self▌

Autonomous design critique mode that adds annotations to web pages via the Agentation toolbar in a visible browser. \n \n Requires the Agentation toolbar installed on the target page and the agent-browser skill available; launches in headed mode so users watch the agent scan, hover, and annotate in real time \n Uses coordinate-based mouse events to trigger annotation dialogs (standard element clicks do not work); includes helper patterns for scrolling, bounding box lookup, and dialog interaction

Automatically capture errors, corrections, and best practices to evolve agent capabilities safely over time. \n \n Records seven types of triggers (failures, user corrections, feature requests, API errors, knowledge gaps, better approaches, task reviews) into structured markdown files with deduplication to avoid low-value entries \n Promotes repeated patterns (≥3 occurrences) from learning logs into permanent capability files (AGENTS.md, TOOLS.md, SOUL.md) or extracts them as independent skills

A skill for continuous self-improvement. The agent tracks mistakes, lessons learned, and improvements over time through regular heartbeat-triggered reflections.

Autonomously research new technologies from the web and generate reusable agent skills. \n \n Discovers authoritative documentation via web search, prioritizing official docs, GitHub repositories, and blogs \n Extracts installation, core concepts, API references, and code examples from 3–5 high-quality sources \n Generates a self-contained skill with YAML frontmatter, markdown instructions, and optional bundled resources (scripts, references, assets) \n Saves skills to workspace-specific or glob

soul-self-evolution \n 对 SOUL.md 或 docs/reference/SOUL.md 进行受控更新： \n \n 只允许改动可演进段 \n 记录 checkpoint \n 支持一键回滚 \n \n 调用 \n python3 skills/soul-self-evolution/run.py apply --path docs/reference/SOUL.md --changes '[{\"section\":\"## Collaboration Preferences\",\"content\":\"- Keep updates concise.\"}]' \n python3 skills/soul-self-evolution/run.py list_checkpoints\n

Captures learnings, errors, and corrections to enable continuous improvement across agent sessions. \n \n Logs failures, user corrections, knowledge gaps, and API errors to structured markdown files ( .learnings/LEARNINGS.md , ERRORS.md , FEATURE_REQUESTS.md ) with consistent ID, priority, and status tracking \n Supports promotion of broadly applicable learnings to project memory files ( CLAUDE.md , AGENTS.md , .github/copilot-instructions.md ) and workspace files in OpenClaw ( SOUL.md , TOOLS.m