g. \"hardcoded business logic\", \"unused exports in moneyballer\u002Fpkg\u002Fdb\", \"deprecated Storage API calls\"). Required — if empty, ask the user.\n\n## Steps\n\n1. **Run the audit.** Invoke the `\u002Fcreate-audit` skill. This produces `docs\u002Faudits\u002F\u003Ctopic-slug>-\u003CYYYY-MM-DD>.md` with Findings and Issues tables. Commit the audit file on a new branch `audit\u002F\u003Ctopic-slug>-\u003Cdate>` and push.\n\n2. **Cluster findings into PR groups.** Read the audit's Issues table and group findings by:\n   - Same file or package → same cluster\n   - Same severity AND same fix pattern → same cluster\n   - Cross-cutting infra changes (test harness, CI config) → their own cluster\n\n   Produce **4–8 clusters**, not 30 single-finding PRs. Each cluster is one PR. Print the clustering plan as a table before dispatching:\n\n   | Cluster | Findings | Blast Radius | Recommended Title                 |\n   | ------- | -------- | ------------ | --------------------------------- |\n   | 1       | 3        | low          | \"Remove unused exports in pkg\u002Fdb\" |\n\n3. **Initialize the status file.**\n\n   ```markdown\n   # Audit-and-Fix Status — \u003Ctopic> — \u003CYYYY-MM-DD>\n\n   Audit: docs\u002Faudits\u002F\u003Ctopic-slug>-\u003Cdate>.md\n\n   | Cluster | PR  | Branch | State   | Last Update |\n   | ------- | --- | ------ | ------- | ----------- |\n   | 1       | —   | —      | pending | \u003Ctimestamp> |\n   ```\n\n   Write to `docs\u002Faudits\u002F\u003Ctopic-slug>-\u003Cdate>-status.md`.\n\n4. **Dispatch parallel cluster implementers.** Use the `Agent` tool with `subagent_type: \"general-purpose\"` in a **single message with multiple tool calls** — one agent per cluster, cap at 6 concurrent. Each subagent receives:\n   - The audit file path and the specific findings in its cluster\n   - Instructions: create a worktree off `main`, implement the fixes, write or update tests, open a **draft** PR with required sections (Summary, Test plan, Spec ID if applicable), wait for CI, address Copilot comments autonomously\n   - A strict rule: **never merge.** Leave the PR as draft when done.\n   - Required output: `{cluster, pr_url, branch, final_state}` where `final_state ∈ {ready, ci-failing, review-pending, blocked}`\n\n5. **Monitor and update the status file** every 5 minutes while subagents run. For each cluster, record: PR URL, branch, current state, last-update timestamp. If a subagent fails (worktree disappears, CI times out), mark its cluster `blocked` and record the reason rather than retrying silently.\n\n6. **Post the final summary table** when all clusters reach `ready` or `blocked`:\n\n   | Cluster | PR   | State   | Notes                         |\n   | ------- | ---- | ------- | ----------------------------- |\n   | 1       | #201 | ready   | 0 Copilot comments            |\n   | 2       | #202 | blocked | rebase conflict on pkg\u002Ffoo.go |\n\n   Do not merge. The user decides which PRs to merge (use `\u002Fmerge-pr` per PR).\n\n## Rules\n\n- Never merge. This command produces draft PRs only.\n- Never force-push. Never use destructive git operations in subagents.\n- If a worktree path disappears mid-run, recreate it — do not fail the whole run.\n- Cap parallelism at 6 concurrent subagents. Batch the rest.\n- Every draft PR must include the audit file path in its Summary section so reviewers can trace the finding.\n- Keep the status file updated even on failures — silence is worse than partial information.\n- If clustering produces more than 8 PRs, STOP and ask the user to narrow the audit scope.\n\n## Compute scope\n\nThe Frontier floor describes the coordinator's consumer requirement. Native skill\nfrontmatter does not enforce that floor. Keep the existing general-purpose worker\ndispatch, inheritance, tools, worktrees and draft-only merge prohibition. This\ndeclaration adds no enforced worker-floor guarantee and does not set a worker's\nmodel or effort. Report coordinator and worker observations separately when they\nare available; an unavailable observation remains unknown.\n","Run a long-horizon audit-then-implement pipeline: produce a structured audit, cluster findings into PR-sized chunks, and spawn parallel subagents to implement fixes as draft PRs.\n\nTrigger: when the user asks for \"audit and fix\", wants to clean up a domain, or kicks off an overnight cleanup run. Also triggered directly via `\u002Faudit-and-fix \u003Cdomain>`.\n\nArguments: `$ARGUMENTS` — the audit domain (e.g. \"hardcoded business logic\", \"unused exports in moneyballer\u002Fpkg\u002Fdb\", \"deprecated Storage API calls\"). Required — if empty, ask the user.\n\n## Steps\n\n1. **Run the audit.** Invoke the `\u002Fcreate-audit` skill. This produces `docs\u002Faudits\u002F\u003Ctopic-slug>-\u003CYYYY-MM-DD>.md` with Findings and Issues tables. Commit the audit file on a new branch `audit\u002F\u003Ctopic-slug>-\u003Cdate>` and push.\n\n2. **Cluster findings into PR groups.** Read the audit's Issues table and group findings by:\n   - Same file or package → same cluster\n   - Same severity AND same fix pattern → same cluster\n   - Cross-cutting infra changes (test harness, CI config) → their own cluster\n\n   Produce **4–8 clusters**, not 30 single-finding PRs. Each cluster is one PR. Print the clustering plan as a table before dispatching:\n\n   | Cluster | Findings | Blast Radius | Recommended Title                 |\n   | ------- | -------- | ------------ | --------------------------------- |\n   | 1       | 3        | low          | \"Remove unused exports in pkg\u002Fdb\" |\n\n3. **Initialize the status file.**\n\n   ```markdown\n   # Audit-and-Fix Status — \u003Ctopic> — \u003CYYYY-MM-DD>\n\n   Audit: docs\u002Faudits\u002F\u003Ctopic-slug>-\u003Cdate>.md\n\n   | Cluster | PR  | Branch | State   | Last Update |\n   | ------- | --- | ------ | ------- | ----------- |\n   | 1       | —   | —      | pending | \u003Ctimestamp> |\n   ```\n\n   Write to `docs\u002Faudits\u002F\u003Ctopic-slug>-\u003Cdate>-status.md`.\n\n4. **Dispatch parallel cluster implementers.** Use the `Agent` tool with `subagent_type: \"general-purpose\"` in a **single message with multiple tool calls** — one agent per cluster, cap at 6 concurrent. Each subagent receives:\n   - The audit file path and the specific findings in its cluster\n   - Instructions: create a worktree off `main`, implement the fixes, write or update tests, open a **draft** PR with required sections (Summary, Test plan, Spec ID if applicable), wait for CI, address Copilot comments autonomously\n   - A strict rule: **never merge.** Leave the PR as draft when done.\n   - Required output: `{cluster, pr_url, branch, final_state}` where `final_state ∈ {ready, ci-failing, review-pending, blocked}`\n\n5. **Monitor and update the status file** every 5 minutes while subagents run. For each cluster, record: PR URL, branch, current state, last-update timestamp. If a subagent fails (worktree disappears, CI times out), mark its cluster `blocked` and record the reason rather than retrying silently.\n\n6. **Post the final summary table** when all clusters reach `ready` or `blocked`:\n\n   | Cluster | PR   | State   | Notes                         |\n   | ------- | ---- | ------- | ----------------------------- |\n   | 1       | #201 | ready   | 0 Copilot comments            |\n   | 2       | #202 | blocked | rebase conflict on pkg\u002Ffoo.go |\n\n   Do not merge. The user decides which PRs to merge (use `\u002Fmerge-pr` per PR).\n\n## Rules\n\n- Never merge. This command produces draft PRs only.\n- Never force-push. Never use destructive git operations in subagents.\n- If a worktree path disappears mid-run, recreate it — do not fail the whole run.\n- Cap parallelism at 6 concurrent subagents. Batch the rest.\n- Every draft PR must include the audit file path in its Summary section so reviewers can trace the finding.\n- Keep the status file updated even on failures — silence is worse than partial information.\n- If clustering produces more than 8 PRs, STOP and ask the user to narrow the audit scope.\n\n## Compute scope\n\nThe Frontier floor describes the coordinator's consumer requirement. Native skill\nfrontmatter does not enforce that floor. Keep the existing general-purpose worker\ndispatch, inheritance, tools, worktrees and draft-only merge prohibition. This\ndeclaration adds no enforced worker-floor guarantee and does not set a worker's\nmodel or effort. Report coordinator and worker observations separately when they\nare available; an unavailable observation remains unknown.\n",{"id":5,"name":5,"task":44,"type":45,"model":25,"owner":46,"tools":47,"domain":48,"created":49,"updated":50,"version":51,"dotbabel":52,"maturity":57,"platform":58,"description":60,"argument-hint":61},[31,38],"skill","@kaiohenricunha","Read, Grep, Glob, Bash",[27],1735689600000,1776384000000,"1.0.0",{"compute":53},{"mode":54,"binding":55,"requirement":56},"floor","consumer","frontier","validated",[59],"none","Run an audit-then-implement pipeline: produce an audit, cluster findings into PR-sized chunks, and spawn parallel subagents to implement fixes as draft PRs. Triggers on: \"audit and fix\", \"clean up domain\", \"overnight cleanup\".\n","[domain]","main","91c337164997b99943fbcc64e8e362577b67bc81","skills\u002Faudit-and-fix","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":70,"prompt":80,"zipAvailable":81},[71,74,77],{"tool":72,"command":73},"npx","npx skills add kaiohenricunha\u002Fdotbabel --skill audit-and-fix",{"tool":75,"command":76},"bunx","bunx skills add kaiohenricunha\u002Fdotbabel --skill audit-and-fix",{"tool":78,"command":79},"pnpm","pnpm dlx skills add kaiohenricunha\u002Fdotbabel --skill audit-and-fix","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Faudit-and-fix\u002FSKILL.md",true,[],[84,114,144,163,184,207],{"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},"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",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[86,96,97,98,99,100,101,102,103,104,105,106,107,108,27,109,110,111,112,113],"testing","merge","code","start","access","session","ops","autonomy","releases","permission","full","runtime","scope","hook","true","action","for","scoped",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":128,"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",[120,125],{"categoryNo":121,"categoryName":122,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":126,"categoryName":127,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000037","律师与法务",[20,129,96,31,130,35,34,131,132,133,134,135,136,137,138,139,140,141,142,143],"veracity audit","data pipeline","math","coverage","only","engineer","formula","scoring","time","project","worker","end","at","invoke","when",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"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",[],[151,152,153,96,31,36,154,20,34,155,33,156,133,157,158,159,160,26,161,162],"spec","validate","validate spec","acceptance","work","never","max","done","arch","line","spec-driven","closure",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":172,"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",[169],{"categoryNo":170,"categoryName":171,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000011","运维与部署",[173,174,175,31,176,38,36,20,177,34,33,178,179,157,180,181,26,182,141,183],"terragrunt","specialist","terragrunt specialist","orchestration","analysis","dependency","hooks","deep","dry","remote","hierarchy",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":197,"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",[190,193,194],{"categoryNo":191,"categoryName":192,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":170,"categoryName":171,"taxonomyType":123,"taxonomyTypeDesc":124},{"categoryNo":195,"categoryName":196,"taxonomyType":123,"taxonomyTypeDesc":124},"01JBSEEDCAT000000000000015","视觉设计",[198,199,174,96,200,31,201,202,203,38,20,34,33,132,204,205,180,206,26,141],"terraform","terraform specialist","design","workflows","architecture","architecture review","test coverage","workspaces","problem",{"skillNo":208,"name":151,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":216,"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",[212,213],{"categoryNo":195,"categoryName":196,"taxonomyType":123,"taxonomyTypeDesc":124},{"categoryNo":214,"categoryName":215,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000032","设计师",[151,200,217,202,218,219,220,221,222,223,224,225,226,25,227,112,228,229,230,56],"component","create","plan","projects","write","interactive","use","document","specification","triggers","technical specification","trade-offs","technical plan","outputs"]