Loading...
Loading...
Found 2,319 Skills
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.
Generates a new image that imitates the style of a reference image while updating content based on user intent. Uses a three-stage pipeline: image annotation (long caption), caption rewriting, and image generation. Use when user asks to "imitate style", "保持这个风格重画", "按这张图风格生成", or "style transfer with new content".
MCP server for real-time Three.js scene inspection, material editing, shader debugging, and performance monitoring from AI agents
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".
Connect Jira, Confluence, and Compass to AI agents and IDEs using Atlassian's remote MCP server with OAuth 2.1 or API token authentication.
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.
Universal CLI client for Model Context Protocol (MCP) with persistent sessions, OAuth, tasks, and JSON output for shell scripting
Use when the user asks "what predefined metrics are available", "which built-in metrics should I use", "what does CSAT measure", "how does hallucination detection work", "what's the difference between Interruption Score and AI Interrupting User", "which metrics are free", "which metrics need audio", "configure silence threshold", "set up sentiment metric", or any question about Cekura's out-of-the-box metrics. Covers the full catalog of predefined metrics — what each does, costs, constraints, configuration options, and when to use each one.
Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness — currently Code Mode, which collapses many tool calls into one sandboxed Python execution. Use when the user mentions pydantic-ai-harness, CodeMode, Monty, code mode, or tool sandboxing, when they want an agent to run agent-written Python, or when a Pydantic AI agent would benefit from orchestrating multiple tool calls in a single sandboxed script.
Connect to the Zhihe AI Legal Large Model Platform for legal research. This skill should be used when users need to conduct legal issue research, look up laws and regulations, retrieve similar cases, or obtain legal research reports. A Zhihe AI platform membership account is required.
Two-layer autonomous conductor — design loop produces decision packets, dispatch loop routes to bounded issues with dedupe/cooldown/archive controls. Replaces v1's single-agent persistence with a durable control loop that stops only at real blockers.
Replace with a trigger-style description of when this skill should activate. Be specific — this is what the agent uses to decide whether to load the skill. Example: "Sui TypeScript SDK integration. Use when writing, reviewing, or debugging TypeScript code that interacts with Sui RPCs, transactions, or on-chain state."