[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F3417SNXASFTDA1B2X4XYZ":3,"skill-same:01M7F3417SNXASFTDA1B2X4XYZ":47},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":12,"updatedAt":33,"install":34,"resources":46},"01M7F3417SNXASFTDA1B2X4XYZ","validate-changes",null,"Evaluate staged changes using LLM-as-a-Judge before committing","313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","313DEVGRP","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34762848?v=4","01M7F2M535Z5X8XGHYD8TDVAB3","A-RMS by 313DEVGRP","01M7F2M54CR0P3631F4YM0D014",0,"MIT","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: validate-changes\ndescription: Evaluate staged changes using LLM-as-a-Judge before committing\neffort: medium\ndisable-model-invocation: true\n---\n\n# Validate changes before commit\n\nEvaluate staged git changes using the output-evaluator agent to catch issues before committing.\n\n## Process\n\n### Step 1: Check for staged changes\n\nRun `git diff --cached --stat` to see what's staged. If nothing is staged, inform the user and exit.\n\n### Step 2: Get the full diff\n\nRun `git diff --cached` to get the complete diff of all staged changes.\n\n### Step 3: Invoke the evaluator\n\nUse the Task tool to launch the `output-evaluator` agent with the diff:\n\n```\nEvaluate these staged changes for correctness, completeness, and safety.\nReturn a JSON verdict with scores and issues.\n\nChanges:\n[paste the git diff here]\n```\n\n### Step 4: Parse and act on verdict\n\nBased on the evaluation result:\n\n**If APPROVE:**\n- Tell the user the changes passed evaluation\n- Show the summary and scores\n- Ask if they want to proceed with commit\n\n**If NEEDS_REVIEW:**\n- Show all issues found (grouped by severity)\n- Show the suggestion from the evaluator\n- Ask the user how to proceed:\n  - Fix issues and re-evaluate\n  - Commit anyway (acknowledge risks)\n  - Abort\n\n**If REJECT:**\n- Clearly state the changes were rejected\n- Show critical issues that caused rejection\n- Do NOT offer to commit anyway\n- Suggest specific fixes\n\n### Step 5: Commit (if approved)\n\nIf user confirms, create the commit using the standard commit flow.\n\n## Usage examples\n\n```\n\u002Fvalidate-changes\n```\n\nOutput:\n```\nEvaluating 3 staged files...\n\nVERDICT: NEEDS_REVIEW\n\nScores:\n  Correctness:  8\u002F10\n  Completeness: 6\u002F10\n  Safety:       9\u002F10\n\nIssues Found:\n  [MEDIUM] src\u002Fapi\u002Fhandler.ts:45\n    Missing error handling for network failures\n\n  [LOW] src\u002Futils\u002Fformat.ts:12\n    Consider adding input validation\n\nSuggestion: Add try-catch around the fetch call in handler.ts\n\nHow would you like to proceed?\n  1. Fix issues and re-evaluate\n  2. Commit anyway (1 medium issue)\n  3. Abort\n```\n\n## Cost awareness\n\nThis command invokes an LLM evaluation, which uses API tokens:\n- **Typical cost**: $0.01-0.05 per evaluation (using Haiku)\n- **Larger diffs**: May cost more due to increased token usage\n\n## When to use\n\n- After significant code changes before committing\n- When working on unfamiliar parts of the codebase\n- For changes that affect security-sensitive code\n- Before pushing to shared branches\n\n## When to skip\n\n- Trivial changes (typos, formatting)\n- Documentation-only changes\n- When you've already manually reviewed thoroughly\n- When iterating quickly on a feature branch\n\n## Integration with git hooks\n\nFor automatic evaluation on every commit, see `pre-commit-evaluator.sh` hook.\nThis command is the manual alternative when you want control over when evaluation runs.\n","# Validate changes before commit\n\nEvaluate staged git changes using the output-evaluator agent to catch issues before committing.\n\n## Process\n\n### Step 1: Check for staged changes\n\nRun `git diff --cached --stat` to see what's staged. If nothing is staged, inform the user and exit.\n\n### Step 2: Get the full diff\n\nRun `git diff --cached` to get the complete diff of all staged changes.\n\n### Step 3: Invoke the evaluator\n\nUse the Task tool to launch the `output-evaluator` agent with the diff:\n\n```\nEvaluate these staged changes for correctness, completeness, and safety.\nReturn a JSON verdict with scores and issues.\n\nChanges:\n[paste the git diff here]\n```\n\n### Step 4: Parse and act on verdict\n\nBased on the evaluation result:\n\n**If APPROVE:**\n- Tell the user the changes passed evaluation\n- Show the summary and scores\n- Ask if they want to proceed with commit\n\n**If NEEDS_REVIEW:**\n- Show all issues found (grouped by severity)\n- Show the suggestion from the evaluator\n- Ask the user how to proceed:\n  - Fix issues and re-evaluate\n  - Commit anyway (acknowledge risks)\n  - Abort\n\n**If REJECT:**\n- Clearly state the changes were rejected\n- Show critical issues that caused rejection\n- Do NOT offer to commit anyway\n- Suggest specific fixes\n\n### Step 5: Commit (if approved)\n\nIf user confirms, create the commit using the standard commit flow.\n\n## Usage examples\n\n```\n\u002Fvalidate-changes\n```\n\nOutput:\n```\nEvaluating 3 staged files...\n\nVERDICT: NEEDS_REVIEW\n\nScores:\n  Correctness:  8\u002F10\n  Completeness: 6\u002F10\n  Safety:       9\u002F10\n\nIssues Found:\n  [MEDIUM] src\u002Fapi\u002Fhandler.ts:45\n    Missing error handling for network failures\n\n  [LOW] src\u002Futils\u002Fformat.ts:12\n    Consider adding input validation\n\nSuggestion: Add try-catch around the fetch call in handler.ts\n\nHow would you like to proceed?\n  1. Fix issues and re-evaluate\n  2. Commit anyway (1 medium issue)\n  3. Abort\n```\n\n## Cost awareness\n\nThis command invokes an LLM evaluation, which uses API tokens:\n- **Typical cost**: $0.01-0.05 per evaluation (using Haiku)\n- **Larger diffs**: May cost more due to increased token usage\n\n## When to use\n\n- After significant code changes before committing\n- When working on unfamiliar parts of the codebase\n- For changes that affect security-sensitive code\n- Before pushing to shared branches\n\n## When to skip\n\n- Trivial changes (typos, formatting)\n- Documentation-only changes\n- When you've already manually reviewed thoroughly\n- When iterating quickly on a feature branch\n\n## Integration with git hooks\n\nFor automatic evaluation on every commit, see `pre-commit-evaluator.sh` hook.\nThis command is the manual alternative when you want control over when evaluation runs.\n",{"name":5,"effort":24,"description":7,"disable-model-invocation":25},"medium",true,"main","f2cc95bc769ca4c3a398965b767dfb41cdf8d698","reference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes",2,"https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace","https:\u002F\u002Fgithub.com\u002F313DEVGRP","https:\u002F\u002Fwww.a-rms.net","2026-10-18 12:48:10",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":25},[36,39,42],{"tool":37,"command":38},"npx","npx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill validate-changes",{"tool":40,"command":41},"bunx","bunx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill validate-changes",{"tool":43,"command":44},"pnpm","pnpm dlx skills add 313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace --skill validate-changes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvalidate-changes\u002FSKILL.md",[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7F343WNVHZWWYJDD77QEJ7J","voice-refine","Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fvoice-refine\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7F33YN9QK88H2B81PVHMNG1","update-threat-db","Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Fupdate-threat-db\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7F33SXQ57G2FVFK094T4584","token-audit","Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftoken-audit\u002Fskill.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7F33NAWXFPHW59CF52EAGGK","talk-stage6-revision","Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-6-revision\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7F33G9V96HVZKAGZ84J4EBR","talk-stage5-script","Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-5-script\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7F33BK00XGVPZCGZ1Y1VQXQ","talk-stage4-position","Generates 3-4 strategic talk angles with strength\u002Fweakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory CHECKPOINT for user confirmation before scripting. Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles.","https:\u002F\u002Fgithub.com\u002F313DEVGRP\u002FJava-Service-Tree-Framework-Multi-Agent-Workspace\u002Fblob\u002Fmain\u002Freference\u002Fclaude-code-ultimate-guide-main\u002Fexamples\u002Fskills\u002Ftalk-pipeline\u002Fstage-4-position\u002FSKILL.md",[],[]]