aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
A software security skill that integrates with Project CodeGuard to help AI coding agents write secure code and prevent common vulnerabilities. Use this skill when writing, reviewing, or modifying code to ensure secure-by-default practices are followed.
Use when you have an OpenAPI spec and want to generate an SDK, or asking "how do I get started with Speakeasy"
Use when SDK methods have auto-generated names like GetApiV1Users, or wanting `sdk.users.list()` style naming
Use when combining multiple OpenAPI specs, or have microservices with separate spec files
Use when you have lint errors but can't modify the source spec, or need to add missing descriptions/tags via overlay
Use when your spec changed and you need to regenerate the SDK, or running `speakeasy run`
Use when SDK generation failed, seeing "Step Failed: Workflow", or `speakeasy run` errors
Use when asking what targets/sources are configured, or wanting to see current Speakeasy setup
Use when you need to customize SDK generation without editing the source spec, or can't modify the original OpenAPI file
Use when SDK method names are ugly, wanting to improve operation IDs, or asking "how can I improve my spec"
Use when applying an overlay file to a spec
Use when checking if an OpenAPI spec is valid, looking for errors, or running `speakeasy lint`
Configure Station CLI settings via browser UI or command line. Use `stn config --browser` for visual editor or `stn config set/show` for CLI operations.
Convert Markdown articles to WeChat Official Account formatted HTML with styled CSS and optionally upload to draft box. Supports API mode for quick conversion and AI mode for beautiful themed layouts (autumn-warm, spring-fresh, ocean-calm). Also supports assisted writing with customizable creator styles (default: Dan Koe - profound, sharp, grounded) and AI trace removal (humanizer) to make AI-generated text sound more natural. Users can add custom styles in writers/ directory. Use when user wants to write articles, convert markdown to WeChat format, remove AI writing traces, or publish to WeChat Official Account.
Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.
Use when analyzing plugin structures, MCP tools, and plugin security patterns.
Use when reviewing hooks for safety, timeouts, and correct frontmatter.