en un clic
context-manager
AI-powered context management for OpenClaw sessions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Menu
AI-powered context management for OpenClaw sessions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
霸下销售总监大师技能包 — 全球顶尖B2B销售能力。对标华为铁三角+Salesforce+麦肯锡谈判法。
墨白首席美学官大师技能包 — 全球顶级视觉战略能力。对标伦敦皇家艺术学院 + 奥美全球 + 苹果Jony Ive设计标准。
轩辕AI编码舰队——OpenClaw作为大脑,指挥Claude Code/Cursor/Windsurf/Trae/Codex CLI集群并行开发。覆盖:ACP配置、IDE接入、权限管理、任务分发、windsurf+cursor双IDE调度、worktree隔离、舰队看板。触发词:IDE舰队、编码集群、AI IDE、多工具编排、ACP配置、Cursor舰队、Windsurf集群、Trae接入、IDE调度、并行编码、AI编码引擎、IDE编排、coding fleet
项目进度追踪与SDLC全周期管理——ETA承诺、实时看板、风险预警、多项目并行调度。覆盖:任务拆解协议、ETA估算模型、进度追踪机制、日报/周报模板、风险预警系统、承诺驱动开发。触发词:项目进度、SDLC、ETA、甘特图、看板、燃尽图、里程碑、进度追踪、project management、进度汇报、阻塞告警
2025年最前沿的AI原生开发范式——VibeCoding。覆盖:Prompt-to-Product工作流、多轮对话管理、AI编码助手协作策略、代码质量保障、v0.dev/Lovable/Claude Code/Replit Agent工具链集成。触发词:vibecoding、VibeCoding、AI原生开发、提示即产品、AI pair programming、conversation-driven coding、prompt engineering for products
飞书云文档内容优化与格式美化。当用户需要优化飞书文档的排版、结构、格式、美观度时使用此技能。支持:(1) 读取飞书文档内容 (2) 优化文档结构和层次 (3) 清空并替换文档内容 (4) 通过浏览器自动化编辑文档。触发词:优化飞书文档、美化文档、整理文档格式、文档排版。
| name | context-manager |
| description | AI-powered context management for OpenClaw sessions |
| user-invocable | true |
| author | Daniel Li |
AI-powered context management for OpenClaw sessions. Uses the agent itself to generate intelligent summaries, then resets the session with compressed context.
# List all sessions with usage stats
~/openclaw/skills/context-manager/compress.sh list
# Check status of a specific session
~/openclaw/skills/context-manager/compress.sh status agent:main:main
# Generate AI summary (read-only, safe)
~/openclaw/skills/context-manager/compress.sh summarize agent:main:main
# Compress session: generate summary, reset, inject (DESTRUCTIVE)
~/openclaw/skills/context-manager/compress.sh summarize agent:main:main --replace
memory/compressed/Key insight: The agent has full visibility into its own context, so it generates the best possible summary.
| Command | Description |
|---|---|
list | List all sessions with token usage |
status [KEY] | Show detailed status for a session |
summarize [KEY] | Generate AI summary (read-only) |
summarize [KEY] --replace | Summarize AND reset session with compressed context |
compress [KEY] | Legacy grep-based extraction (not recommended) |
check [KEY] | Check if session exceeds threshold |
check-all | Check all sessions at once |
| Command | Description |
|---|---|
set-threshold N | Set compression threshold (50-99%, default: 80) |
set-depth LEVEL | Set depth: brief/balanced/comprehensive |
set-quiet-hours HH | Set quiet hours (e.g., "23:00-07:00") |
help | Show help and usage examples |
$ ~/openclaw/skills/context-manager/compress.sh list
📋 Available Sessions (4 total)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
# SESSION KEY KIND TOKENS USAGE
1 agent:main:main direct 70188 70%
2 agent:main:slack:channel:c0aaruq2en9 group 20854 20%
3 agent:main:cron:0d02af4b-... direct 18718 18%
$ ~/openclaw/skills/context-manager/compress.sh status agent:main:main
📊 Context Manager Status
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Session Key: agent:main:main
Session ID: fc192a2d-091c-48c7-9fad-12bf34687454
Kind: direct
Model: gemini-3-flash
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Threshold: 80%
Tokens: 70188 / 100000
Usage: 70%
$ ~/openclaw/skills/context-manager/compress.sh summarize agent:main:main
🧠 Requesting AI summary for session: agent:main:main
Session ID: fc192a2d-091c-48c7-9fad-12bf34687454
✅ AI Summary generated!
Saved to: memory/compressed/20260127-123146.ai-summary.md
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
### Session Summary: January 27, 2026
#### 1. What was accomplished
- System audit completed
- Essay generation with sub-agents
...
$ ~/openclaw/skills/context-manager/compress.sh summarize agent:main:main --replace
🧠 Requesting AI summary for session: agent:main:main
Session ID: fc192a2d-091c-48c7-9fad-12bf34687454
Mode: REPLACE (will reset session after summary)
✅ AI Summary generated!
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[AI-generated summary displayed]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔄 Resetting session and injecting compressed context...
Backing up session file...
Backup saved: memory/compressed/20260127-123146.session-backup.jsonl
Deleting session JSONL to reset...
Injecting compressed context into fresh session...
✅ Session compressed successfully!
Old session ID: fc192a2d-091c-48c7-9fad-12bf34687454
New session ID: a1b2c3d4-...
Session is ready to continue with compressed context
Result: 70k tokens → 16k tokens (77% reduction)
When compression occurs, these files are created in memory/compressed/:
| File | Description |
|---|---|
{timestamp}.ai-summary.md | AI-generated session summary |
{timestamp}.session-backup.jsonl | Full backup of original session (can restore if needed) |
{timestamp}.transcript.md | Raw transcript extraction (legacy) |
{timestamp}.summary.md | Grep-based summary (legacy) |
brew install jq)openclaw agent and openclaw sessionsThe script uses JSONL deletion to reset sessions (official method):
memory/compressed/~/.openclaw/agents/{agent}/sessions/{sessionId}.jsonlopenclaw agent --to mainThe /reset slash command only works in the chat interface. When sent via openclaw agent --session-id, it's treated as a regular message and the agent tries to interpret it as a task.
The script asks the agent to provide:
If the AI summary extraction fails, check stderr redirect:
# The script uses 2>/dev/null to avoid Node deprecation warnings breaking JSON
openclaw agent --session-id $ID -m "..." --json 2>/dev/null
Verify the JSONL file path:
ls ~/.openclaw/agents/main/sessions/
If something goes wrong:
cp memory/compressed/{timestamp}.session-backup.jsonl \
~/.openclaw/agents/main/sessions/{sessionId}.jsonl
Use openclaw logs to troubleshoot:
openclaw logs --limit 50 --json | grep -i "error\|fail"
summarize without --replace first to verify the summary qualitystatus to verify compression workedopenclaw sessions --helpopenclaw agent --help