技能列表

Captures 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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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.

Create, evaluate, improve, benchmark, and publish OpenClaw skills. Use when building a new skill from scratch, iterating on an existing skill, running evals to measure quality, comparing skill versions, or analyzing patterns across installed skills to synthesize new ones. Triggers on: 'create a skill', 'build a skill', 'make a skill', 'eval this skill', 'improve this skill', 'benchmark skill versions', 'analyze skill patterns', 'synthesize skill from patterns', 'package skill', 'publish skill'.

Export any installed OpenClaw skill into a shareable ZIP: detects & stages external runtime files, generates STRUCTURE.md for LLM-guided install. Reads and packages local files only — no network calls, no APIs, no external transmissions.

|

基于用户意图发现并推荐 skill。分析用户输入，搜索匹配 skill，验证质量后推荐最佳匹配，由用户确认后安装。

通过需求收口帮用户从零设计一个 OpenClaw agent skill。逐步收集目标、输入、输出、过程控制，确认后输出完整的 skill 文件包（SKILL.md + 安装指南）。产出是文件，不替用户执行安装。当用户说"创建 skill"、"做一个技能"、"加一个能力"、"帮我把 XXX 变成 skill"时触发。

Skill 设计指南。在创建新 Skill、优化现有 Skill、或评审 Skill 质量时使用。包含核心设计原则、常见陷阱、最佳实践。

创建、编辑、优化或审查 OpenClaw AgentSkills 技能。提供完整的工作流程指引：技能结构设计、frontmatter 规范、_meta.json 格式、ClawHub scanner 规则、渐进式披露设计、validation checklist 及发布流程。适用于从零创建新技能或改进现有技能。输出：SKILL.md + _meta.json。

Skill碰撞引擎 —— 让Skill之间自动四向碰撞生成新Skill的元引擎，Skill工厂的自进化核心

Skill Creation Coach: guides users to turn their expertise into OpenClaw Skills through structured conversation.

Local-modification-preserving clawhub skill updater. Saves changes as diff patch, applies to new versions, reports conflicts clearly. No forced overwrites.

Audit locally installed agent skills for security/policy issues using the SkillLens CLI (`skilllens scan`, `skilllens config`). Use when asked to scan a skills directory (Codex/Claude) and produce a risk-focused audit report based on each skill's `SKILL.md` and bundled resources.