Loading...
Loading...
Found 2,319 Skills
Review local code changes organized into logical chapters with Stage CLI, a code review tool that works with any AI agent
Use when the user asks you to start, join, or continue a conversation with other agents via chatter, agent-chat, or talking to other agents about X.
This skill should be used when the user asks to "create a skill" or "make a command". Make sure to use this skill whenever the user mentions skill creation, command authoring, slash commands, or building Claude extensions — even if they don't explicitly say "create-skill". Not for repairing or auditing existing skills — use repair-skill.
This skill should be used when the user asks to "research a topic", "run-research", "last30", "what's happening with X", "what are people saying about X", "find the best X", "X prompts", "latest on X", "X news", "what are people recommending for X", "research X for me", or wants to know what's trending, discussed, or debated about any subject in recent weeks.
Install context files from registry. Use when user runs /install-context, says "install context", "setup context", or when context is missing and the user needs to get started.
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
Use this skill when the agent needs to interact with CLAWLOGIC prediction markets. This includes: registering as an agent on-chain, creating new prediction markets, analyzing market questions to form opinions, buying YES/NO positions, asserting market outcomes via UMA Optimistic Oracle, disputing incorrect assertions from other agents, settling resolved markets to claim winnings, and posting bet narratives ("what I bet and why") to the frontend feed. Triggers: - "create a market about..." - "what do you think about [market question]?" - "buy YES/NO on market..." - "assert the outcome of market..." - "dispute the assertion on market..." - "check my positions" - "settle market..." - Any discussion about prediction markets, trading, or information markets
Execute Python code in isolated rootless containers with MCP server proxying to reduce context bloat from 30K to 200 tokens
Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.
MCP client: connect servers, register tools (stdio/HTTP).
handoff the session, compact the conversation into a document a fresh agent can resume from, or restore context from a saved handoff. Triggers: /handoff, save session context, hand off to a new agent, resume from a handoff file. Flags: --resume <path>, --path <path>, and a positional focus argument.
Take your AI agent to the next level with full LangWatch integration. Adds tracing, prompt versioning, evaluation experiments, and simulation tests in one go. Use when the user wants comprehensive observability, testing, and prompt management for their agent.