[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CM15F0F2Y0BT0CJKZXGMBM":3,"skill-same:01M7CM15F0F2Y0BT0CJKZXGMBM":48},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7CM15F0F2Y0BT0CJKZXGMBM","context-compression",null,"Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.","haliltek\u002Fdev.tr","haliltek","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F31656259?v=4","01M7CKZCVHYRZ5CFNDBMFT5S7Q","Halil TEK","01M7CKZCWH3RX91D93NHE4DP2J",0,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcontext-compression\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: context-compression\ndescription: Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.\nwhen_to_use: \"When a session has 20+ turns, when context feels repetitive, when the agent is losing track of earlier work, or when the user says 'summarize what we've done'. NOT for short sessions.\"\nallowed-tools: Read, Write, Grep\nversion: 1.0.0\neffort: low\n---\n\n# Context Compression — Long Session Management\n\n> Keep sessions productive by compressing completed work while preserving key decisions.\n\n## Overview\n\nLong sessions (30+ turns) cause context degradation — the AI loses track of earlier work, repeats itself, or forgets decisions. Context compression proactively summarizes completed phases so the context window stays focused on active work.\n\n**Token Impact:** Recovers 5,000-15,000 tokens in long sessions by replacing verbose tool outputs with semantic summaries.\n\n---\n\n## When to Compress\n\n| Signal | Action |\n|---|---|\n| Session has 20+ turns | Consider proactive compression |\n| Agent repeats earlier suggestions | Context is saturated — compress now |\n| User says \"we already discussed this\" | Compress immediately |\n| Switching to a new phase of work | Compress the completed phase |\n| Large tool output (500+ lines) | Micro-compact the output |\n\n---\n\n## Compression Levels\n\n### Level 1: Micro-Compact (Tool Output)\n\nCompress individual tool outputs while retaining semantic content:\n\n```\n❌ Before (raw grep output — 200 lines, ~4,000 tokens):\nsrc\u002Fauth\u002Fjwt.ts:15: import { verify } from 'jsonwebtoken'\nsrc\u002Fauth\u002Fjwt.ts:23: export function validateToken(token: string) {\nsrc\u002Fauth\u002Fjwt.ts:24:   try {\nsrc\u002Fauth\u002Fjwt.ts:25:     const decoded = verify(token, SECRET)\n... (195 more lines)\n\n✅ After (micro-compact — 5 lines, ~100 tokens):\nGrep results for \"jwt\": Found 8 files, 42 matches.\nKey files: src\u002Fauth\u002Fjwt.ts (main JWT logic), src\u002Fmiddleware\u002Fauth.ts (middleware),\nsrc\u002Fapi\u002Flogin.ts (token creation). Token validation at jwt.ts:23-40.\nError handling at jwt.ts:42-55. Secret loaded from env at jwt.ts:8.\n```\n\n### Level 2: Phase Summary\n\nReplace a completed work phase with a summary:\n\n```\n❌ Before (full research transcript — ~3,000 tokens):\n[turn 1] Read package.json...\n[turn 2] Read src\u002Findex.ts...\n[turn 3] Grep for \"auth\"...\n[turn 4] Found 8 files related to auth...\n[turn 5] Read src\u002Fauth\u002Fjwt.ts...\n... (10 more turns of exploration)\n\n✅ After (phase summary — ~200 tokens):\n## Research Phase Complete\n- Project: Next.js 15 app with JWT auth\n- Auth files: 8 files in src\u002Fauth\u002F, src\u002Fmiddleware\u002F, src\u002Fapi\u002F\n- Token flow: login → create JWT → store in httpOnly cookie → validate in middleware\n- Bug location: src\u002Fauth\u002Fjwt.ts:45 — expiry check uses `\u003C` instead of `\u003C=`\n- Decision: Fix the comparison operator, add edge case test\n```\n\n### Level 3: Session Checkpoint\n\nFull session summary for long-running work:\n\n```markdown\n## Session Checkpoint (Turn 35)\n\n### Completed\n- [x] Researched auth system (8 files, JWT flow mapped)\n- [x] Fixed token expiry bug in jwt.ts:45\n- [x] Added edge case test in jwt.test.ts\n- [x] Verified: all 42 tests passing\n\n### In Progress\n- [ ] Update API documentation\n- [ ] Review related middleware\n\n### Key Decisions\n1. Keep httpOnly cookies (not localStorage) for token storage\n2. Use `\u003C=` for expiry check to include exact-moment expiry\n3. Add 5-minute grace period for clock skew\n\n### Files Modified\n- src\u002Fauth\u002Fjwt.ts (line 45: comparison fix)\n- tests\u002Fauth\u002Fjwt.test.ts (added 3 edge case tests)\n```\n\n---\n\n## Compression Protocol\n\n### Step 1: Identify Completed Phases\n```\nWhat work is DONE and won't be revisited?\n→ Research findings already synthesized\n→ Implementation already verified\n→ Decisions already made and applied\n```\n\n### Step 2: Extract Key Information\n```\nFrom the completed phase, preserve:\n✅ Decisions made and WHY\n✅ File paths and line numbers of changes\n✅ Key findings that inform ongoing work\n✅ Error messages or test results (summarized)\n\nDiscard:\n❌ Step-by-step tool invocation details\n❌ Full file contents that were read\n❌ Exploratory dead-ends that didn't lead anywhere\n❌ Verbose error stack traces (keep the message only)\n```\n\n### Step 3: Write Summary\n```\nUse the Phase Summary format above.\nKeep to 100-300 tokens per completed phase.\nInclude enough detail to resume work without re-reading.\n```\n\n---\n\n## Best Practices\n\n1. **Compress phases, not facts** — Individual decisions should stay, full transcripts should go\n2. **Preserve \"why\" over \"what\"** — Why a decision was made matters more than the exact commands run\n3. **Never auto-compress** — Always tell the user \"I'm summarizing the completed research phase to keep context focused\"\n4. **Keep file references** — Always preserve file paths and line numbers in summaries\n5. **Checkpoint on phase transitions** — Natural compression point when switching from research to implementation\n","# Context Compression — Long Session Management\n\n> Keep sessions productive by compressing completed work while preserving key decisions.\n\n## Overview\n\nLong sessions (30+ turns) cause context degradation — the AI loses track of earlier work, repeats itself, or forgets decisions. Context compression proactively summarizes completed phases so the context window stays focused on active work.\n\n**Token Impact:** Recovers 5,000-15,000 tokens in long sessions by replacing verbose tool outputs with semantic summaries.\n\n---\n\n## When to Compress\n\n| Signal | Action |\n|---|---|\n| Session has 20+ turns | Consider proactive compression |\n| Agent repeats earlier suggestions | Context is saturated — compress now |\n| User says \"we already discussed this\" | Compress immediately |\n| Switching to a new phase of work | Compress the completed phase |\n| Large tool output (500+ lines) | Micro-compact the output |\n\n---\n\n## Compression Levels\n\n### Level 1: Micro-Compact (Tool Output)\n\nCompress individual tool outputs while retaining semantic content:\n\n```\n❌ Before (raw grep output — 200 lines, ~4,000 tokens):\nsrc\u002Fauth\u002Fjwt.ts:15: import { verify } from 'jsonwebtoken'\nsrc\u002Fauth\u002Fjwt.ts:23: export function validateToken(token: string) {\nsrc\u002Fauth\u002Fjwt.ts:24:   try {\nsrc\u002Fauth\u002Fjwt.ts:25:     const decoded = verify(token, SECRET)\n... (195 more lines)\n\n✅ After (micro-compact — 5 lines, ~100 tokens):\nGrep results for \"jwt\": Found 8 files, 42 matches.\nKey files: src\u002Fauth\u002Fjwt.ts (main JWT logic), src\u002Fmiddleware\u002Fauth.ts (middleware),\nsrc\u002Fapi\u002Flogin.ts (token creation). Token validation at jwt.ts:23-40.\nError handling at jwt.ts:42-55. Secret loaded from env at jwt.ts:8.\n```\n\n### Level 2: Phase Summary\n\nReplace a completed work phase with a summary:\n\n```\n❌ Before (full research transcript — ~3,000 tokens):\n[turn 1] Read package.json...\n[turn 2] Read src\u002Findex.ts...\n[turn 3] Grep for \"auth\"...\n[turn 4] Found 8 files related to auth...\n[turn 5] Read src\u002Fauth\u002Fjwt.ts...\n... (10 more turns of exploration)\n\n✅ After (phase summary — ~200 tokens):\n## Research Phase Complete\n- Project: Next.js 15 app with JWT auth\n- Auth files: 8 files in src\u002Fauth\u002F, src\u002Fmiddleware\u002F, src\u002Fapi\u002F\n- Token flow: login → create JWT → store in httpOnly cookie → validate in middleware\n- Bug location: src\u002Fauth\u002Fjwt.ts:45 — expiry check uses `\u003C` instead of `\u003C=`\n- Decision: Fix the comparison operator, add edge case test\n```\n\n### Level 3: Session Checkpoint\n\nFull session summary for long-running work:\n\n```markdown\n## Session Checkpoint (Turn 35)\n\n### Completed\n- [x] Researched auth system (8 files, JWT flow mapped)\n- [x] Fixed token expiry bug in jwt.ts:45\n- [x] Added edge case test in jwt.test.ts\n- [x] Verified: all 42 tests passing\n\n### In Progress\n- [ ] Update API documentation\n- [ ] Review related middleware\n\n### Key Decisions\n1. Keep httpOnly cookies (not localStorage) for token storage\n2. Use `\u003C=` for expiry check to include exact-moment expiry\n3. Add 5-minute grace period for clock skew\n\n### Files Modified\n- src\u002Fauth\u002Fjwt.ts (line 45: comparison fix)\n- tests\u002Fauth\u002Fjwt.test.ts (added 3 edge case tests)\n```\n\n---\n\n## Compression Protocol\n\n### Step 1: Identify Completed Phases\n```\nWhat work is DONE and won't be revisited?\n→ Research findings already synthesized\n→ Implementation already verified\n→ Decisions already made and applied\n```\n\n### Step 2: Extract Key Information\n```\nFrom the completed phase, preserve:\n✅ Decisions made and WHY\n✅ File paths and line numbers of changes\n✅ Key findings that inform ongoing work\n✅ Error messages or test results (summarized)\n\nDiscard:\n❌ Step-by-step tool invocation details\n❌ Full file contents that were read\n❌ Exploratory dead-ends that didn't lead anywhere\n❌ Verbose error stack traces (keep the message only)\n```\n\n### Step 3: Write Summary\n```\nUse the Phase Summary format above.\nKeep to 100-300 tokens per completed phase.\nInclude enough detail to resume work without re-reading.\n```\n\n---\n\n## Best Practices\n\n1. **Compress phases, not facts** — Individual decisions should stay, full transcripts should go\n2. **Preserve \"why\" over \"what\"** — Why a decision was made matters more than the exact commands run\n3. **Never auto-compress** — Always tell the user \"I'm summarizing the completed research phase to keep context focused\"\n4. **Keep file references** — Always preserve file paths and line numbers in summaries\n5. **Checkpoint on phase transitions** — Natural compression point when switching from research to implementation\n",{"name":5,"effort":24,"version":25,"description":7,"when_to_use":26,"allowed-tools":27},"low","1.0.0","When a session has 20+ turns, when context feels repetitive, when the agent is losing track of earlier work, or when the user says 'summarize what we've done'. NOT for short sessions.","Read, Write, Grep","main","35fc33da79b31d7f8dadfc704083baff1b5672a0",".agents\u002Fskills\u002Fcontext-compression","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr","https:\u002F\u002Fgithub.com\u002Fhaliltek","2026-11-13 01:38:48",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add haliltek\u002Fdev.tr --skill context-compression",{"tool":40,"command":41},"bunx","bunx skills add haliltek\u002Fdev.tr --skill context-compression",{"tool":43,"command":44},"pnpm","pnpm dlx skills add haliltek\u002Fdev.tr --skill context-compression","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcontext-compression\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7CM8JAC0X6HVS8VCHH51KPZ","respectfully","Wraps any prompt with a reminder to respect CLAUDE.md files","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frespectfully\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CM8FPHK4J5EP607Y77XHA4","recruiter","Think like a skeptical technical recruiter when working on the daily.dev Recruiter platform. Use when reviewing UI\u002FUX, features, or code in webapp\u002Fpages\u002Frecruiter.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frecruiter\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7CM8CB9XR2W46XJ3T2X0245","changelog","Generate a daily.dev changelog post for a new feature or update. Use when a team member needs to write a changelog announcement.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CM88HKHZP4S2H9GYKWCBPB","webapp-testing","Web application testing principles. E2E, Playwright, deep audit strategies.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CM831R2XYCHFNRGXD6NYS1","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CM7XTJ13ZQFZ9Y5SRYF8CP","vulnerability-scanner","Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.","https:\u002F\u002Fgithub.com\u002Fhaliltek\u002Fdev.tr\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvulnerability-scanner\u002FSKILL.md",[],[]]