メニュー
Captures learnings, errors, corrections for continuous improvement.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.
Transform agents from task-followers into proactive partners.
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.
自动生成短视频。支持图文轮播、文字动画、卡片风格和 AI 视频大模型生成等多种视频类型。用户需要生成视频时使用此技能。
Process multiple items with progress tracking, checkpointing, and failure recovery.
增强版浏览器自动化。基于 Playwright 实现完整浏览器操作，包括基础导航、截图、点击、表单填写、内容提取、文件上传/下载、多标签页管理。支持反检测和高级自动化。
| name | self-improvement |
| description | Captures learnings, errors, corrections for continuous improvement. |
| triggers | null |
| version | 1.0.0 |
| status | stable |
| updated | "2026-03-11T00:00:00.000Z" |
| provides | ["self_improvement"] |
| os | ["darwin","linux","win32"] |
| clawdbot | {"emoji":"🛠️","category":"tools","priority":"medium"} |
| Situation | Action |
|---|---|
| Command fails | Log to .learnings/ERRORS.md |
| User corrects you | .learnings/LEARNINGS.md (correction) |
| Missing feature | .learnings/FEATURE_REQUESTS.md |
| Better approach found | .learnings/LEARNINGS.md (best_practice) |
| Broadly applicable | Promote to AGENTS.md / TOOLS.md / SOUL.md |
Auto: on failure, correction, or feature request.
Full reference:
SKILL-REFERENCE.md
