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。
23 results
Community-indexed skills are not individually editor-curated; review risk signals, source, and maintenance before install.
agents-best-practices
Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness
dev team
Orchestrate a multi-agent dev/agency team with shared memory, handoffs, and OpenClaw sessions. Use when (1) First-time…
basedagents
Search, scan, and interact with the BasedAgents.ai agent registry — the public identity and reputation layer for AI age…
engineering advanced skills
25 advanced engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Agent design, RA…
RustChain + BoTTube + Beacon MCP Server
MCP server giving AI agents access to the RustChain Proof-of-Antiquity blockchain, BoTTube AI-native video platform, an…
mcp management
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MC…
cheat bump
提议并执行 rubric 或 bucket 升级。两种模式：**完整 rubric bump**（最高风险动作，5 步强制 + 跨模型审核）和 **--bucket-only 轻量重校**（只换 bucket 边界，不动 rubric 公…
board meeting
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, in…
board meeting
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, in…
designing workflow skills
Guides the design and structuring of workflow-based Claude Code skills with multi-step phases, decision trees, subagent…
board meeting
Multi-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, in…
kiro impl
Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manual…
kiro spec batch
Create complete specs (requirements, design, tasks) for all features in roadmap.md using parallel sub-agent dispatch by…
agents sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real…
orchestrate batch refactor
Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation. U…
prompt engineering patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in producti…
latent briefing
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "…
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
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
brain
Use this skill when the task needs durable memory shared across coding-agent harnesses through the external brain CLI an
skill_search
A Minimal, Self-Evolving Autonomous Agent Framework
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-
agent-orchestration
AI DevKit · Proactively orchestrate running AI agents — scan statuses, assess progress, send next instructions, and coor