Proactive Self-Improving Agent
Skill ยืนยันแล้ว自动捕获经验并安全进化的技能。触发条件：(1)命令/操作失败时→记ERRORS.md (2)被用户纠正('不对'/'应该是')时→记LEARNINGS.md (3)用户需要不存在的能力时→记FEATURE_REQUESTS.md (4)外部API/工具出错时→记ERRORS.md (5)发现自己知识过时/错误时→记LEARNINGS.md (6)发现更好做法时→记LEARNINGS.md (7)每个任务完成时→回顾过程，有新经验则记LEARNINGS.md。去重原则：如果没有新经验或已有条目已覆盖则跳过不写。每次写入同时在.learnings/CHANGELOG.md追加JSONL日志。经验反复出现≥3次时晋升到AGENTS.md/TOOLS.md/SOUL.md。详见正文。
This skill enhances agent capabilities by automatically logging errors, user corrections, and task reviews into structured files (.learnings/LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md). It includes mechanisms for experience evolution, such as promoting learnings to permanent rules or extracting them into new skills, all while maintaining safety and logging all actions in CHANGELOG.md.
การติดตั้ง
npx skills add yanhongxi-openclaw/proactive-self-improving-agentเรียกใช้ Vercel skills CLI (skills.sh) ผ่าน npx — ต้องติดตั้ง Node.js ในเครื่อง และมี agent ที่รองรับ skills อย่างน้อยหนึ่งตัว (Claude Code, Cursor, Codex, …) ทั้งนี้สมมติว่า repo ใช้รูปแบบ agentskills.io
ส่วนขยายที่คล้ายกัน
Self-Improvement
92Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
OpenClaw Config
98Manage OpenClaw bot configuration - channels, agents, security, and autopilot settings
Tandem TypeScript Client
98TypeScript client for the Tandem autonomous agent engine HTTP + SSE API
3D Graphics with Three.js
983D web graphics with Three.js (WebGL/WebGPU). Capabilities: scenes, cameras, geometries, materials, lights, animations, model loading (GLTF/FBX), PBR materials, shadows, post-processing (bloom, SSAO, SSR), custom shaders, instancing, LOD, physics, VR/XR. Actions: create, build, animate, render 3D scenes/models. Keywords: Three.js, WebGL, WebGPU, 3D graphics, scene, camera, geometry, material, light, animation, GLTF, FBX, OrbitControls, PBR, shadow mapping, post-processing, bloom, SSAO, shader, instancing, LOD, WebXR, VR, AR, product configurator, data visualization, architectural walkthrough, interactive 3D, canvas. Use when: creating 3D visualizations, building WebGL/WebGPU apps, loading 3D models, adding animations, implementing VR/XR, creating interactive graphics, building product configurators.
Claude to DeerFlow
96Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
Context Degradation Patterns
95Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.