[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MZ3719CHVMNH1QMKMSFEAN":3,"skill-same:01M6MZ3719CHVMNH1QMKMSFEAN":56},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M6MZ3719CHVMNH1QMKMSFEAN","ops-mode",null,"Activate full operational constraints mode for disciplined, efficient execution. Use when the user asks for ops mode.","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\u002Fops-mode\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"ops","mode","ops mode","execution","constraints","user","use","activate","full","for","2026-11-10 10:12:30",false,"---\nname: ops-mode\ndescription: Activate full operational constraints mode for disciplined, efficient execution. Use when the user asks for ops mode.\n---\n\n# Operational Mode Activated\n\nThis session is now operating in **OPS-MODE** with comprehensive operational constraints enforced.\n\n## Active Constraints\n\n### Token & Context Efficiency\n- Minimize context loading - only essential information\n- Compress outputs - no verbose explanations unless requested\n- Focused reasoning - minimal \"thinking out loud\"\n- When approaching 70% context, initiate compaction\n\n### Tool Protocols\n\n**Documentation & Research:**\n- Context7 MCP for library\u002FAPI documentation (retry once on failure, then fallback)\n- WebSearch for current information beyond training cutoff\n- WebFetch for specific documentation pages\n\n**Code Search:**\n| Need | Tool |\n|------|------|\n| Text patterns | GrepTool |\n| Code structures | Skill(ast-grep) |\n| Complex analysis | Python script |\n| File patterns | Glob |\n| Exploration | Task(Explore) |\n\n### Parallel Execution Mandate\n\nBefore any multi-step task, evaluate:\n```\nIndependent subtasks exist?\n├── NO → Sequential execution\n└── YES → Dependencies between them?\n    ├── YES → Parallelize independent portions\n    └── NO → DISPATCH PARALLEL AGENTS NOW\n```\n\nUse multiple Task tool invocations in a single message for parallelization.\n\n### Development Discipline\n\n**Principles enforced:**\n- KISS - Keep It Simple, Stupid\n- DRY - Don't Repeat Yourself\n- SOLID - Object-oriented design principles\n- SOC - Separation of Concerns\n- 12 Factor App - Application architecture\n\n**TDD Mandate:**\n- RED → GREEN → REFACTOR cycle\n- Write test BEFORE implementation\n- No rationalizations for skipping\n\n**Impact Analysis:**\n- Use Skill(impact-analysis) for ALL code changes\n- HIGH risk impacts must be resolved before proceeding\n\n### System Mapping Pre-Flight\n\nBefore modifying code, perform 5-point check (if applicable):\n1. **Architecture** - Files, modules, entry points\n2. **Execution Flow** - Call chains, async boundaries\n3. **Logging** - Existing observability\n4. **Dependencies** - Imports, external services\n5. **Environment** - Config, env vars, flags\n\nUse `Skill(system-mapping)` for detailed protocol.\n\n### Planning Output Protocol\n\nAt end of any planning:\n1. Explicitly ask for approval\n2. Offer options: proceed \u002F create AA-MA docs \u002F adjust\n3. Identify single next action\n\n---\n\n## Session Start: Lessons Review\n\nBefore executing any task, check if the project has a `docs\u002Flessons.md` file. If it exists, read the top 10 entries and internalize them. If it doesn't exist, note this and continue.\n\nThis enforces the self-improvement-loop rule: \"At the beginning of EVERY new session, your first operational action must be to review lessons.\"\n\n---\n\n## Pre-Task Checklist\n\nBefore proceeding with your task:\n\n- [ ] **Lessons reviewed** - Read `docs\u002Flessons.md` top entries (if exists)\n- [ ] **Skills reviewed** - Checked available skills for relevance\n- [ ] **Parallelization evaluated** - Identified if subagents can help\n- [ ] **System mapping needed?** - For code changes to unfamiliar areas\n- [ ] **TDD applicable?** - Plan tests first if implementing code\n- [ ] **AA-MA active?** - Check `.claude\u002Fdev\u002Factive\u002F` for existing plans\n\n---\n\n## Quick Commands\n\n| Command | Purpose |\n|---------|---------|\n| `Skill(operational-constraints)` | Full constraint documentation |\n| `Skill(system-mapping)` | 5-point pre-flight protocol |\n| `Skill(test-driven-development)` | TDD workflow |\n| `Skill(impact-analysis)` | Change risk assessment |\n| `Skill(dispatching-parallel-agents)` | Parallel execution patterns |\n\n---\n\n## Confirmation\n\n```\nOPS-MODE: ACTIVE\n\nConstraints enforced:\n  ✓ Lessons review (self-improvement loop)\n  ✓ Token efficiency\n  ✓ Tool protocols (Context7, GrepTool, ast-grep)\n  ✓ Parallel execution evaluation\n  ✓ TDD discipline\n  ✓ System mapping pre-flight\n  ✓ Planning approval protocol\n\nSession ready for disciplined execution.\n```\n\n---\n\n**What task would you like to work on?**\n","# Operational Mode Activated\n\nThis session is now operating in **OPS-MODE** with comprehensive operational constraints enforced.\n\n## Active Constraints\n\n### Token & Context Efficiency\n- Minimize context loading - only essential information\n- Compress outputs - no verbose explanations unless requested\n- Focused reasoning - minimal \"thinking out loud\"\n- When approaching 70% context, initiate compaction\n\n### Tool Protocols\n\n**Documentation & Research:**\n- Context7 MCP for library\u002FAPI documentation (retry once on failure, then fallback)\n- WebSearch for current information beyond training cutoff\n- WebFetch for specific documentation pages\n\n**Code Search:**\n| Need | Tool |\n|------|------|\n| Text patterns | GrepTool |\n| Code structures | Skill(ast-grep) |\n| Complex analysis | Python script |\n| File patterns | Glob |\n| Exploration | Task(Explore) |\n\n### Parallel Execution Mandate\n\nBefore any multi-step task, evaluate:\n```\nIndependent subtasks exist?\n├── NO → Sequential execution\n└── YES → Dependencies between them?\n    ├── YES → Parallelize independent portions\n    └── NO → DISPATCH PARALLEL AGENTS NOW\n```\n\nUse multiple Task tool invocations in a single message for parallelization.\n\n### Development Discipline\n\n**Principles enforced:**\n- KISS - Keep It Simple, Stupid\n- DRY - Don't Repeat Yourself\n- SOLID - Object-oriented design principles\n- SOC - Separation of Concerns\n- 12 Factor App - Application architecture\n\n**TDD Mandate:**\n- RED → GREEN → REFACTOR cycle\n- Write test BEFORE implementation\n- No rationalizations for skipping\n\n**Impact Analysis:**\n- Use Skill(impact-analysis) for ALL code changes\n- HIGH risk impacts must be resolved before proceeding\n\n### System Mapping Pre-Flight\n\nBefore modifying code, perform 5-point check (if applicable):\n1. **Architecture** - Files, modules, entry points\n2. **Execution Flow** - Call chains, async boundaries\n3. **Logging** - Existing observability\n4. **Dependencies** - Imports, external services\n5. **Environment** - Config, env vars, flags\n\nUse `Skill(system-mapping)` for detailed protocol.\n\n### Planning Output Protocol\n\nAt end of any planning:\n1. Explicitly ask for approval\n2. Offer options: proceed \u002F create AA-MA docs \u002F adjust\n3. Identify single next action\n\n---\n\n## Session Start: Lessons Review\n\nBefore executing any task, check if the project has a `docs\u002Flessons.md` file. If it exists, read the top 10 entries and internalize them. If it doesn't exist, note this and continue.\n\nThis enforces the self-improvement-loop rule: \"At the beginning of EVERY new session, your first operational action must be to review lessons.\"\n\n---\n\n## Pre-Task Checklist\n\nBefore proceeding with your task:\n\n- [ ] **Lessons reviewed** - Read `docs\u002Flessons.md` top entries (if exists)\n- [ ] **Skills reviewed** - Checked available skills for relevance\n- [ ] **Parallelization evaluated** - Identified if subagents can help\n- [ ] **System mapping needed?** - For code changes to unfamiliar areas\n- [ ] **TDD applicable?** - Plan tests first if implementing code\n- [ ] **AA-MA active?** - Check `.claude\u002Fdev\u002Factive\u002F` for existing plans\n\n---\n\n## Quick Commands\n\n| Command | Purpose |\n|---------|---------|\n| `Skill(operational-constraints)` | Full constraint documentation |\n| `Skill(system-mapping)` | 5-point pre-flight protocol |\n| `Skill(test-driven-development)` | TDD workflow |\n| `Skill(impact-analysis)` | Change risk assessment |\n| `Skill(dispatching-parallel-agents)` | Parallel execution patterns |\n\n---\n\n## Confirmation\n\n```\nOPS-MODE: ACTIVE\n\nConstraints enforced:\n  ✓ Lessons review (self-improvement loop)\n  ✓ Token efficiency\n  ✓ Tool protocols (Context7, GrepTool, ast-grep)\n  ✓ Parallel execution evaluation\n  ✓ TDD discipline\n  ✓ System mapping pre-flight\n  ✓ Planning approval protocol\n\nSession ready for disciplined execution.\n```\n\n---\n\n**What task would you like to work on?**\n",{"name":5,"description":7},"main","cd9a2962c9a7e0797fe440f7b1ba4ceccc16ae0d","claude-code\u002Fskills\u002Fops-mode",1,"https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge","https:\u002F\u002Fgithub.com\u002Fsnewhouse","Data Scientist, Bioinformatician, Dad, Husband, MS warrior","2026-11-11 21:34:39",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add snewhouse\u002Faa-ma-forge --skill ops-mode",{"tool":48,"command":49},"bunx","bunx skills add snewhouse\u002Faa-ma-forge --skill ops-mode",{"tool":51,"command":52},"pnpm","pnpm dlx skills add snewhouse\u002Faa-ma-forge --skill ops-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fops-mode\u002FSKILL.md",true,[],[57,81,108,128,153,183],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":68,"publishedAt":29},"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",[63],{"categoryNo":64,"categoryName":65,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[69,70,71,72,73,74,75,76,77,25,78,79,80],"deploy","deploy helper","helper","you","live","with","can","rollouts","shipping","deployments","releases","help",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":100,"publishedAt":29},"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",[89,92,95],{"categoryNo":90,"categoryName":91,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":93,"categoryName":94,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[101,102,28,103,25,104,105,106,107],"writing","writing for agents","line","instructions","read","editing","documents",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":29},"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",[],[115,116,117,118,119,25,24,74,120,121,122,123,124,125,126,28,127],"verify","plan","verify plan","loops","task","verification","report","types","plan verification","entry","iterate","Existing","saved",{"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":134,"publishedAt":29},"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",[],[135,136,115,137,138,139,140,141,142,143,144,145,146,147,148,116,149,150,151,152],"impl","verify impl","adversarial","post","panel","via","critical","review","context7","up","evidence","reviewer","parallel","adr","audit","code","tdd","milestone",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":163,"publishedAt":29},"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",[159,160],{"categoryNo":93,"categoryName":94,"taxonomyType":66,"taxonomyTypeDesc":67},{"categoryNo":161,"categoryName":162,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000038","人力资源",[164,165,166,144,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"understand codebase","codebase","understand","walkthrough","analysis","SET","ci","learn","diagrams","repo health","implementing","re","quick","impact","get","project","deep","shared","map",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":189,"publishedAt":29},"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",[],[190,191,192,193,194,195,196,28,20,197,140,198,199,200,201,119,202,203,204,22],"compression","token compression","token","workflows","output","modes","accuracy","manual","intensity","tokens","hitl","three","general","auto","technical"]