[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XDGFP312M8Y7Q1WN9051CB":3,"skill-same:01M6XDGFP312M8Y7Q1WN9051CB":87},{"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":66,"commitSha":67,"skillDirectory":68,"forksCount":14,"repositoryHtmlUrl":69,"repositoryHomepageUrl":6,"ownerHtmlUrl":70,"ownerBlogUrl":6,"ownerDescription":71,"updatedAt":72,"install":73,"resources":86},"01M6XDGFP312M8Y7Q1WN9051CB","code-simplifier",null,"Simplify and refine changed code for clarity, consistency, and maintainability while preserving all functionality. PR-scoped by default. Accepts an optional PR number, file glob, or base branch to narrow scope. Triggers on: \"simplify code\", \"code simplifier\", \"clean up the code\", \"simplify the PR\".","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\u002Fcode-simplifier\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"code","code simplifier","simplifier","up","routine","number","sonnet","devex","scope","refine","clean","default","review","edit","read","branch","clarity","Bash","simplify","workflow","2026-11-10 10:12:30",false,"---\nid: code-simplifier\nname: code-simplifier\ntype: skill\nversion: 1.0.0\ndomain:\n  - devex\nplatform:\n  - none\ntask:\n  - review\nmaturity: draft\nowner: \"@kaiohenricunha\"\ncreated: 2026-05-11T00:00:00.000Z\nupdated: 2026-05-11T00:00:00.000Z\ndescription: |\n  Simplify and refine changed code for clarity, consistency, and maintainability while preserving all functionality. PR-scoped by default. Accepts an optional PR number, file glob, or base branch to narrow scope. Triggers on: \"simplify code\", \"code simplifier\", \"clean up the code\", \"simplify the PR\".\nargument-hint: \"[PR# | file-glob | base-branch]\"\ntools: Read, Grep, Glob, Bash, Edit\nmodel: sonnet\ndotbabel:\n  compute:\n    mode: dynamic\n    requirement: routine\n    binding: consumer\n    rationale: Scoped engineering follows an existing implementation or review workflow with checkable results.\n---\n\nSimplify and refine changed code for clarity, consistency, and maintainability while preserving all functionality. PR-scoped by default — operates only on files changed in the current branch.\n\nTrigger: when the user asks to \"simplify code\", \"clean up the code\", \"simplify the PR\", or \"run the code simplifier\". Also triggered directly via `\u002Fcode-simplifier [arg]`.\n\nArguments: `$ARGUMENTS` — optional. Accepts a PR number (e.g. `42`), a file glob (e.g. `src\u002F**\u002F*.ts`), or a base branch (e.g. `origin\u002Fdevelop`). If empty, defaults to files changed vs `origin\u002Fmain`.\n\n## Steps\n\n### 1. Detect scope\n\nDetermine which files to simplify. First, validate `$ARGUMENTS` if provided — reject values that start with `-` or contain shell metacharacters (`; & | > \u003C \\` \\`` \\``); they indicate injection attempts.\n\nIf `$ARGUMENTS` matches `^[0-9]+$` (a PR number), fetch the changed file list:\n\n```bash\ngh pr diff \"$ARGUMENTS\" --name-only\nMERGE_BASE=\"\"  # not applicable for PR# mode\n```\n\nIf `$ARGUMENTS` looks like a file glob (contains `*`, `?`, or `\u002F` without being a valid ref), expand it:\n\n```bash\ngit ls-files -- \"$ARGUMENTS\"\nMERGE_BASE=\"\"  # not applicable for glob mode\n```\n\nIf `$ARGUMENTS` is a branch name or empty, diff against the base:\n\n```bash\nBASE=\"${ARGUMENTS:-origin\u002Fmain}\"\n# Fallback if the specified base doesn't exist\nif ! git rev-parse --verify \"$BASE\" >\u002Fdev\u002Fnull 2>&1; then\n  BASE=$(git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD 2>\u002Fdev\u002Fnull | sed 's|refs\u002Fremotes\u002F||')\n  if [ -z \"$BASE\" ]; then\n    echo \"ERROR: cannot determine base branch. Pass a base branch as argument.\"\n    exit 1\n  fi\nfi\nMERGE_BASE=$(git merge-base HEAD \"$BASE\")\ngit diff \"$MERGE_BASE\" --name-only\n```\n\nFilter to code files only — skip binary files, images, lockfiles (`*.lock`, `package-lock.json`), and any generated artifact paths listed in the project's `CLAUDE.md`. Do not assume project-specific paths.\n\n**Gate:** if zero files are in scope, stop: \"No changed code files detected — nothing to simplify.\"\n\nReport: \"Scope: N files changed.\"\n\n### 2. Read project conventions\n\nRead the project's `CLAUDE.md` (if present) to discover language-specific coding standards, naming conventions, formatting preferences, and any generated-artifact paths to exclude. Do not assume any language or framework — let the project's own instructions guide your simplification choices.\n\nIf no `CLAUDE.md` exists, apply universal simplification principles only.\n\n### 3. Read changed files\n\nRead each file identified in step 1 in full. For large files (>500 lines), focus on the changed hunks by reading the diff:\n\n```bash\n# Branch\u002Fbase mode — $MERGE_BASE is defined\ngit diff \"$MERGE_BASE\" -- \u003Cfile>\n\n# PR# mode — use gh to fetch the hunk\ngh pr diff \"$ARGUMENTS\" -- \u003Cfile>\n```\n\nUse whichever command matches the input mode from step 1.\n\n### 4. Analyze for simplification opportunities\n\nFor each file, identify opportunities to improve clarity without changing behavior:\n\n- **Reduce nesting:** flatten deeply nested if\u002Felse chains, extract early returns\n- **Eliminate redundancy:** remove duplicate logic, consolidate repeated patterns\n- **Improve naming:** rename unclear variables and functions to express intent\n- **Remove dead code:** delete unreachable code, unused imports, commented-out blocks — but only within the changed scope\n- **Simplify control flow:** replace overly clever constructs with straightforward alternatives\n  - Avoid nested ternary operators — prefer switch statements or if\u002Felse chains for multiple conditions\n  - Choose clarity over brevity — explicit code is better than dense one-liners\n- **Consolidate related logic:** group related statements, reduce unnecessary indirection\n- **Remove noise comments:** delete comments that describe what the code obviously does\n\n**Balance:** do not over-simplify. Concrete examples of the boundary:\n\n- ✓ Replace `a ? b : c ? d : e` with an if\u002Felse chain\n- ✓ Extract a guard clause instead of wrapping the entire function body in `if (ok) { ... }`\n- ✗ Don't merge two 5-line functions into one 15-line function to \"reduce files\"\n- ✗ Don't combine unrelated logic to reduce line count\n\nAlso avoid:\n\n- Creating overly clever solutions that are harder to understand\n- Combining too many concerns into single functions\n- Removing helpful abstractions that improve organization\n- Making the code harder to debug or extend\n\n### 5. Apply edits\n\nEdit each file using the Edit tool. One edit per logical simplification — do not batch unrelated changes into a single edit.\n\n**Hard rules:**\n\n- **MUST NOT edit files outside the scope from step 1.** This is the most important guardrail. If a simplification opportunity exists in an unchanged file, mention it in the report but do not touch it.\n- **MUST NOT change behavior.** Only change how the code is expressed, never what it does. All original features, outputs, and behaviors must remain intact.\n- **MUST NOT auto-commit.** Leave changes in the working tree. The user or calling skill (e.g. `\u002Fpre-pr`) decides whether to commit.\n- **MUST NOT add new dependencies, features, or abstractions** beyond what the existing code already uses.\n\n### 6. Report\n\nAfter all edits, provide a concise summary:\n\n```\nCode simplification: \u003Cbranch> (base: \u003Cbase>)\n\n  Files analyzed: N\n  Files modified: M\n  Files skipped:  K (no opportunities found)\n\n  Changes:\n    - \u003Cfile>: \u003Cone-line description of what changed and why>\n    - \u003Cfile>: \u003Cone-line description>\n\n  Out-of-scope opportunities (not applied):\n    - \u003Cfile>:\u003Cline>: \u003Cdescription> (file not in changed set)\n```\n\nIf no simplification opportunities were found: \"Code simplification: clean — no changes needed.\"\n","Simplify and refine changed code for clarity, consistency, and maintainability while preserving all functionality. PR-scoped by default — operates only on files changed in the current branch.\n\nTrigger: when the user asks to \"simplify code\", \"clean up the code\", \"simplify the PR\", or \"run the code simplifier\". Also triggered directly via `\u002Fcode-simplifier [arg]`.\n\nArguments: `$ARGUMENTS` — optional. Accepts a PR number (e.g. `42`), a file glob (e.g. `src\u002F**\u002F*.ts`), or a base branch (e.g. `origin\u002Fdevelop`). If empty, defaults to files changed vs `origin\u002Fmain`.\n\n## Steps\n\n### 1. Detect scope\n\nDetermine which files to simplify. First, validate `$ARGUMENTS` if provided — reject values that start with `-` or contain shell metacharacters (`; & | > \u003C \\` \\`` \\``); they indicate injection attempts.\n\nIf `$ARGUMENTS` matches `^[0-9]+$` (a PR number), fetch the changed file list:\n\n```bash\ngh pr diff \"$ARGUMENTS\" --name-only\nMERGE_BASE=\"\"  # not applicable for PR# mode\n```\n\nIf `$ARGUMENTS` looks like a file glob (contains `*`, `?`, or `\u002F` without being a valid ref), expand it:\n\n```bash\ngit ls-files -- \"$ARGUMENTS\"\nMERGE_BASE=\"\"  # not applicable for glob mode\n```\n\nIf `$ARGUMENTS` is a branch name or empty, diff against the base:\n\n```bash\nBASE=\"${ARGUMENTS:-origin\u002Fmain}\"\n# Fallback if the specified base doesn't exist\nif ! git rev-parse --verify \"$BASE\" >\u002Fdev\u002Fnull 2>&1; then\n  BASE=$(git symbolic-ref refs\u002Fremotes\u002Forigin\u002FHEAD 2>\u002Fdev\u002Fnull | sed 's|refs\u002Fremotes\u002F||')\n  if [ -z \"$BASE\" ]; then\n    echo \"ERROR: cannot determine base branch. Pass a base branch as argument.\"\n    exit 1\n  fi\nfi\nMERGE_BASE=$(git merge-base HEAD \"$BASE\")\ngit diff \"$MERGE_BASE\" --name-only\n```\n\nFilter to code files only — skip binary files, images, lockfiles (`*.lock`, `package-lock.json`), and any generated artifact paths listed in the project's `CLAUDE.md`. Do not assume project-specific paths.\n\n**Gate:** if zero files are in scope, stop: \"No changed code files detected — nothing to simplify.\"\n\nReport: \"Scope: N files changed.\"\n\n### 2. Read project conventions\n\nRead the project's `CLAUDE.md` (if present) to discover language-specific coding standards, naming conventions, formatting preferences, and any generated-artifact paths to exclude. Do not assume any language or framework — let the project's own instructions guide your simplification choices.\n\nIf no `CLAUDE.md` exists, apply universal simplification principles only.\n\n### 3. Read changed files\n\nRead each file identified in step 1 in full. For large files (>500 lines), focus on the changed hunks by reading the diff:\n\n```bash\n# Branch\u002Fbase mode — $MERGE_BASE is defined\ngit diff \"$MERGE_BASE\" -- \u003Cfile>\n\n# PR# mode — use gh to fetch the hunk\ngh pr diff \"$ARGUMENTS\" -- \u003Cfile>\n```\n\nUse whichever command matches the input mode from step 1.\n\n### 4. Analyze for simplification opportunities\n\nFor each file, identify opportunities to improve clarity without changing behavior:\n\n- **Reduce nesting:** flatten deeply nested if\u002Felse chains, extract early returns\n- **Eliminate redundancy:** remove duplicate logic, consolidate repeated patterns\n- **Improve naming:** rename unclear variables and functions to express intent\n- **Remove dead code:** delete unreachable code, unused imports, commented-out blocks — but only within the changed scope\n- **Simplify control flow:** replace overly clever constructs with straightforward alternatives\n  - Avoid nested ternary operators — prefer switch statements or if\u002Felse chains for multiple conditions\n  - Choose clarity over brevity — explicit code is better than dense one-liners\n- **Consolidate related logic:** group related statements, reduce unnecessary indirection\n- **Remove noise comments:** delete comments that describe what the code obviously does\n\n**Balance:** do not over-simplify. Concrete examples of the boundary:\n\n- ✓ Replace `a ? b : c ? d : e` with an if\u002Felse chain\n- ✓ Extract a guard clause instead of wrapping the entire function body in `if (ok) { ... }`\n- ✗ Don't merge two 5-line functions into one 15-line function to \"reduce files\"\n- ✗ Don't combine unrelated logic to reduce line count\n\nAlso avoid:\n\n- Creating overly clever solutions that are harder to understand\n- Combining too many concerns into single functions\n- Removing helpful abstractions that improve organization\n- Making the code harder to debug or extend\n\n### 5. Apply edits\n\nEdit each file using the Edit tool. One edit per logical simplification — do not batch unrelated changes into a single edit.\n\n**Hard rules:**\n\n- **MUST NOT edit files outside the scope from step 1.** This is the most important guardrail. If a simplification opportunity exists in an unchanged file, mention it in the report but do not touch it.\n- **MUST NOT change behavior.** Only change how the code is expressed, never what it does. All original features, outputs, and behaviors must remain intact.\n- **MUST NOT auto-commit.** Leave changes in the working tree. The user or calling skill (e.g. `\u002Fpre-pr`) decides whether to commit.\n- **MUST NOT add new dependencies, features, or abstractions** beyond what the existing code already uses.\n\n### 6. Report\n\nAfter all edits, provide a concise summary:\n\n```\nCode simplification: \u003Cbranch> (base: \u003Cbase>)\n\n  Files analyzed: N\n  Files modified: M\n  Files skipped:  K (no opportunities found)\n\n  Changes:\n    - \u003Cfile>: \u003Cone-line description of what changed and why>\n    - \u003Cfile>: \u003Cone-line description>\n\n  Out-of-scope opportunities (not applied):\n    - \u003Cfile>:\u003Cline>: \u003Cdescription> (file not in changed set)\n```\n\nIf no simplification opportunities were found: \"Code simplification: clean — no changes needed.\"\n",{"id":5,"name":5,"task":49,"type":50,"model":30,"owner":51,"tools":52,"domain":53,"created":54,"updated":54,"version":55,"dotbabel":56,"maturity":61,"platform":62,"description":64,"argument-hint":65},[36],"skill","@kaiohenricunha","Read, Grep, Glob, Bash, Edit",[31],1778457600000,"1.0.0",{"compute":57},{"mode":58,"binding":59,"rationale":60,"requirement":28},"dynamic","consumer","Scoped engineering follows an existing implementation or review workflow with checkable results.","draft",[63],"none","Simplify and refine changed code for clarity, consistency, and maintainability while preserving all functionality. PR-scoped by default. Accepts an optional PR number, file glob, or base branch to narrow scope. Triggers on: \"simplify code\", \"code simplifier\", \"clean up the code\", \"simplify the PR\".\n","[PR# | file-glob | base-branch]","main","91c337164997b99943fbcc64e8e362577b67bc81","skills\u002Fcode-simplifier","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":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add kaiohenricunha\u002Fdotbabel --skill code-simplifier",{"tool":79,"command":80},"bunx","bunx skills add kaiohenricunha\u002Fdotbabel --skill code-simplifier",{"tool":82,"command":83},"pnpm","pnpm dlx skills add kaiohenricunha\u002Fdotbabel --skill code-simplifier","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkaiohenricunha\u002Fdotbabel\u002Fblob\u002Fmain\u002Fskills\u002Fcode-simplifier\u002FSKILL.md",true,[],[88,112,144,165,187,210],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":95,"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",[94],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[90,96,97,24,98,99,100,101,102,103,104,105,106,32,31,107,108,109,110,111],"testing","merge","start","access","session","ops","autonomy","releases","permission","full","runtime","hook","true","action","for","scoped",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":126,"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",[118,123],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000037","律师与法务",[127,128,96,36,129,130,41,131,132,133,134,135,136,137,138,139,140,141,142,143],"audit","veracity audit","data pipeline","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":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",[],[151,152,153,96,36,154,155,127,41,156,38,157,133,158,159,160,161,162,163,164],"spec","validate","validate spec","run","acceptance","work","never","max","done","arch","line","2025","spec-driven","closure",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":174,"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",[171],{"categoryNo":172,"categoryName":173,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000011","运维与部署",[175,176,177,36,178,179,154,127,180,41,38,181,182,158,183,184,162,185,141,186],"terragrunt","specialist","terragrunt specialist","orchestration","debugging","analysis","dependency","hooks","deep","dry","remote","hierarchy",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":200,"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",[193,196,197],{"categoryNo":194,"categoryName":195,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":172,"categoryName":173,"taxonomyType":121,"taxonomyTypeDesc":122},{"categoryNo":198,"categoryName":199,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000015","视觉设计",[201,202,176,96,203,36,204,205,206,179,127,41,38,132,207,208,183,209,162,141],"terraform","terraform specialist","design","workflows","architecture","architecture review","test coverage","workspaces","problem",{"skillNo":211,"name":151,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":219,"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",[215,216],{"categoryNo":198,"categoryName":199,"taxonomyType":121,"taxonomyTypeDesc":122},{"categoryNo":217,"categoryName":218,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",[151,203,220,205,221,222,223,224,225,226,227,228,229,230,231,110,232,233,234,235],"component","create","plan","projects","write","interactive","use","document","specification","triggers","opus","technical specification","trade-offs","technical plan","outputs","frontier"]