context-compressor

安装量: 81
排名: #9672

安装

npx skills add https://github.com/oimiragieo/agent-studio --skill context-compressor

Context Compressor Skill Step 1: Identify Compressible Content Content types that can be compressed: Type Compression Strategy Code Keep signatures, summarize implementations Conversations Extract decisions, drop small talk Documentation Keep headings and key points Errors Keep message and location, drop stack frames Logs Keep patterns, drop repetitions Step 2: Apply Compression Techniques Technique 1: Decision Extraction Before: User: Should we use Redis or Memcached? Assistant: Let me analyze both options... [500 words of analysis] Recommendation: Redis for pub/sub support. User: Ok let's use Redis. After: Decision: Use Redis (chosen for pub/sub support) Technique 2: Code Summarization Before: // 100 lines of UserService implementation After: UserService: CRUD operations for users - Methods: create, read, update, delete, findByEmail - Dependencies: db, validator, logger - Location: src/services/user.js Technique 3: Error Compression Before: Error: Cannot read property 'id' of undefined at UserController.getUser (src/controllers/user.js:45:23) at Layer.handle [as handle_request] (node_modules/express/lib/router/layer.js:95:5) ... 20 more stack frames After: Error: Cannot read 'id' of undefined @ src/controllers/user.js:45 Cause: User object is null when accessing .id Step 3: Structure Compressed Output Use consistent formats:

Session Summary

Decisions Made

[D1] Use Redis for caching

[D2] JWT for authentication

Files Modified

src/auth/jwt.js (new)

src/config/redis.js (updated)

Open Items

[ ] Add rate limiting

[ ] Write tests for JWT
Step 4: Validate Compression
Ensure critical info preserved:
All decisions captured
Key file locations retained
Error causes documented
Next steps clear
Preserve Decisions
Never lose decision rationale
Keep Locations
File paths and line numbers are critical
Summarize, Don't Delete
Transform verbose content
Use References
Point to files instead of including content
Test Recovery
Can you continue work from compressed context? Compress the last 10 messages for context handoff Example Response :

Context Summary (compressed from 10 messages)

Task Implementing user authentication with JWT

Progress 1. Created JWT utility (src/auth/jwt.js) 2. Added login endpoint (src/routes/auth.js) 3. Tests failing - mock issue

Key Decisions

Using RS256 for JWT signing (security over performance)

1-hour token expiry with refresh tokens

Current Issue Jest mock for jwt.sign not working Location: src/auth/ ** tests ** /jwt.test.js:23

Next Steps 1. Fix JWT mock 2. Add refresh token endpoint Rules Never lose decision rationale Always include file locations Test that work can continue from compressed context Workflow Integration This skill supports multi-agent orchestration by enabling efficient context management: Router Decision: .claude/workflows/core/router-decision.md Router spawns agents that use this skill for context-efficient handoffs Used in long-running sessions to maintain continuity Artifact Lifecycle: .claude/workflows/core/skill-lifecycle.md Compression patterns evolve with framework changes Session summaries feed into memory protocol Related Workflows: session-handoff skill for complete handoff protocol swarm-coordination skill for multi-agent context sharing Memory Protocol (MANDATORY) Before starting: cat .claude/context/memory/learnings.md After completing: New pattern -> .claude/context/memory/learnings.md Issue found -> .claude/context/memory/issues.md Decision made -> .claude/context/memory/decisions.md ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.

返回排行榜