[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MZ31F7M5EP8TD7QNWJB7WK":3,"skill-same:01M6MZ31F7M5EP8TD7QNWJB7WK":67},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6MZ31F7M5EP8TD7QNWJB7WK","operational-constraints",null,"Activate comprehensive operational constraints for disciplined execution. Use at session start, before complex tasks, during planning phases, or when encountering friction. Enforces token efficiency, tool protocols, parallel execution, TDD, and system mapping.","snewhouse\u002Faa-ma-forge","snewhouse","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6317143?v=4","01M6MYYWF28C4KBQHHWB9SC6TS","Stephen J Newhouse","01M6MYYWJWQMDN2ZPFMJ584SSM",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Foperational-constraints\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"operational constraints","constraints","ops","token efficiency","for","mode","session start","efficiency","task","activate","use","tasks","session","parallel","tool","system","ultrathink","execution","protocols","planning","2026-11-10 10:12:30",false,"---\nname: operational-constraints\ndescription: Activate comprehensive operational constraints for disciplined execution. Use at session start, before complex tasks, during planning phases, or when encountering friction. Enforces token efficiency, tool protocols, parallel execution, TDD, and system mapping.\nwhen_to_use: Use for ops-mode, ultrathink, operational mode, disciplined execution, a complex task, or a request to enable constraints.\n---\n\n# Operational Constraints Skill\n\nComprehensive operational rules for disciplined Claude Code execution. This skill captures battle-tested constraints that prevent common pitfalls and ensure consistent, high-quality outputs.\n\n## When to Use\n\n**ALWAYS invoke this skill when:**\n- Starting a session that will involve complex multi-step work\n- Before `\u002Faa-ma-plan` or any significant planning\n- After encountering friction or repeated issues\n- When you notice yourself making avoidable mistakes\n- Any session requiring disciplined, methodical execution\n\n**Quick activation:** `\u002Fops-mode` command loads this automatically.\n\n---\n\n## Core Constraints\n\n### 1. Token & Context Efficiency\n\n**Output compression:** Use `Skill(token-compression)` for response token reduction.\nDefault level: `full`. During AA-MA execution, level is set automatically by task Mode\n(HITL→lite, AFK→ultra). See skill for intensity details and auto-clarity exceptions.\n\n**Context loading:**\n- When approaching 70% context usage, consider context compaction\n- Prefer loading REFERENCE and TASKS files over full history\n- Suppress verbose logs unless actively debugging\n- Use structured summaries over lengthy explanations\n- No redundant confirmation messages\n\n**Anti-patterns to avoid:**\n- Loading entire files when only specific sections needed\n- Repeating information already established in context\n- Verbose \"thinking out loud\" when concise reasoning suffices\n\n---\n\n### 2. Research & Tools Protocol\n\n**Principles:**\n- Use the right tool for the job\n- Leverage external knowledge sources for current information\n- Prefer specialized tools over bash commands\n\n**Tool Selection Matrix:**\n\n| Need | Primary Tool | Alternative |\n|------|--------------|-------------|\n| Library\u002FAPI docs | Context7 MCP | WebSearch |\n| Current information | WebSearch | WebFetch |\n| Text pattern search | GrepTool | - |\n| Structural code search | Skill(ast-grep) | GrepTool |\n| Complex file analysis | Python script | - |\n| File pattern matching | Glob | - |\n| Codebase exploration | Task(Explore) | GrepTool + Glob |\n\n**Context7 MCP Protocol:**\n1. ALWAYS use Context7 for library\u002FAPI documentation when available\n2. If Context7 fails, retry once\n3. If retry fails, fallback to:\n   - Native Claude Code documentation tools\n   - Community-vetted code snippets\n   - Official documentation via WebFetch\n4. Record and surface fallback status\n\n**Search Tools:**\n```\n# Pattern-based content search\nGrepTool: pattern=\"function_name\", path=\"src\u002F\"\n\n# Structural code search (AST-based)\nSkill(ast-grep) for:\n- Finding all function definitions matching pattern\n- Refactoring code structures\n- Complex code transformations\n\n# Large file analysis\nPython script when:\n- Multiple processing steps required\n- Complex logic needed\n- Results need aggregation\n```\n\n---\n\n### 3. Parallel Execution Mandate\n\n**Principle:** MUST evaluate if parallel subagents can handle independent subtasks.\n\n**Decision Tree:**\n```\nAre there multiple distinct subtasks?\n├── NO → Execute sequentially\n└── YES → Do they have dependencies between them?\n    ├── YES → Identify dependency chain, parallelize independent portions\n    └── NO → PARALLELIZE IMMEDIATELY\n```\n\n**When to use parallel agents:**\n- 3+ independent research questions\n- Multiple files need analysis without interdependencies\n- Different aspects of a problem can be explored simultaneously\n- Investigation tasks that don't share state\n\n**How to parallelize:**\n```\nUse Task tool with multiple invocations in SINGLE message:\n- Task 1: Explore agent for area A\n- Task 2: Explore agent for area B\n- Task 3: Plan agent for design\n\nOR use Skill(dispatching-parallel-agents) for structured dispatch.\n```\n\n**Anti-patterns:**\n- Sequential execution of clearly independent tasks\n- Waiting for one exploration to complete before starting another\n- Not considering parallelization at all\n\n---\n\n### 4. Development Discipline\n\n**Full doctrine (auto-loaded, stated once):** the principles (KISS, DRY, YAGNI, SoC, SOLID), the testing floor, comments and suppressions are in [`claude-code\u002Frules\u002Fcoding-standards.md`](..\u002F..\u002Frules\u002Fcoding-standards.md); the AA-MA process doctrine is in [`claude-code\u002Frules\u002Fengineering-standards.md`](..\u002F..\u002Frules\u002Fengineering-standards.md). This section names them without restating them. Also: 12-Factor for services; TDD via `Skill(test-driven-development)`.\n\n**Impact Analysis:**\n- Use `Skill(impact-analysis)` for ALL code changes\n- Required at milestone boundaries during AA-MA execution\n- HIGH risk impacts must be resolved before proceeding\n\n**Code Quality:**\n- Functional working code over perfection\n- Follow existing codebase patterns\n\n---\n\n### 5. System Mapping (Pre-Flight)\n\n**Principle:** Before modifying code, understand the system context.\n\n**5-Point Protocol:**\n\n| Point | Question | Tools |\n|-------|----------|-------|\n| 1. Architecture | What files\u002Fmodules are involved? | Glob, LS |\n| 2. Execution Flows | How does data\u002Fcontrol flow? | Grep, ast-grep |\n| 3. Logging | What observability exists? | Grep \"logger\\|logging\" |\n| 4. Dependencies | What does this code depend on? | Grep \"import\\|from\" |\n| 5. Environment | What config\u002Fenv vars matter? | Grep \"environ\\|getenv\" |\n\n**When to perform:**\n- Changes touch 3+ files\n- Unfamiliar code area\n- Integrating with external services\n- Modifying data pipelines\n\n**Detailed protocol:** See `Skill(system-mapping)`\n\n---\n\n### 6. Planning Output Protocol\n\n**At the end of any planning phase, MUST:**\n\n1. **Explicitly ask for approval** before proceeding\n2. **Offer clear options:**\n   - Proceed with implementation\n   - Create AA-MA artifacts first\n   - Adjust\u002Frefine the plan\n3. **Create AA-MA artifacts** when approved for complex tasks\n4. **Identify the single next action** to take\n5. **Emit element #12 (Engineering Standards Declaration)** as part of the plan output — declare which themes from `engineering-standards.md` materially apply and how. See `Skill(plan-verification)` Angle 6 for the verification path.\n\n**Template:**\n```\n## Plan Summary\n[Concise overview]\n\n## Proposed Approach\n[Key decisions]\n\n## Ready to proceed?\n- [ ] Approve and proceed\n- [ ] Create AA-MA artifacts first\n- [ ] Need adjustments: [specify]\n```\n\n---\n\n## Checklists\n\n### Session Start Checklist\n- [ ] Is this a complex multi-step task? If yes, invoke this skill\n- [ ] Any active AA-MA plans? Check `.claude\u002Fdev\u002Factive\u002F`\n- [ ] What skills might apply? Review available skills\n\n### Pre-Task Checklist\n- [ ] Can this be parallelized? Evaluate subagent opportunities\n- [ ] Is system-mapping needed? Check 5-point protocol triggers\n- [ ] TDD applicable? Plan tests first if coding\n- [ ] Impact analysis required? For code changes, always\n\n### Pre-Commit Checklist\n- [ ] All tests passing?\n- [ ] Impact analysis completed for changes?\n- [ ] AA-MA docs updated if active plan?\n- [ ] Conventional commit message?\n\n---\n\n## Cross-References\n\n| Skill\u002FCommand | Purpose | When to Use |\n|---------------|---------|-------------|\n| `Skill(system-mapping)` | Detailed 5-point pre-flight | Before code modifications |\n| `Skill(test-driven-development)` | TDD enforcement | All coding tasks |\n| `Skill(impact-analysis)` | Change risk assessment | Before and after code changes |\n| `Skill(dispatching-parallel-agents)` | Parallel execution patterns | Independent subtasks |\n| `Skill(ast-grep)` | Structural code search | Complex code analysis |\n| `\u002Fops-mode` | Quick constraint activation | Session start |\n| `\u002Faa-ma-plan` | Comprehensive planning | Major features |\n| `claude-code\u002Frules\u002Fengineering-standards.md` | 6-theme doctrine (auto-loaded) | Always |\n\n---\n\n## Quick Reference Card\n\n```\nTOKEN EFFICIENCY\n├── Skill(token-compression) for output reduction\n├── Load only essential context\n└── No redundant confirmations\n\nTOOLS\n├── Context7 → Library docs\n├── GrepTool → Pattern search\n├── ast-grep → Structural search\n└── Python → Complex analysis\n\nPARALLEL\n├── 3+ independent tasks → PARALLELIZE\n├── No dependencies → PARALLELIZE\n└── Use Task tool with multiple calls\n\nDISCIPLINE\n├── coding-standards.md (principles, TDD floor)\n├── Impact analysis for all changes\n└── System mapping for unfamiliar code\n\nPLANNING\n├── Ask approval before proceeding\n├── Offer: proceed \u002F AA-MA \u002F adjust\n└── Identify single next action\n```\n\n---\n\n## Activation Confirmation\n\nWhen this skill is loaded, acknowledge with:\n\n```\nOPERATIONAL CONSTRAINTS: ACTIVE\n\nEnforcing:\n- Token compression (Skill: token-compression)\n- Tool protocols (Context7, GrepTool, ast-grep)\n- Parallel execution evaluation\n- TDD discipline\n- System mapping pre-flight\n- Planning approval protocol\n\nReady for disciplined execution.\n```\n","# Operational Constraints Skill\n\nComprehensive operational rules for disciplined Claude Code execution. This skill captures battle-tested constraints that prevent common pitfalls and ensure consistent, high-quality outputs.\n\n## When to Use\n\n**ALWAYS invoke this skill when:**\n- Starting a session that will involve complex multi-step work\n- Before `\u002Faa-ma-plan` or any significant planning\n- After encountering friction or repeated issues\n- When you notice yourself making avoidable mistakes\n- Any session requiring disciplined, methodical execution\n\n**Quick activation:** `\u002Fops-mode` command loads this automatically.\n\n---\n\n## Core Constraints\n\n### 1. Token & Context Efficiency\n\n**Output compression:** Use `Skill(token-compression)` for response token reduction.\nDefault level: `full`. During AA-MA execution, level is set automatically by task Mode\n(HITL→lite, AFK→ultra). See skill for intensity details and auto-clarity exceptions.\n\n**Context loading:**\n- When approaching 70% context usage, consider context compaction\n- Prefer loading REFERENCE and TASKS files over full history\n- Suppress verbose logs unless actively debugging\n- Use structured summaries over lengthy explanations\n- No redundant confirmation messages\n\n**Anti-patterns to avoid:**\n- Loading entire files when only specific sections needed\n- Repeating information already established in context\n- Verbose \"thinking out loud\" when concise reasoning suffices\n\n---\n\n### 2. Research & Tools Protocol\n\n**Principles:**\n- Use the right tool for the job\n- Leverage external knowledge sources for current information\n- Prefer specialized tools over bash commands\n\n**Tool Selection Matrix:**\n\n| Need | Primary Tool | Alternative |\n|------|--------------|-------------|\n| Library\u002FAPI docs | Context7 MCP | WebSearch |\n| Current information | WebSearch | WebFetch |\n| Text pattern search | GrepTool | - |\n| Structural code search | Skill(ast-grep) | GrepTool |\n| Complex file analysis | Python script | - |\n| File pattern matching | Glob | - |\n| Codebase exploration | Task(Explore) | GrepTool + Glob |\n\n**Context7 MCP Protocol:**\n1. ALWAYS use Context7 for library\u002FAPI documentation when available\n2. If Context7 fails, retry once\n3. If retry fails, fallback to:\n   - Native Claude Code documentation tools\n   - Community-vetted code snippets\n   - Official documentation via WebFetch\n4. Record and surface fallback status\n\n**Search Tools:**\n```\n# Pattern-based content search\nGrepTool: pattern=\"function_name\", path=\"src\u002F\"\n\n# Structural code search (AST-based)\nSkill(ast-grep) for:\n- Finding all function definitions matching pattern\n- Refactoring code structures\n- Complex code transformations\n\n# Large file analysis\nPython script when:\n- Multiple processing steps required\n- Complex logic needed\n- Results need aggregation\n```\n\n---\n\n### 3. Parallel Execution Mandate\n\n**Principle:** MUST evaluate if parallel subagents can handle independent subtasks.\n\n**Decision Tree:**\n```\nAre there multiple distinct subtasks?\n├── NO → Execute sequentially\n└── YES → Do they have dependencies between them?\n    ├── YES → Identify dependency chain, parallelize independent portions\n    └── NO → PARALLELIZE IMMEDIATELY\n```\n\n**When to use parallel agents:**\n- 3+ independent research questions\n- Multiple files need analysis without interdependencies\n- Different aspects of a problem can be explored simultaneously\n- Investigation tasks that don't share state\n\n**How to parallelize:**\n```\nUse Task tool with multiple invocations in SINGLE message:\n- Task 1: Explore agent for area A\n- Task 2: Explore agent for area B\n- Task 3: Plan agent for design\n\nOR use Skill(dispatching-parallel-agents) for structured dispatch.\n```\n\n**Anti-patterns:**\n- Sequential execution of clearly independent tasks\n- Waiting for one exploration to complete before starting another\n- Not considering parallelization at all\n\n---\n\n### 4. Development Discipline\n\n**Full doctrine (auto-loaded, stated once):** the principles (KISS, DRY, YAGNI, SoC, SOLID), the testing floor, comments and suppressions are in [`claude-code\u002Frules\u002Fcoding-standards.md`](..\u002F..\u002Frules\u002Fcoding-standards.md); the AA-MA process doctrine is in [`claude-code\u002Frules\u002Fengineering-standards.md`](..\u002F..\u002Frules\u002Fengineering-standards.md). This section names them without restating them. Also: 12-Factor for services; TDD via `Skill(test-driven-development)`.\n\n**Impact Analysis:**\n- Use `Skill(impact-analysis)` for ALL code changes\n- Required at milestone boundaries during AA-MA execution\n- HIGH risk impacts must be resolved before proceeding\n\n**Code Quality:**\n- Functional working code over perfection\n- Follow existing codebase patterns\n\n---\n\n### 5. System Mapping (Pre-Flight)\n\n**Principle:** Before modifying code, understand the system context.\n\n**5-Point Protocol:**\n\n| Point | Question | Tools |\n|-------|----------|-------|\n| 1. Architecture | What files\u002Fmodules are involved? | Glob, LS |\n| 2. Execution Flows | How does data\u002Fcontrol flow? | Grep, ast-grep |\n| 3. Logging | What observability exists? | Grep \"logger\\|logging\" |\n| 4. Dependencies | What does this code depend on? | Grep \"import\\|from\" |\n| 5. Environment | What config\u002Fenv vars matter? | Grep \"environ\\|getenv\" |\n\n**When to perform:**\n- Changes touch 3+ files\n- Unfamiliar code area\n- Integrating with external services\n- Modifying data pipelines\n\n**Detailed protocol:** See `Skill(system-mapping)`\n\n---\n\n### 6. Planning Output Protocol\n\n**At the end of any planning phase, MUST:**\n\n1. **Explicitly ask for approval** before proceeding\n2. **Offer clear options:**\n   - Proceed with implementation\n   - Create AA-MA artifacts first\n   - Adjust\u002Frefine the plan\n3. **Create AA-MA artifacts** when approved for complex tasks\n4. **Identify the single next action** to take\n5. **Emit element #12 (Engineering Standards Declaration)** as part of the plan output — declare which themes from `engineering-standards.md` materially apply and how. See `Skill(plan-verification)` Angle 6 for the verification path.\n\n**Template:**\n```\n## Plan Summary\n[Concise overview]\n\n## Proposed Approach\n[Key decisions]\n\n## Ready to proceed?\n- [ ] Approve and proceed\n- [ ] Create AA-MA artifacts first\n- [ ] Need adjustments: [specify]\n```\n\n---\n\n## Checklists\n\n### Session Start Checklist\n- [ ] Is this a complex multi-step task? If yes, invoke this skill\n- [ ] Any active AA-MA plans? Check `.claude\u002Fdev\u002Factive\u002F`\n- [ ] What skills might apply? Review available skills\n\n### Pre-Task Checklist\n- [ ] Can this be parallelized? Evaluate subagent opportunities\n- [ ] Is system-mapping needed? Check 5-point protocol triggers\n- [ ] TDD applicable? Plan tests first if coding\n- [ ] Impact analysis required? For code changes, always\n\n### Pre-Commit Checklist\n- [ ] All tests passing?\n- [ ] Impact analysis completed for changes?\n- [ ] AA-MA docs updated if active plan?\n- [ ] Conventional commit message?\n\n---\n\n## Cross-References\n\n| Skill\u002FCommand | Purpose | When to Use |\n|---------------|---------|-------------|\n| `Skill(system-mapping)` | Detailed 5-point pre-flight | Before code modifications |\n| `Skill(test-driven-development)` | TDD enforcement | All coding tasks |\n| `Skill(impact-analysis)` | Change risk assessment | Before and after code changes |\n| `Skill(dispatching-parallel-agents)` | Parallel execution patterns | Independent subtasks |\n| `Skill(ast-grep)` | Structural code search | Complex code analysis |\n| `\u002Fops-mode` | Quick constraint activation | Session start |\n| `\u002Faa-ma-plan` | Comprehensive planning | Major features |\n| `claude-code\u002Frules\u002Fengineering-standards.md` | 6-theme doctrine (auto-loaded) | Always |\n\n---\n\n## Quick Reference Card\n\n```\nTOKEN EFFICIENCY\n├── Skill(token-compression) for output reduction\n├── Load only essential context\n└── No redundant confirmations\n\nTOOLS\n├── Context7 → Library docs\n├── GrepTool → Pattern search\n├── ast-grep → Structural search\n└── Python → Complex analysis\n\nPARALLEL\n├── 3+ independent tasks → PARALLELIZE\n├── No dependencies → PARALLELIZE\n└── Use Task tool with multiple calls\n\nDISCIPLINE\n├── coding-standards.md (principles, TDD floor)\n├── Impact analysis for all changes\n└── System mapping for unfamiliar code\n\nPLANNING\n├── Ask approval before proceeding\n├── Offer: proceed \u002F AA-MA \u002F adjust\n└── Identify single next action\n```\n\n---\n\n## Activation Confirmation\n\nWhen this skill is loaded, acknowledge with:\n\n```\nOPERATIONAL CONSTRAINTS: ACTIVE\n\nEnforcing:\n- Token compression (Skill: token-compression)\n- Tool protocols (Context7, GrepTool, ast-grep)\n- Parallel execution evaluation\n- TDD discipline\n- System mapping pre-flight\n- Planning approval protocol\n\nReady for disciplined execution.\n```\n",{"name":5,"description":7,"when_to_use":44},"Use for ops-mode, ultrathink, operational mode, disciplined execution, a complex task, or a request to enable constraints.","main","cd9a2962c9a7e0797fe440f7b1ba4ceccc16ae0d","claude-code\u002Fskills\u002Foperational-constraints",1,"https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge","https:\u002F\u002Fgithub.com\u002Fsnewhouse","Data Scientist, Bioinformatician, Dad, Husband, MS warrior","2026-11-12 06:45:42",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add snewhouse\u002Faa-ma-forge --skill operational-constraints",{"tool":59,"command":60},"bunx","bunx skills add snewhouse\u002Faa-ma-forge --skill operational-constraints",{"tool":62,"command":63},"pnpm","pnpm dlx skills add snewhouse\u002Faa-ma-forge --skill operational-constraints","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Foperational-constraints\u002FSKILL.md",true,[],[68,92,119,139,163,193],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":79,"publishedAt":39},"01M6MZ588SD5DDH59H18PRNWEV","deploy-helper","You can use this to help with deploy stuff, deploying, deployments, releases, shipping, pushing to prod, going live, rollouts.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fevals\u002Fskill-draft\u002Fdraft\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[80,81,82,83,84,85,86,87,88,29,89,90,91],"deploy","deploy helper","helper","you","live","with","can","rollouts","shipping","deployments","releases","help",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":96,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":111,"publishedAt":39},"01M6MZ54NEKRYXGMJ1KJWYMKM7","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","MIT","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[100,103,106],{"categoryNo":101,"categoryName":102,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":104,"categoryName":105,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[112,113,23,114,29,115,116,117,118],"writing","writing for agents","line","instructions","read","editing","documents",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":39},"01M6MZ500T0FH1G8TBSQV7G5G2","verify-plan","Slash entry for plan verification: runs plan-verification on an existing AA-MA plan, writes [task]-verification.md, and with --iterate loops until the plan converges. Use when the user types \u002Fverify-plan or wants the verification report saved.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fverify-plan\u002FSKILL.md",[],[126,127,128,129,27,29,130,85,131,132,133,134,135,136,137,23,138],"verify","plan","verify plan","loops","user","verification","report","types","plan verification","entry","iterate","Existing","saved",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":39},"01M6MZ4V9ST4K54NT1SRBGCE7P","verify-impl","Post-impl adversarial review symmetric to \u002Fverify-plan. Dispatches up to 5 parallel audit agents (code-reviewer, security-auditor, tdd-sequence-auditor, context7-evidence-auditor, future-proofing-auditor) based on the milestone's plan-declared Audit-Profile. CRITICAL findings surface via AskUserQuestion accept\u002Fdispute\u002Fdefer panel before §7.3 user authorization. Introduced in v0.8.0 per ADR-0005. Invoked by Phase 6.8 of \u002Fexecute-aa-ma-milestone.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fverify-impl\u002FSKILL.md",[],[146,147,126,148,149,150,151,152,153,154,155,156,157,32,158,127,159,160,161,162],"impl","verify impl","adversarial","post","panel","via","critical","review","context7","up","evidence","reviewer","adr","audit","code","tdd","milestone",{"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":173,"publishedAt":39},"01M6MZ4K7CC9PMJ1KEY3F53RS1","understand-codebase","Onboard to a new, inherited, or shared codebase. Read it, understand it, map it, and learn its conventions, versioning, tests, tech stack, rules (AGENTS.md \u002F CLAUDE.md \u002F .cursorrules \u002F etc.), build\u002Frun\u002FCI, integrations, security posture, and repo health — then produce an honest pros\u002Fcons verdict, a \"contribute safely\" playbook, and an \"add a feature\" playbook, written to ONBOARDING.md at the repo root plus a .claude\u002Fonboarding\u002F set of deep-dives — and optionally author an AGENTS.md if one is missing, or review and propose improvements to an existing one. Tiered (Quick \u002F Standard \u002F Deep). Reuses codemem (index + diagrams), gsd-map-codebase, system-mapping, code-intelligence, impact-analysis rather than re-implementing them; Deep tier runs a TeamCreate agent-team. Keywords: new codebase, shared codebase, inherited code, onboard, understand this repo, how do I contribute, how do I add a feature, ramp up, get oriented, ONBOARDING.md, AGENTS.md, codebase walkthrough, joining a project.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Funderstand-codebase\u002FSKILL.md",[169,170],{"categoryNo":104,"categoryName":105,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":171,"categoryName":172,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000038","人力资源",[174,175,176,155,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192],"understand codebase","codebase","understand","walkthrough","analysis","SET","ci","learn","diagrams","repo health","implementing","re","quick","impact","get","project","deep","shared","map",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":199,"publishedAt":39},"01M6MZ4D1ZC8MTW064QXY6WC76","token-compression","Output token compression for AA-MA workflows. Reduces response tokens by 40-75% while preserving full technical accuracy. Three intensity levels mapped to execution modes: lite (HITL), full (general), ultra (AFK). Auto-activates during AA-MA execution based on task Mode field. Manual activation via \u002Fcompress lite|full|ultra.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Ftoken-compression\u002FSKILL.md",[],[200,201,202,203,204,205,206,23,24,207,151,208,209,210,211,27,212,213,214,36],"compression","token compression","token","workflows","output","modes","accuracy","manual","intensity","tokens","hitl","three","general","auto","technical"]