AI 智能体 技能与专家

防遗忘防卡顿的context管理协议。自动监控水位、分区管理、压缩前存档、压缩后恢复。适用于所有OpenClaw agent和sub-agent。在heartbeat或session启动时触发。

Automatically converts raw long conversations into structured, themed Markdown knowledge cards with source traceability, running incrementally and silently i...

Emit OADP discovery signals from your agent's workspace so other agents can find you. Adds markers to your files, configures .well-known endpoints, and joins...

Run multi-model AI synthesis inquiries via QuorumAI. Four AI models (Claude, GPT, Gemini, Grok) compete to answer your question from specialized perspectives...

Meta-cognitive reasoning skill that makes any AI agent dramatically better at decision-making by thinking backwards before acting forward. Applies Munger's I...

Optimize OpenClaw agent context files by reducing token usage 30-50% with backups, preview, rollback, and preserving core functionality on request.

Require verifiable human approval before high-risk agent actions.

Query up-to-date library documentation and code examples using Context7 MCP. Use when you need current, version-specific documentation for npm packages, Pyth...

Transfer memory files from one OpenClaw agent to another. Use when you need to migrate memory, configuration, or context from one agent to another agent.

Automated soul synthesis for AI agents. Extracts identity from memory files, promotes recurring patterns to axioms (N>=3), generates SOUL.md with full proven...

Optimize Azure dev/test environment costs with auto-shutdown schedules and Dev/Test pricing enrollment

Use AI AutoGLM Phone Agent for automated mobile device control. Suitable for tasks requiring mobile phone automation, such as APP automated testing, data col...

实时记录和展示 Agent 任务执行进度，支持任务开始、命令执行、状态更新及错误日志的统一管理。

OpenClaw Agent App Installer: install/upgrade & register the jun-invest-option-master-agent isolated agent workspace. Includes auto backup/versioning to Claw...

Documents Followin OpenAPI endpoints for agent integration. Use when calling feed APIs, channel feeds, trending, category feeds, or integrating with Followin...

Use when executing implementation plans with independent tasks in the current session. Features domain-specialist routing, independent verification gates, an...

Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turn...

Provide step-by-step diagnostics and command-line fixes for common OpenClaw issues including memory plugin faults, Feishu disconnects, LLM timeouts, and Tele...

This skill should be used when the user asks to "create a multi-agent system", "spawn agents for parallel tasks", "decompose task recursively", "set up agent...

Multi-agent development team workflow skill. Use when coordinating complex development tasks requiring multiple specialized roles - PM, Architect, Developer,...

Create and manage automated workflows visually with drag-and-drop triggers, actions, conditions, and 100+ integrations without coding.

Ping major LLM providers in parallel and compare real API latency. Run with /ping

Fixes the three OpenClaw memory failure modes: /new amnesia (agent forgets everything after a fresh session), compaction loss (context fills up, compact fire...

Run long-lived AI coding agents (Codex, Claude Code) in persistent tmux sessions with Ralph retry loops and completion hooks. Use when running multi-step cod...