Loading...
Loading...
Found 1,463 Skills
Continuous Agentation annotation handling. Use when the user says "watch mode", asks you to watch for Agentation annotations, process feedback as it arrives, or keep fixing annotation-driven changes until told to stop or a timeout is reached.
Build serverless TypeScript functions on Zavu Cloud — declare agents + tools in code with defineAgent / defineTool, deploy with `zavu deploy`, debug with `zavu agents executions`. Use this skill whenever the user wants code-driven AI agents, custom tool handlers, or event-driven business logic.
A-share Individual Stock In-depth Research System. When users mention phrases like "Analyze XXX stock", "Check XXX", "Research XXX", "Is XXX worth buying?", "How is XXX?", "XXX fundamentals", or directly provide a 6-digit A-share stock code (starting with 000/001/002/300/301/600/601/603/605/688), a three-phase process is automatically triggered: Phase 1 Data Collection (K-line/Financials/Shareholders) → Phase 2 Step 0-8 In-depth Analysis (Industrial Chain/Elasticity/Valuation/Risk-Reward Ratio/Stop-loss Signal) → Phase 3 Handwritten HTML Research Report. The generated results are data.json + report.md + report.html under output/<Stock Name>_<Code>/<YYYY-MM-DD>/. This tool is for research reference only, does not constitute securities investment consulting business, and does not constitute investment advice.
Master agentic engineering with Claude Code through best practices for agents, commands, skills, workflows, and orchestration patterns
MCP server for Xiaohongshu (Little Red Book) - search, publish posts, manage interactions, and automate content operations
Visualize and manage Claude Code AI agents as pixel art characters in a VS Code extension office interface
Install and use World2Agent (W2A) sensors to give AI agents structured, real-time perception of the real world
Feishu Real-time Event Subscription (WebSocket). Use `event list` to view supported EventKeys; `event schema` to check event payload/scope; `event consume` to start long-connection subscription, where event streams are written to stdout in NDJSON format (blocking, one process subscribes to one EventKey); `event status` to view active local consume processes; `event stop` to terminate consume processes by PID / EventKey / --all. Supports over 22 EventKeys (including IM message receive/read/recall/reaction, group member changes, contact employee changes, calendar changes, cloud disk title/collaborator changes, approval instances and tasks, VC meeting start/end). Status files: ~/.feishu-cli/events/<app_id>/bus.json + flock file lock + WebSocket auto-reconnect. This skill is applicable when users request "listen to Feishu events", "real-time message event reception", "approval callback subscription", "event stream", "WebSocket long-connection listening", "event consume", "event list / schema / status / stop", "AI Agent bot real-time response". Note: This skill only handles subscription; for event webhook business logic (pushing to Feishu messages/writing to multidimensional tables), please use with feishu-cli-msg / feishu-cli-bitable.
Propose and execute rubric or bucket upgrades. Two modes: **Full rubric bump** (highest-risk action, mandatory 5-step process + cross-model audit) and **--bucket-only lightweight recalibration** (only update bucket boundaries, no changes to rubric formulas). **Phase 2 mandates using cheat-score-blind sub-agent to re-score the calibration pool** — self-scored fallback is not accepted. Trigger phrases: "upgrade rubric"/"bump rubric"/"update formula"/"I want to add a dimension"/"adjust weights"/"recalibrate bucket"/"recalibrate bucket".
Multi-perspective deliberation on a question. Use when the user says "get perspectives on", "multiple viewpoints", "council on this", "devil's advocate", "stress test this idea", "red team this", "poke holes in", "second opinion on", "what am I missing", or wants multi-perspective analysis of a decision, design, or strategy.
ELFA AI — real-time crypto social intelligence and automated condition-engine skills for AI agents. Track trending tokens, surface narratives, search mentions, run market analysis, and build automated trigger-based workflows.
Use when a locally-served model misbehaves in an agent harness — wrong/empty tool calls, truncated output, context overflow, or slow generation. Diagnoses whether the fault is the model tier, the serving config, or the harness wiring, using the agentic repo's probe and model matrix.