发现 Skills

Deploy trained rl-tools policies to hardware — ESP32, Teensy, Crazyflie, PX4, Betaflight platform adapters and firmware integration.

Gymnasium vector environment API — SyncVectorEnv, AsyncVectorEnv, batched step/reset semantics, autoreset modes, and vector wrappers for parallel RL.

Salesforce metadata operations expert. Use when creating custom objects, fields, validation rules, record types, permission sets, or querying org metadata structures via the Cirra AI MCP Server.

Opinionated constraints for building better interfaces with agents. Use when building UI components, implementing animations, designing layouts, reviewing frontend accessibility, or working with Tailwind CSS, motion/react, or accessible primitives like Radix/Base UI.

Systematic debugging methodology — binary search isolation, hypothesis-driven debugging, reproducing issues, and root cause analysis. Use when debugging errors, unexpected behavior, or test failures.

MAP Protocol: omnichain interoperability layer with Bitcoin integration. Cross-chain messaging across many chains; positions itself as Bitcoin L2 connector. USE WHEN: building cross-chain apps spanning Bitcoin + others.

Expert knowledge in API design, authentication, caching, and backend best practices. Use for backend development tasks.

Expert knowledge in React patterns, component design, state management, and frontend best practices. Use for frontend development tasks.

Expert knowledge in project planning, requirements gathering, user stories, and scope management. Use when planning new projects or features.

Expert knowledge in testing methodologies, test patterns, and quality assurance. Use when writing tests or setting up testing infrastructure.

Routes requests that explicitly ask to delegate a coding or terminal task to the Codex CLI to the full-access `codexx` runner. Use when the user clearly wants Codex CLI. Not for generic requests to use an AI model or agent.

Publishing and release workflows for LeanSpec packages. Use when preparing releases, publishing to npm, bumping versions, syncing package versions, testing dev builds, or troubleshooting npm distribution.

Find an alive AI agent on the SIGNA network that matches a capability tag, send them a task via wallet-signed DM, wait for their wallet-signed reply, return it. Use this to hand off a sub-task to a specialist agent on a different platform.

Run Playwright tests at scale with cloud-hosted browsers and integrated Azure portal reporting.

Query databases, analyze spreadsheets, create visualizations, and generate insights that drive decisions.

Debug pattern errors systematically

Check SLA compliance across open tickets and flag breaches or at-risk tickets

Automate Google Search Console tasks via Rube MCP (Composio): search performance, URL inspection, sitemaps, and indexing status. Always search tools first for current schemas.

Automate PDF.co tasks via Rube MCP (Composio). Always search tools first for current schemas.

Interview the user about what they want to build, then write a complete spec to SPEC.md

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

This skill should be used when the user asks to "create a wireframe", "design a layout", "plan UI structure", "sketch component layout", "create WIREFRAME.md", "mobile-first wireframe", or mentions ASCII wireframes, layout planning, or UI structure before implementation. Provides mobile-first ASCII wireframe methodology for visualizing layouts before code.

Routes database schema inspection and SQL generation tasks to the Atlas Agent Creator for accurate database operations.

Performance testing, load testing, stress testing