[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XD2V956VQA8X4AFBY3CT9B":3,"skill-same:01M6XD2V956VQA8X4AFBY3CT9B":96},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":27,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":57,"updatedAt":58,"install":59,"resources":71},"01M6XD2V956VQA8X4AFBY3CT9B","deploy-status",null,"Show deployed git SHAs across configured production targets and compare them against origin\u002Fmain. Use during deploy verification, incident response, and release drift checks. Triggers on: \"what is deployed\", \"deploy status\", \"production drift\", \"is prod on main\", \"compare prod to main\".","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\u002Fdeploy-status\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"status","deploy status","deploy","main","incident response","false","dry","origin","triggers","across","incident","drift","show","fetch","read","Bash","verification","git","release","run","2026-11-10 10:12:30",false,"---\n# dotbabel:generated projection=sha256:141e8d3ebd24aee7afb9317ed36b375086a12c70040fa1f7d9acd884c0ddd189 source=skills\u002Fdeploy-status\u002FSKILL.md — do not edit directly\nallowed-tools: Read Grep Glob Bash\nargument-hint: \"[--dry-run] [--no-fetch]\"\ndescription: |\n  Show deployed git SHAs across configured production targets and compare them against origin\u002Fmain. Use during deploy verification, incident response, and release drift checks. Triggers on: \"what is deployed\", \"deploy status\", \"production drift\", \"is prod on main\", \"compare prod to main\".\ndisable-model-invocation: false\nname: deploy-status\nuser-invocable: true\n---\n\n# Deploy Status\n\nReport what git revision is live across production deploy targets and whether\neach target matches `origin\u002Fmain`.\n\n## Workflow\n\n1. Resolve the helper script:\n\n   ```bash\n   if [ -f \"$HOME\u002F.claude\u002Fskills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\" ]; then\n     DEPLOY_OPS=\"$HOME\u002F.claude\u002Fskills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\"\n   elif [ -f \"skills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\" ]; then\n     DEPLOY_OPS=\"skills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\"\n   else\n     echo \"deploy-status helper not found; re-run dotbabel bootstrap or dotbabel init\" >&2\n     exit 2\n   fi\n   ```\n\n2. Run the status command from the consuming project root:\n\n   ```bash\n   node \"$DEPLOY_OPS\" status $ARGUMENTS\n   ```\n\n3. Preserve the helper's exit code:\n   - `0` - every target is in sync with `origin\u002Fmain`\n   - `1` - at least one target is behind, ahead, or otherwise drifted\n   - `2` - target discovery, provider auth, provider parsing, or SHA detection failed\n\n## Target Discovery\n\nDiscovery is configuration-first only where auto-discovery cannot prove a target.\nThe helper:\n\n1. Auto-discovers Vercel from `.vercel\u002Fproject.json`.\n2. Auto-discovers Fly.io from top-level `app = \"...\"`\n   in `fly.toml`.\n3. Merges `.claude\u002Fdeploy-targets.json` when present. Config entries override\n   matching auto-discovered targets and add non-discoverable platforms.\n\nExample config: `examples\u002Fdeploy-targets.example.json`.\n\n## Smoke checks\n\nA target in `.claude\u002Fdeploy-targets.json` may declare a `smoke` array, run\nafter a deploy to confirm the thing actually answers:\n\n```bash\nnode \"$DEPLOY_OPS\" smoke            # human-readable\nnode \"$DEPLOY_OPS\" smoke --json     # machine-readable, see schemas\u002Fdotbabel.smoke-report.schema.json\nnode \"$DEPLOY_OPS\" smoke --dry-run  # list the checks without running them\n```\n\nExit codes match the status command: `0` every check passed (or none is\ndeclared, or it was a dry run — neither is a failure), `1` at least one failed\nor the run hit its time budget, `2` target discovery failed.\n\nRead `verdict` rather than inferring success from the exit code: `pass`,\n`fail`, `not_configured` (no target declares checks) and `not_run` (a dry run).\nA dry run also sets `dry_run: true` and reports each planned check with\n`ok: null`, so a stray `--dry-run` in a pipeline cannot be mistaken for a green\ngate over zero executed checks.\n\nTwo check types. An `http` check is **GET only** and retries up to 3 times with\n2s, 4s and 8s backoff; a `command` check runs its `argv` **exactly once**,\nbecause a command may not be idempotent and a retry would repeat a side effect\nnobody agreed to. Each request is aborted after 10 seconds — a timeout is\ntransient, so it is retried on the backoff schedule — and the whole run stops\nafter 300 seconds.\n\n**A check with no `expect_status` defaults to requiring 2xx.** A response\narriving is not the same as a response being good: without that default, a\ncheck declaring no expectations reported green against a hard 500, which turns\nan outage into a passing release gate. Set `expect_status` explicitly when you\nwant a specific non-2xx code.\n\nThese requests go to production and may carry a real credential, so the guards\nare enforced rather than advised:\n\n- A URL with embedded credentials is refused, and is **not** echoed back in the\n  error — the config carrying it is already a committed secret.\n- `https` is required for every host except `localhost` and `127.0.0.1`.\n- Redirects are followed manually, at most 3, and only to the **same https\n  origin**. Handing the response the power to choose the next host is how a\n  secret header reaches somewhere it was never meant to go.\n- A header value is read **only** from a named environment variable\n  (`{ \"env\": \"SMOKE_BEARER\" }`). A literal in the config is refused, and a\n  variable that is unset fails the check rather than quietly sending no header\n  and passing against an anonymous response.\n- Header **names** are reported; values never are. The failing response body is\n  shown truncated and redacted, because an endpoint that echoes the header back\n  would otherwise leak it through the very message reporting the failure.\n- A refusal from any of these guards is never retried: a retry cannot turn it\n  into a pass, and a differing later response would mask it.\n\n```json\n{\n  \"kind\": \"vercel\",\n  \"project\": \"my-app\",\n  \"smoke\": [\n    {\n      \"type\": \"http\",\n      \"url\": \"https:\u002F\u002Fmy-app.example.com\u002Fhealthz\",\n      \"expect_status\": 200,\n      \"expect_text\": \"ok\"\n    },\n    {\n      \"type\": \"http\",\n      \"url\": \"https:\u002F\u002Fmy-app.example.com\u002Fapi\u002Fme\",\n      \"expect_status\": 200,\n      \"headers\": { \"Authorization\": { \"env\": \"SMOKE_BEARER\" } }\n    },\n    { \"type\": \"command\", \"argv\": [\".\u002Fscripts\u002Fsmoke-api.sh\", \"--prod\"] }\n  ]\n}\n```\n\n## Provider References\n\nLoad only the provider notes that match discovered targets:\n\n| Provider    | Reference                   |\n| ----------- | --------------------------- |\n| Vercel      | `references\u002Fvercel.md`      |\n| Fly.io      | `references\u002Ffly.md`         |\n| AWS Amplify | `references\u002Faws-amplify.md` |\n\n## Rules\n\n- Do not prompt for provider tokens. Use the existing CLI auth state\n  (`vercel whoami`, `fly auth whoami`).\n- Do not deploy or roll back from this skill. This skill is read-only except for\n  `git fetch origin main --quiet`.\n- If a provider cannot expose a git SHA, report that target as unknown and exit\n  `2` rather than inventing drift data.\n- On a smoke failure, recommend `\u002Frollback-prod` and stop. The rule floor\n  forbids production changes without explicit instruction, so this skill never\n  rolls back on its own.\n","# Deploy Status\n\nReport what git revision is live across production deploy targets and whether\neach target matches `origin\u002Fmain`.\n\n## Workflow\n\n1. Resolve the helper script:\n\n   ```bash\n   if [ -f \"$HOME\u002F.claude\u002Fskills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\" ]; then\n     DEPLOY_OPS=\"$HOME\u002F.claude\u002Fskills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\"\n   elif [ -f \"skills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\" ]; then\n     DEPLOY_OPS=\"skills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs\"\n   else\n     echo \"deploy-status helper not found; re-run dotbabel bootstrap or dotbabel init\" >&2\n     exit 2\n   fi\n   ```\n\n2. Run the status command from the consuming project root:\n\n   ```bash\n   node \"$DEPLOY_OPS\" status $ARGUMENTS\n   ```\n\n3. Preserve the helper's exit code:\n   - `0` - every target is in sync with `origin\u002Fmain`\n   - `1` - at least one target is behind, ahead, or otherwise drifted\n   - `2` - target discovery, provider auth, provider parsing, or SHA detection failed\n\n## Target Discovery\n\nDiscovery is configuration-first only where auto-discovery cannot prove a target.\nThe helper:\n\n1. Auto-discovers Vercel from `.vercel\u002Fproject.json`.\n2. Auto-discovers Fly.io from top-level `app = \"...\"`\n   in `fly.toml`.\n3. Merges `.claude\u002Fdeploy-targets.json` when present. Config entries override\n   matching auto-discovered targets and add non-discoverable platforms.\n\nExample config: `examples\u002Fdeploy-targets.example.json`.\n\n## Smoke checks\n\nA target in `.claude\u002Fdeploy-targets.json` may declare a `smoke` array, run\nafter a deploy to confirm the thing actually answers:\n\n```bash\nnode \"$DEPLOY_OPS\" smoke            # human-readable\nnode \"$DEPLOY_OPS\" smoke --json     # machine-readable, see schemas\u002Fdotbabel.smoke-report.schema.json\nnode \"$DEPLOY_OPS\" smoke --dry-run  # list the checks without running them\n```\n\nExit codes match the status command: `0` every check passed (or none is\ndeclared, or it was a dry run — neither is a failure), `1` at least one failed\nor the run hit its time budget, `2` target discovery failed.\n\nRead `verdict` rather than inferring success from the exit code: `pass`,\n`fail`, `not_configured` (no target declares checks) and `not_run` (a dry run).\nA dry run also sets `dry_run: true` and reports each planned check with\n`ok: null`, so a stray `--dry-run` in a pipeline cannot be mistaken for a green\ngate over zero executed checks.\n\nTwo check types. An `http` check is **GET only** and retries up to 3 times with\n2s, 4s and 8s backoff; a `command` check runs its `argv` **exactly once**,\nbecause a command may not be idempotent and a retry would repeat a side effect\nnobody agreed to. Each request is aborted after 10 seconds — a timeout is\ntransient, so it is retried on the backoff schedule — and the whole run stops\nafter 300 seconds.\n\n**A check with no `expect_status` defaults to requiring 2xx.** A response\narriving is not the same as a response being good: without that default, a\ncheck declaring no expectations reported green against a hard 500, which turns\nan outage into a passing release gate. Set `expect_status` explicitly when you\nwant a specific non-2xx code.\n\nThese requests go to production and may carry a real credential, so the guards\nare enforced rather than advised:\n\n- A URL with embedded credentials is refused, and is **not** echoed back in the\n  error — the config carrying it is already a committed secret.\n- `https` is required for every host except `localhost` and `127.0.0.1`.\n- Redirects are followed manually, at most 3, and only to the **same https\n  origin**. Handing the response the power to choose the next host is how a\n  secret header reaches somewhere it was never meant to go.\n- A header value is read **only** from a named environment variable\n  (`{ \"env\": \"SMOKE_BEARER\" }`). A literal in the config is refused, and a\n  variable that is unset fails the check rather than quietly sending no header\n  and passing against an anonymous response.\n- Header **names** are reported; values never are. The failing response body is\n  shown truncated and redacted, because an endpoint that echoes the header back\n  would otherwise leak it through the very message reporting the failure.\n- A refusal from any of these guards is never retried: a retry cannot turn it\n  into a pass, and a differing later response would mask it.\n\n```json\n{\n  \"kind\": \"vercel\",\n  \"project\": \"my-app\",\n  \"smoke\": [\n    {\n      \"type\": \"http\",\n      \"url\": \"https:\u002F\u002Fmy-app.example.com\u002Fhealthz\",\n      \"expect_status\": 200,\n      \"expect_text\": \"ok\"\n    },\n    {\n      \"type\": \"http\",\n      \"url\": \"https:\u002F\u002Fmy-app.example.com\u002Fapi\u002Fme\",\n      \"expect_status\": 200,\n      \"headers\": { \"Authorization\": { \"env\": \"SMOKE_BEARER\" } }\n    },\n    { \"type\": \"command\", \"argv\": [\".\u002Fscripts\u002Fsmoke-api.sh\", \"--prod\"] }\n  ]\n}\n```\n\n## Provider References\n\nLoad only the provider notes that match discovered targets:\n\n| Provider    | Reference                   |\n| ----------- | --------------------------- |\n| Vercel      | `references\u002Fvercel.md`      |\n| Fly.io      | `references\u002Ffly.md`         |\n| AWS Amplify | `references\u002Faws-amplify.md` |\n\n## Rules\n\n- Do not prompt for provider tokens. Use the existing CLI auth state\n  (`vercel whoami`, `fly auth whoami`).\n- Do not deploy or roll back from this skill. This skill is read-only except for\n  `git fetch origin main --quiet`.\n- If a provider cannot expose a git SHA, report that target as unknown and exit\n  `2` rather than inventing drift data.\n- On a smoke failure, recommend `\u002Frollback-prod` and stop. The rule floor\n  forbids production changes without explicit instruction, so this skill never\n  rolls back on its own.\n",{"name":5,"description":49,"allowed-tools":50,"argument-hint":51,"user-invocable":52,"disable-model-invocation":45},"Show deployed git SHAs across configured production targets and compare them against origin\u002Fmain. Use during deploy verification, incident response, and release drift checks. Triggers on: \"what is deployed\", \"deploy status\", \"production drift\", \"is prod on main\", \"compare prod to main\".\n","Read Grep Glob Bash","[--dry-run] [--no-fetch]",true,"91c337164997b99943fbcc64e8e362577b67bc81","examples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status","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":60,"prompt":70,"zipAvailable":52},[61,64,67],{"tool":62,"command":63},"npx","npx skills add kaiohenricunha\u002Fdotbabel --skill deploy-status",{"tool":65,"command":66},"bunx","bunx skills add kaiohenricunha\u002Fdotbabel --skill deploy-status",{"tool":68,"command":69},"pnpm","pnpm dlx skills add kaiohenricunha\u002Fdotbabel --skill deploy-status","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status\u002FSKILL.md",[72,78,82,86,90],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"examples\u002Fdeploy-targets.example.json","REFERENCE","参考文档",924,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status\u002Fexamples\u002Fdeploy-targets.example.json",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Faws-amplify.md",566,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status\u002Freferences\u002Faws-amplify.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ffly.md",1121,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status\u002Freferences\u002Ffly.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fvercel.md",1069,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status\u002Freferences\u002Fvercel.md",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fdeploy-ops.mjs","SCRIPT","脚本",45610,"https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fexamples\u002Fminimal-consumer\u002F.claude\u002Fskills\u002Fdeploy-status\u002Fscripts\u002Fdeploy-ops.mjs",[97,128,159,179,198,221],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":108,"publishedAt":44},"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",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[99,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"testing","merge","code","start","access","session","ops","autonomy","releases","permission","full","runtime","scope","devex","hook","true","action","for","scoped",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":140,"publishedAt":44},"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",[134,137],{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":138,"categoryName":139,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000037","律师与法务",[141,142,109,143,144,145,39,146,147,148,149,150,151,152,153,154,155,156,157,158],"audit","veracity audit","review","data pipeline","pipeline","math","coverage","only","engineer","formula","scoring","time","project","worker","end","at","invoke","when",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":44},"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",[],[166,167,168,109,143,43,169,141,39,170,38,171,148,172,173,174,175,176,177,178],"spec","validate","validate spec","acceptance","work","never","max","done","arch","line","2025","spec-driven","closure",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":186,"publishedAt":44},"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",[185],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[187,188,189,143,190,191,43,141,192,39,38,193,194,172,195,30,176,196,156,197],"terragrunt","specialist","terragrunt specialist","orchestration","debugging","analysis","dependency","hooks","deep","remote","hierarchy",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":211,"publishedAt":44},"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",[204,207,208],{"categoryNo":205,"categoryName":206,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":209,"categoryName":210,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[212,213,188,109,214,143,215,216,217,191,141,39,38,147,218,219,195,220,176,156],"terraform","terraform specialist","design","workflows","architecture","architecture review","test coverage","workspaces","problem",{"skillNo":222,"name":166,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":230,"publishedAt":44},"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",[226,227],{"categoryNo":209,"categoryName":210,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":228,"categoryName":229,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000032","设计师",[166,214,231,216,232,233,234,235,236,237,238,239,32,240,241,126,242,243,244,245],"component","create","plan","projects","write","interactive","use","document","specification","opus","technical specification","trade-offs","technical plan","outputs","frontier"]