Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
mpecan/tokf 147
-
tokf-run
Compress verbose CLI output with tokf before returning results. Activates for git, cargo, npm, docker, go, gradle, kubectl, and other supported commands.
mpecan/tokf 147
-
ss-a11y
Audit a component or page for accessibility issues and fix them
bitjaru/styleseed 152
-
ss-lint
Quick automated lint — detects common design system violations in seconds
bitjaru/styleseed 152
-
ss-page
bitjaru/styleseed 152
-
ss-update
Update StyleSeed engine in your project — analyzes what's outdated and updates safely
bitjaru/styleseed 152
-
ss-feedback
Add appropriate user feedback states (loading, success, error, empty) to a component or page
bitjaru/styleseed 152
-
ss-pattern
bitjaru/styleseed 152
-
ss-tokens
bitjaru/styleseed 152
-
ss-flow
bitjaru/styleseed 152
-
ss-component
bitjaru/styleseed 152
-
ss-setup
Interactive setup wizard — guides you step-by-step to configure the design system for your project
bitjaru/styleseed 152
-
ss-audit
Audit screens for UX issues using Nielsen's heuristics and modern mobile UX best practices
bitjaru/styleseed 152
-
ss-review
Review UI code for design system compliance, accessibility, and best practices
bitjaru/styleseed 152
-
ss-copy
bitjaru/styleseed 152
-
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts screenshots, descriptions, or URLs as input and produces production-ready React components. Checks existing Storybook components before generating, orchestrates design extraction via Stitch MCP, component matching via 21st.dev registry, adaptation to project design tokens, and self-healing verification via run-story-tests. Use when converting visual designs to code, implementing UI from mockups, or building components from screenshots.
yonatangross/orchestkit 143
-
multimodal-llm
Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling, Sora, Veo, Runway), or building multimodal AI pipelines.
yonatangross/orchestkit 143
-
langgraph
LangGraph 1.x (LTS) workflow patterns for state management, routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.
yonatangross/orchestkit 143
-
web-research-workflow
Unified decision tree for web research and competitive monitoring. Auto-selects WebFetch, Tavily, or agent-browser based on target site characteristics and available API keys. Includes competitor page tracking, snapshot diffing, and change alerting. Use when researching web content, scraping, extracting raw markdown, capturing documentation, or monitoring competitor changes.
yonatangross/orchestkit 143
-
rag-retrieval
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, agentic RAG, multimodal RAG, query decomposition, reranking, or pgvector search.
yonatangross/orchestkit 143
-
design-system-tokens
Design token management with W3C Design Token Community Group specification, three-tier token hierarchy (global/alias/component), OKLCH color spaces, Style Dictionary transformation, and dark mode theming. Use when creating design token files, implementing theme systems, managing token versioning, or building design-to-code pipelines.
yonatangross/orchestkit 143
-
multi-surface-render
Multi-surface rendering with json-render — same JSON spec produces React components, PDFs, emails, Remotion videos, OG images, and more. Covers renderer target selection, registry mapping, and platform-specific APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output for multiple platforms, creating PDF reports, email templates, demo videos, or social media images from a single component spec.
yonatangross/orchestkit 143
-
doctor
OrchestKit doctor for health diagnostics. Use when running checks on plugin health, diagnosing problems, or troubleshooting issues.
yonatangross/orchestkit 143
-
python-backend
Python backend patterns for asyncio, FastAPI, SQLAlchemy 2.0 async, and connection pooling. Use when building async Python services, FastAPI endpoints, database sessions, or connection pool tuning.
yonatangross/orchestkit 143