[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QJ4NMNWDVV1NMRXFJ817KB":3,"skill-same:01M6QJ4NMNWDVV1NMRXFJ817KB":81},{"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":33,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":13,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":66,"install":67,"resources":80},"01M6QJ4NMNWDVV1NMRXFJ817KB","staged-code-review",null,"Comprehensive pre-commit review of git staged changes. Performs tech-stack-aware code quality checks and generates conventional commit messages. Should be used when the user is about to commit code and wants a quality gate — catching debug leftovers, sensitive data, missing error handling before they enter the repository. Distinguished from frontend-code-review which reviews general code quality, this skill focuses specifically on git staged changes pre-commit.","ImaginerLabs\u002Fskill-manager","ImaginerLabs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F214277308?v=4","01M6QGGDPNF15RMMT1RCFDH9FN","01M6QGGDTH5BY64DQ123NR8M33",0,"MIT","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Fcoding\u002Fstaged-code-review\u002FSKILL.md",[17,22,25,28],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"staged code review","review","code","staged","code review","data","commit code","which","reviews","error","coding","commit messages","stack","conventional commit","messages","repository","code-review","git","commit","frontend","2026-11-10 10:12:30",false,"---\nname: staged-code-review\ndescription: >-\n  Comprehensive pre-commit review of git staged changes. Performs tech-stack-aware code quality checks and generates\n  conventional commit messages. Should be used when the user is about to commit code and wants a quality gate —\n  catching debug leftovers, sensitive data, missing error handling before they enter the repository.\n  Distinguished from frontend-code-review which reviews general code quality, this skill focuses specifically\n  on git staged changes pre-commit.\ncategory: coding\nboundary:\n  vs_frontend-code-review: \"frontend-code-review covers general code quality, this skill focuses specifically on git staged changes pre-commit\"\n---\n\n# Git Staged Code Review\n\n## Core Capability\n\nBefore `git commit`, review all staged changes for quality issues and generate a conventional commit message. This is the last quality gate — catching problems here is far cheaper than finding them in production or during PR review.\n\n## When to Use\n\n- The last quality checkpoint before `git commit`\n- When linking requirement IDs, Story IDs to commit records\n- Tech-stack-differentiated code checks in multi-stack projects\n- Local checks before CI\u002FCD pipeline\n\n## Workflow\n\n### Step 1: Read Staged Diff\n\n```bash\ngit diff --staged\ngit diff --staged --name-only\n```\n\n**Pre-check**: If staging area is empty, prompt the user to run `git add` first.\n\n### Step 2: Identify Tech Stack\n\nAuto-detect based on changed file extensions and content:\n\n| File signature                                     | Tech stack         | Applied rules                                 |\n| -------------------------------------------------- | ------------------ | --------------------------------------------- |\n| `*.tsx` \u002F `*.jsx` \u002F `*.ts` \u002F `*.js` + React import | React \u002F TypeScript | Stale closures, Hook deps, render performance |\n| `*.vue`                                            | Vue                | Reactive traps, lifecycle side effects        |\n| `*.go`                                             | Go                 | Error handling, goroutine leaks               |\n| `*.py`                                             | Python             | Exception handling, type annotations          |\n| `*.java` \u002F `*.kt`                                  | Java \u002F Kotlin      | Null pointers, resource release               |\n| `*.rs`                                             | Rust               | Ownership, lifetimes                          |\n\n### Step 3: Execute Code Review\n\n#### Universal Checks\n\n- **Debug code**: Leftover `console.log`, `debugger`, `print`, unhandled `TODO`\n- **Sensitive data**: Hardcoded passwords, tokens, keys, internal addresses\n- **Comment quality**: Remove meaningless comments; complex logic must have explanatory comments\n- **Error handling**: New async\u002FIO operations must have error handling\n- **Boundary conditions**: Null, empty arrays, extreme inputs must be guarded\n\n#### React\u002FTypeScript Specific Checks\n\n- Hook dependency arrays complete (exhaustive-deps)\n- Objects\u002Ffunctions passed to children wrapped in useMemo \u002F useCallback\n- useEffect has corresponding cleanup function\n- List rendering key uses stable unique ID\n- New Props have TypeScript type definitions\n\n### Step 4: Parse User Parameters\n\n| Parameter format    | Meaning           | Message example                           |\n| ------------------- | ----------------- | ----------------------------------------- |\n| `--story=STORY-123` | Link Story ID     | `feat: xxx\\n\\nStory: STORY-123`           |\n| `--task=TASK-456`   | Link Task ID      | `feat: xxx\\n\\nTask: TASK-456`             |\n| `--fix=BUG-789`     | Link Bug ID       | `fix: xxx\\n\\nFixes: BUG-789`              |\n| `--review`          | Force review mode | No auto-commit, only output review report |\n\n### Step 5: Decide Next Steps Based on Review Results\n\n| Conclusion                                  | Action                                              |\n| ------------------------------------------- | --------------------------------------------------- |\n| ✅ **Pass**: No blocking issues             | Generate commit message, ask user whether to commit |\n| ⚠️ **Warning**: Suggestions but no blockers | List suggestions, ask user whether to proceed       |\n| ❌ **Fail**: Blocking issues exist          | List must-fix issues, **do not commit**             |\n\n**Blocking issues (must fix before commit):**\n\n- Hardcoded passwords, tokens, private keys\n- Leftover `debugger` statements\n- Code that could cause security vulnerabilities (XSS, SQL injection, etc.)\n\n---\n\n## Commit Message Convention\n\nFollows [Conventional Commits](https:\u002F\u002Fwww.conventionalcommits.org\u002F):\n\n```\n\u003Ctype>(\u003Cscope>): \u003Csubject>\n\n[body]\n\n[footer]\n```\n\n**Type options:**\n\n| type       | Use case                           | Example                                        |\n| ---------- | ---------------------------------- | ---------------------------------------------- |\n| `feat`     | New feature                        | `feat(user): add avatar upload`                |\n| `fix`      | Bug fix                            | `fix(cart): fix quantity calculation error`    |\n| `refactor` | Refactoring                        | `refactor(utils): refactor utility functions`  |\n| `perf`     | Performance optimization           | `perf(list): optimize list render performance` |\n| `style`    | Code formatting                    | `style: unify code indentation`                |\n| `test`     | Testing                            | `test(user): add login unit tests`             |\n| `chore`    | Build\u002Ftoolchain\u002Fdependency updates | `chore: upgrade dependencies`                  |\n| `docs`     | Documentation changes              | `docs: update API docs`                        |\n\n---\n\n## Output Format\n\n```markdown\n## Staged Code Review Report\n\n### Review Overview\n\n- **Changed files**: X\n- **Tech stack**: [detected]\n- **Conclusion**: ✅ Pass \u002F ⚠️ Warning \u002F ❌ Fail\n\n### Universal Checks\n\n| Check               | Status            | Notes            |\n| ------------------- | ----------------- | ---------------- |\n| Debug code          | ✅ PASS \u002F ❌ FAIL | [specific issue] |\n| Sensitive data      | ✅ PASS \u002F ❌ FAIL | [specific issue] |\n| Error handling      | ✅ PASS \u002F ⚠️ WARN | [specific issue] |\n| Boundary conditions | ✅ PASS \u002F ⚠️ WARN | [specific issue] |\n\n### Issue List\n\n#### ❌ Blocking Issues (must fix)\n\n- `filename:line`: [issue] → [fix suggestion]\n\n#### ⚠️ Suggestions (optional)\n\n- `filename:line`: [issue] → [optimization suggestion]\n\n### Commit Message\n```\n\n[type]([scope]): [subject]\n\n[body (if any)]\n\n[footer (if any, including linked parameters)]\n\n```\n\n### Next Steps\n\n- [ ] Commit directly (review passed)\n- [ ] Fix and re-review\n- [ ] Abort this commit\n```\n","# Git Staged Code Review\n\n## Core Capability\n\nBefore `git commit`, review all staged changes for quality issues and generate a conventional commit message. This is the last quality gate — catching problems here is far cheaper than finding them in production or during PR review.\n\n## When to Use\n\n- The last quality checkpoint before `git commit`\n- When linking requirement IDs, Story IDs to commit records\n- Tech-stack-differentiated code checks in multi-stack projects\n- Local checks before CI\u002FCD pipeline\n\n## Workflow\n\n### Step 1: Read Staged Diff\n\n```bash\ngit diff --staged\ngit diff --staged --name-only\n```\n\n**Pre-check**: If staging area is empty, prompt the user to run `git add` first.\n\n### Step 2: Identify Tech Stack\n\nAuto-detect based on changed file extensions and content:\n\n| File signature                                     | Tech stack         | Applied rules                                 |\n| -------------------------------------------------- | ------------------ | --------------------------------------------- |\n| `*.tsx` \u002F `*.jsx` \u002F `*.ts` \u002F `*.js` + React import | React \u002F TypeScript | Stale closures, Hook deps, render performance |\n| `*.vue`                                            | Vue                | Reactive traps, lifecycle side effects        |\n| `*.go`                                             | Go                 | Error handling, goroutine leaks               |\n| `*.py`                                             | Python             | Exception handling, type annotations          |\n| `*.java` \u002F `*.kt`                                  | Java \u002F Kotlin      | Null pointers, resource release               |\n| `*.rs`                                             | Rust               | Ownership, lifetimes                          |\n\n### Step 3: Execute Code Review\n\n#### Universal Checks\n\n- **Debug code**: Leftover `console.log`, `debugger`, `print`, unhandled `TODO`\n- **Sensitive data**: Hardcoded passwords, tokens, keys, internal addresses\n- **Comment quality**: Remove meaningless comments; complex logic must have explanatory comments\n- **Error handling**: New async\u002FIO operations must have error handling\n- **Boundary conditions**: Null, empty arrays, extreme inputs must be guarded\n\n#### React\u002FTypeScript Specific Checks\n\n- Hook dependency arrays complete (exhaustive-deps)\n- Objects\u002Ffunctions passed to children wrapped in useMemo \u002F useCallback\n- useEffect has corresponding cleanup function\n- List rendering key uses stable unique ID\n- New Props have TypeScript type definitions\n\n### Step 4: Parse User Parameters\n\n| Parameter format    | Meaning           | Message example                           |\n| ------------------- | ----------------- | ----------------------------------------- |\n| `--story=STORY-123` | Link Story ID     | `feat: xxx\\n\\nStory: STORY-123`           |\n| `--task=TASK-456`   | Link Task ID      | `feat: xxx\\n\\nTask: TASK-456`             |\n| `--fix=BUG-789`     | Link Bug ID       | `fix: xxx\\n\\nFixes: BUG-789`              |\n| `--review`          | Force review mode | No auto-commit, only output review report |\n\n### Step 5: Decide Next Steps Based on Review Results\n\n| Conclusion                                  | Action                                              |\n| ------------------------------------------- | --------------------------------------------------- |\n| ✅ **Pass**: No blocking issues             | Generate commit message, ask user whether to commit |\n| ⚠️ **Warning**: Suggestions but no blockers | List suggestions, ask user whether to proceed       |\n| ❌ **Fail**: Blocking issues exist          | List must-fix issues, **do not commit**             |\n\n**Blocking issues (must fix before commit):**\n\n- Hardcoded passwords, tokens, private keys\n- Leftover `debugger` statements\n- Code that could cause security vulnerabilities (XSS, SQL injection, etc.)\n\n---\n\n## Commit Message Convention\n\nFollows [Conventional Commits](https:\u002F\u002Fwww.conventionalcommits.org\u002F):\n\n```\n\u003Ctype>(\u003Cscope>): \u003Csubject>\n\n[body]\n\n[footer]\n```\n\n**Type options:**\n\n| type       | Use case                           | Example                                        |\n| ---------- | ---------------------------------- | ---------------------------------------------- |\n| `feat`     | New feature                        | `feat(user): add avatar upload`                |\n| `fix`      | Bug fix                            | `fix(cart): fix quantity calculation error`    |\n| `refactor` | Refactoring                        | `refactor(utils): refactor utility functions`  |\n| `perf`     | Performance optimization           | `perf(list): optimize list render performance` |\n| `style`    | Code formatting                    | `style: unify code indentation`                |\n| `test`     | Testing                            | `test(user): add login unit tests`             |\n| `chore`    | Build\u002Ftoolchain\u002Fdependency updates | `chore: upgrade dependencies`                  |\n| `docs`     | Documentation changes              | `docs: update API docs`                        |\n\n---\n\n## Output Format\n\n```markdown\n## Staged Code Review Report\n\n### Review Overview\n\n- **Changed files**: X\n- **Tech stack**: [detected]\n- **Conclusion**: ✅ Pass \u002F ⚠️ Warning \u002F ❌ Fail\n\n### Universal Checks\n\n| Check               | Status            | Notes            |\n| ------------------- | ----------------- | ---------------- |\n| Debug code          | ✅ PASS \u002F ❌ FAIL | [specific issue] |\n| Sensitive data      | ✅ PASS \u002F ❌ FAIL | [specific issue] |\n| Error handling      | ✅ PASS \u002F ⚠️ WARN | [specific issue] |\n| Boundary conditions | ✅ PASS \u002F ⚠️ WARN | [specific issue] |\n\n### Issue List\n\n#### ❌ Blocking Issues (must fix)\n\n- `filename:line`: [issue] → [fix suggestion]\n\n#### ⚠️ Suggestions (optional)\n\n- `filename:line`: [issue] → [optimization suggestion]\n\n### Commit Message\n```\n\n[type]([scope]): [subject]\n\n[body (if any)]\n\n[footer (if any, including linked parameters)]\n\n```\n\n### Next Steps\n\n- [ ] Commit directly (review passed)\n- [ ] Fix and re-review\n- [ ] Abort this commit\n```\n",{"name":5,"boundary":59,"category":44,"description":7},{"vs_frontend-code-review":60},"frontend-code-review covers general code quality, this skill focuses specifically on git staged changes pre-commit","main","b9a52d8e27455bdad953d64928696d028223ea1b","skills\u002Fcoding\u002Fstaged-code-review","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager","https:\u002F\u002Fgithub.com\u002FImaginerLabs","2026-04-18 16:27:13",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add ImaginerLabs\u002Fskill-manager --skill staged-code-review",{"tool":73,"command":74},"bunx","bunx skills add ImaginerLabs\u002Fskill-manager --skill staged-code-review",{"tool":76,"command":77},"pnpm","pnpm dlx skills add ImaginerLabs\u002Fskill-manager --skill staged-code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Fcoding\u002Fstaged-code-review\u002FSKILL.md",true,[],[82,111,132,160,187,211],{"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":92,"publishedAt":54},"01M6QJCB2SD5KHC41ZDQC0GA1T","meeting-minutes","Generate concise, actionable meeting minutes for internal meetings. Includes metadata, attendees, agenda, decisions, action items (owner + due date), and follow-up steps.","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fmeeting-minutes\u002FSKILL.md",[88,89],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":90,"categoryName":91,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000034","行政与办公人员",[93,94,95,96,97,98,99,100,101,102,84,61,103,104,105,106,107,108,109,110],"meeting minutes","meeting","minutes","writing","github","copilot","generate","decisions","meetings","up","agenda","actionable","concise","follow-up","tree","true","action","for",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":54},"01M6QJC71RRGTGNNFEHJG6S20G","documentation-writer","Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fdocumentation-writer\u002FSKILL.md",[],[118,119,120,96,97,98,121,122,123,124,125,126,61,127,128,129,130,107,108,131],"documentation","documentation writer","writer","https","quality","technical","technical writer","expert","documentation expert","structure","authoring","software","principles","high",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":145,"publishedAt":54},"01M6QJC0V3C7C4R9768J1AJYWY","doc-coauthoring","Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Fwriting\u002Fdoc-coauthoring\u002FSKILL.md",[138,141,142],{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":143,"categoryName":144,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000036","内容创作者",[146,147,96,148,149,118,150,151,152,153,154,155,61,156,157,128,158,159,107,110],"doc coauthoring","doc","workflow","official","tasks","decision","write","context","proposals","guide","refine","iteration","trigger","co",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":172,"publishedAt":54},"01M6QJBJ0YPVEWGEXZH3PJRRTT","code-review-workflow","Executes comprehensive 4-phase code review: basic review, quality check, bundle analysis, and test coverage. Should be used when the user mentions comprehensive code review, checking code quality, or reviewing staged changes with multi-phase analysis. This is the comprehensive review workflow, distinct from focused skills like frontend-code-review, staged-code-review, or code-change-test-designer.","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002Fcode-review-workflow\u002FSKILL.md",[166,167,170,171],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":168,"categoryName":169,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},[38,35,148,36,173,174,53,175,176,177,50,178,179,180,181,182,183,184,185,186],"code review workflow","testing","test","change","code quality","analysis","check","coverage","quality check","basic","multi","comprehensive code review","with","phase",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":202,"publishedAt":54},"01M6QJB7XNHV3VEEQF4W7FMWF6","code-change-test-designer","Analyzes code changes and designs comprehensive test cases. Reads diffs, summarizes capability changes, and designs test cases covering main flows and edge cases. Should be used when the user mentions test coverage, designing tests for code changes, or analyzing diff\u002Fcommit for testing purposes. Distinguished from code-review-workflow which provides comprehensive review, this skill focuses on test case design for code changes.","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Ftesting\u002Fcode-change-test-designer\u002FSKILL.md",[193,194,197,198,199],{"categoryNo":168,"categoryName":169,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":195,"categoryName":196,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":29,"categoryName":30,"taxonomyType":31,"taxonomyTypeDesc":32},{"categoryNo":200,"categoryName":201,"taxonomyType":31,"taxonomyTypeDesc":32},"01JBSEEDCAT000000000000032","设计师",[175,176,36,203,204,174,205,206,148,52,50,207,180,208,61,209,210,41,110,186],"designer","code change test designer","design","diffs","edge","diff","tests","flows",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":218,"publishedAt":54},"01M6QJB195WD7DCJWDMKWKB29S","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002FImaginerLabs\u002Fskill-manager\u002Fblob\u002Fmain\u002Fskills\u002Fmeta-skills\u002Fskill-creator\u002FSKILL.md",[217],{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[219,220,221,222,149,223,224,225,226,227,178,228,229,230,61,231,232,107,110,213],"skill creator","creator","performance","run evals","variance analysis","create","run","benchmark","Meta","improve","edit","evals","optimize","existing skill"]