[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MZ4D1ZC8MTW064QXY6WC76":3,"skill-same:01M6MZ4D1ZC8MTW064QXY6WC76":66},{"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":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6MZ4D1ZC8MTW064QXY6WC76","token-compression",null,"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.","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\u002Ftoken-compression\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"compression","token compression","token","intensity","workflows","modes","accuracy","for","mode","manual","output","via","technical","tokens","execution","hitl","three","task","general","auto","2026-11-10 10:12:30",false,"---\nname: token-compression\ndescription: >\n  Output token compression for AA-MA workflows. Reduces response tokens by 40-75%\n  while preserving full technical accuracy. Three intensity levels mapped to execution\n  modes: lite (HITL), full (general), ultra (AFK). Auto-activates during AA-MA\n  execution based on task Mode field. Manual activation via \u002Fcompress lite|full|ultra.\n---\n\n# Token Compression\n\nReduce output tokens while preserving technical substance. Inspired by\n[caveman](https:\u002F\u002Fgithub.com\u002FJuliusBrussee\u002Fcaveman) prompt compression patterns,\nadapted for AA-MA execution mode integration.\n\n## Activation\n\n- **Automatic:** During AA-MA execution, intensity is set by task Mode field\n  - `Mode: HITL` → lite (preserve clarity for human review)\n  - `Mode: AFK` → ultra (maximum compression for autonomous execution)\n- **Manual:** ask for \"compress lite|full|ultra\" to override during any session\n- **Default:** `full` when activated outside AA-MA execution context\n\n## Rules\n\nDrop: articles (a\u002Fan\u002Fthe), filler (just\u002Freally\u002Fbasically\u002Factually\u002Fsimply),\npleasantries (sure\u002Fcertainly\u002Fof course\u002Fhappy to), hedging (it might be worth,\nyou could consider). Fragments OK. Short synonyms (big not extensive, fix not\n\"implement a solution for\"). Technical terms exact. Code blocks unchanged.\nErrors quoted exact.\n\nPattern: `[thing] [action] [reason]. [next step].`\n\nNot: \"Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by...\"\nYes: \"Bug in auth middleware. Token expiry check use `\u003C` not `\u003C=`. Fix:\"\n\n## Intensity Levels\n\n| Level | Rules | When |\n|-------|-------|------|\n| **lite** | No filler\u002Fhedging. Keep articles + full sentences. Professional but tight. | HITL tasks, complex explanations, user-facing content |\n| **full** | Drop articles, fragments OK, short synonyms. | General use, default level |\n| **ultra** | Abbreviate (DB\u002Fauth\u002Fconfig\u002Freq\u002Fres\u002Ffn\u002Fimpl), strip conjunctions, arrows for causality (X → Y), one word when one word enough. | AFK tasks, autonomous execution, subagent output |\n\n### Examples\n\n**\"Why does the test fail?\"**\n- lite: \"The test fails because the mock returns an empty list instead of the expected user objects. Update the mock fixture to return test data.\"\n- full: \"Mock returns empty list, not expected user objects. Update mock fixture with test data.\"\n- ultra: \"Mock → empty list. Need test data in fixture.\"\n\n**\"Explain the deployment pipeline.\"**\n- lite: \"The pipeline runs lint, tests, and builds a Docker image. On merge to main, it deploys to staging automatically. Production requires manual approval.\"\n- full: \"Pipeline: lint → test → Docker build. Merge to main = auto-deploy staging. Prod needs manual approval.\"\n- ultra: \"lint→test→Docker→staging(auto). Prod=manual.\"\n\n## Auto-Clarity Exceptions\n\nDrop compression for:\n- Security warnings and vulnerability disclosures\n- Irreversible action confirmations (DELETE, DROP, force-push)\n- Multi-step sequences where fragment order risks misinterpretation\n- User appears confused or asks for clarification\n\nResume compression after the clear section is complete.\n\n**Example — destructive operation:**\n> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.\n> ```sql\n> DROP TABLE users;\n> ```\n> Compression resume. Verify backup first.\n\n## Boundaries\n\n- Code blocks: always rendered normally, never compressed\n- Commit messages: follow Conventional Commits format, never compressed\n- PR descriptions: write normally\n- Error messages: quote exact, never paraphrase\n- \"compress off\" or \"normal mode\": deactivate compression\n- Level persists until changed or session end\n\n## Integration with AA-MA Execution\n\nWhen the `aa-ma-execution` skill detects a task's `Mode:` field:\n\n```\nMode: AFK  → Skill(token-compression) at ultra\nMode: HITL → Skill(token-compression) at lite\nNo Mode    → Skill(token-compression) at full (default)\n```\n\nThis mapping ensures autonomous agents produce minimal output (saving tokens\nfor reasoning), while human-interactive sessions preserve enough context for\nthe user to follow along.\n","# Token Compression\n\nReduce output tokens while preserving technical substance. Inspired by\n[caveman](https:\u002F\u002Fgithub.com\u002FJuliusBrussee\u002Fcaveman) prompt compression patterns,\nadapted for AA-MA execution mode integration.\n\n## Activation\n\n- **Automatic:** During AA-MA execution, intensity is set by task Mode field\n  - `Mode: HITL` → lite (preserve clarity for human review)\n  - `Mode: AFK` → ultra (maximum compression for autonomous execution)\n- **Manual:** ask for \"compress lite|full|ultra\" to override during any session\n- **Default:** `full` when activated outside AA-MA execution context\n\n## Rules\n\nDrop: articles (a\u002Fan\u002Fthe), filler (just\u002Freally\u002Fbasically\u002Factually\u002Fsimply),\npleasantries (sure\u002Fcertainly\u002Fof course\u002Fhappy to), hedging (it might be worth,\nyou could consider). Fragments OK. Short synonyms (big not extensive, fix not\n\"implement a solution for\"). Technical terms exact. Code blocks unchanged.\nErrors quoted exact.\n\nPattern: `[thing] [action] [reason]. [next step].`\n\nNot: \"Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by...\"\nYes: \"Bug in auth middleware. Token expiry check use `\u003C` not `\u003C=`. Fix:\"\n\n## Intensity Levels\n\n| Level | Rules | When |\n|-------|-------|------|\n| **lite** | No filler\u002Fhedging. Keep articles + full sentences. Professional but tight. | HITL tasks, complex explanations, user-facing content |\n| **full** | Drop articles, fragments OK, short synonyms. | General use, default level |\n| **ultra** | Abbreviate (DB\u002Fauth\u002Fconfig\u002Freq\u002Fres\u002Ffn\u002Fimpl), strip conjunctions, arrows for causality (X → Y), one word when one word enough. | AFK tasks, autonomous execution, subagent output |\n\n### Examples\n\n**\"Why does the test fail?\"**\n- lite: \"The test fails because the mock returns an empty list instead of the expected user objects. Update the mock fixture to return test data.\"\n- full: \"Mock returns empty list, not expected user objects. Update mock fixture with test data.\"\n- ultra: \"Mock → empty list. Need test data in fixture.\"\n\n**\"Explain the deployment pipeline.\"**\n- lite: \"The pipeline runs lint, tests, and builds a Docker image. On merge to main, it deploys to staging automatically. Production requires manual approval.\"\n- full: \"Pipeline: lint → test → Docker build. Merge to main = auto-deploy staging. Prod needs manual approval.\"\n- ultra: \"lint→test→Docker→staging(auto). Prod=manual.\"\n\n## Auto-Clarity Exceptions\n\nDrop compression for:\n- Security warnings and vulnerability disclosures\n- Irreversible action confirmations (DELETE, DROP, force-push)\n- Multi-step sequences where fragment order risks misinterpretation\n- User appears confused or asks for clarification\n\nResume compression after the clear section is complete.\n\n**Example — destructive operation:**\n> **Warning:** This will permanently delete all rows in the `users` table and cannot be undone.\n> ```sql\n> DROP TABLE users;\n> ```\n> Compression resume. Verify backup first.\n\n## Boundaries\n\n- Code blocks: always rendered normally, never compressed\n- Commit messages: follow Conventional Commits format, never compressed\n- PR descriptions: write normally\n- Error messages: quote exact, never paraphrase\n- \"compress off\" or \"normal mode\": deactivate compression\n- Level persists until changed or session end\n\n## Integration with AA-MA Execution\n\nWhen the `aa-ma-execution` skill detects a task's `Mode:` field:\n\n```\nMode: AFK  → Skill(token-compression) at ultra\nMode: HITL → Skill(token-compression) at lite\nNo Mode    → Skill(token-compression) at full (default)\n```\n\nThis mapping ensures autonomous agents produce minimal output (saving tokens\nfor reasoning), while human-interactive sessions preserve enough context for\nthe user to follow along.\n",{"name":5,"description":7},"main","cd9a2962c9a7e0797fe440f7b1ba4ceccc16ae0d","claude-code\u002Fskills\u002Ftoken-compression",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":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add snewhouse\u002Faa-ma-forge --skill token-compression",{"tool":58,"command":59},"bunx","bunx skills add snewhouse\u002Faa-ma-forge --skill token-compression",{"tool":61,"command":62},"pnpm","pnpm dlx skills add snewhouse\u002Faa-ma-forge --skill token-compression","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Ftoken-compression\u002FSKILL.md",true,[],[67,92,119,139,163,193],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"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",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[79,80,81,82,83,84,85,86,87,88,89,90,91],"deploy","deploy helper","helper","can","you","with","live","releases","rollouts","deployments","use","shipping","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":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":104,"categoryName":105,"taxonomyType":76,"taxonomyTypeDesc":77},"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",[26,112,113,114,89,115,116,117,118],"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",[],[126,127,128,129,130,89,131,36,132,133,84,134,135,136,137,138,26],"verify plan","plan","verify","plan verification","user","verification","loops","types","report","saved","entry","iterate","Existing",{"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",[],[128,146,147,148,149,150,30,151,152,153,154,155,156,157,158,127,159,160,161,162],"impl","verify impl","adversarial","post","panel","critical","evidence","review","context7","up","reviewer","parallel","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":76,"taxonomyTypeDesc":77},{"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","understand codebase","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},"01M6MZ493XAJBXC35CHW4MV066","system-mapping","Lightweight pre-flight checklist for understanding system context before code changes. Perform 5-point analysis of architecture, execution flows, logging, dependencies, and environment. Use before modifying unfamiliar code or multi-file changes.","https:\u002F\u002Fgithub.com\u002Fsnewhouse\u002Faa-ma-forge\u002Fblob\u002Fmain\u002Fclaude-code\u002Fskills\u002Fsystem-mapping\u002FSKILL.md",[],[200,201,202,203,204,26,205,206,207,89,208,209,210,178,33,211,212,160,213,214],"system mapping","mapping","system","checklist","changes","flows","multi","dependencies","environment","context","check","file","logging","architecture","change"]