跳到正文
cccskills
免费在 GitHub 公开

session-compression

Lossless session context compression for token efficiency. Extracts entities, decisions, and state into compact format before context window fills. 10-30x reduction in context size while preserving all actionable information.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Session Compression

Compress session context without losing actionable information. Use before context window fills up or when handing off between sessions.

Why Compress

MetricRaw ContextCompressed
Token count~50K~3-5K
Decision countScatteredIndexed
File referencesBuried in proseListed
Error historyVerbose stack tracesRoot cause + fix
Reduction1x10-30x

Compression Format

ACDE Format (Actions, Context, Decisions, Entities)

## A: Actions Completed
- [x] Refactored auth middleware (auth.ts, middleware.ts)
- [x] Added rate limiting (api/limiter.ts)
- [ ] Pending: Write tests for rate limiter

## C: Context
- Project: my-app (Next.js 16, TypeScript)
- Branch: feat/auth-refactor (3 commits ahead of main)
- Blockers: None

## D: Decisions
- D1: JWT over sessions (stateless, mobile-friendly)
- D2: 100 req/min rate limit (based on load test)
- D3: Rejected Redis session store (overkill for current scale)

## E: Entities
- Files: auth.ts:42, middleware.ts:15, api/limiter.ts (new)
- Deps: jsonwebtoken@9.0.0, express-rate-limit@7.0.0
- APIs: POST /auth/login, POST /auth/refresh, GET /auth/me

When to Compress

  1. Pre-compact: Before context window compression (auto via hook)
  2. Session handoff: When switching between sessions on same project
  3. Agent delegation: When handing complex task to another agent
  4. Milestone reached: After completing a significant piece of work

Compression Rules

What to Keep (Lossless)

  • All decisions with reasoning (D1, D2, D3...)
  • File paths and line numbers of changes
  • Unresolved blockers or pending items
  • Error root causes (not full stack traces)
  • External constraints

What to Drop (Safe)

  • Exploratory reads that didn't lead anywhere
  • Redundant confirmations ("yes that looks good")
  • Intermediate debugging steps (keep only root cause)
  • Tool output that was just for verification
  • Repeated context that's already in CLAUDE.md

Entity Coding

Replace verbose references with short codes:

"the authentication middleware in src/middleware/auth.ts" -> "auth.ts"
"the user requested that we use JWT tokens" -> "D1: JWT"
"the PostgreSQL database running on port 5432" -> "pg:5432"

Integration

Pre-Compact Hook

The session-compressor hook automatically generates ACDE format before context compression:

  1. Scans recent tool calls for file paths -> E section
  2. Extracts decisions from conversation -> D section
  3. Lists completed/pending tasks -> A section
  4. Summarizes project state -> C section

With Memory Palace

Compressed sessions feed into the palace:

  • Decisions -> stored as drawers in appropriate rooms
  • Entities -> indexed for cross-session search
  • Actions -> tracked in thoughts/PROGRESS.md

With Compass Agent

Compass uses ACDE format for "where were we?" recovery:

Last session compressed:
A: 3 done, 1 pending (rate limiter tests)
D: JWT auth, 100rpm limit
E: auth.ts, middleware.ts, limiter.ts

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

axe-core integration, WCAG 2.2 AA checklist, keyboard navigation testing, screen reader testing, and ARIA pattern validation.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Agent Context Isolation

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Agent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik denetimi. Yeni agent/skill eklendiginde veya mevcut dosyalar duzenlediginde otomatik calistirilir.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

查看 vibeeval 的全部技能

报告此技能的问题