Browse the full skills directory.浏览完整技能目录。
Filter by query, category, scenario, platform, and risk signals with server-side catalog results.按关键词、品类、场景、平台和风险信号筛选；URL 参数会直接下推到目录 API。
10 resultsPage 2
Community-indexed skills are not individually editor-curated; review risk signals, source, and maintenance before install.
arming-thought
触发：在每次新的顶层对话开始时自动调用，用于建立“实事求是”的总原则，并在明确适用时为后续任务选择下游 skill；如果你是被派遣执行单一具体任务的子 agent，则跳过此 skill。 English: Trigger at the st
autobrowse
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and imp
harness
하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시,
cc-sdd-new-agent
Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end. Use when i
acontext-installer
Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.
workspace-dispatch
Single-agent mission orchestrator. Decomposes a mission into tasks, spawns one worker per task using the default model,
refly
Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user inte
autoresearch
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experim
memos-local
Persistent local memory for OpenClaw agents. Use when users say: - "install memos" - "install MemOS" - "setup memory" -
Agents Best Practices
Provider-neutral guidance for designing, auditing, and refactoring production agentic harnesses.