github-agentic-workflows
GitHub Agentic Workflows (gh-aw) - markdown-based AI automation with 5-layer security, safe outputs, and Continuous AI patterns
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-30 00:12
Agents & models
25,265 results
riksdag-regering-mcp
Riksdag-Regering MCP server with 32 specialized tools for Swedish political data (Parliament, Government, MPs, votes, documents)
sonic
AI voice (TTS), music, lyrics, and sound-effect generation for agents. Use when the user asks to generate, synthesize, or create speech, voiceovers, songs,…
zod
zod — an installable skill for AI agents, published by hashintel/hash.
woo-review
Managed agentic PR reviews with parallel matrix execution and skeptical validation.
woostack-reflect
Use when reviewing a completed conversation for concrete, preventable instruction gaps; invoke as /woostack-reflect to report suggestions and, only after…
optimize-skill
Analyzes and optimizes an existing agent skill for conciseness, discoverability, and adherence to best practices. Use when a skill needs improvement, is too…
iblai-vibe-agent-evals
Add the agent Evals tab (run the agent against benchmarks, score responses with LLM-as-Judge reviews or manual scores, export CSV) to your Next.js app
iblai-vibe-agent-grader
Add the agent Grader tab (rubric-based grading with a grading toggle, grading setup form, criteria table, and grade results with LMS-synced overrides) to your…
iblai-vibe-agent-lti
Add the agent LTI tab (LTI 1.3 launch toggle with agent links, signing keys, tools, and platform endpoints) to your Next.js app
di-agent-flow-lifecycle
Entry point for ALL flow work in watsonx.data integration — creating, editing, running, diagnosing a failed run, or backing up/restoring a flow. Load this…
ray-consult
Enterprise knowledge base / AI implementation consulting as one line—pre-diagnosis + solution blueprint. The diagnosis section uses the GROUND six-dimension model to assess readiness, conducts requirements archaeology to see through the "real problem," matches pathology patterns, and outputs a maturity level + red/yellow/green feasibility rating + conditions for turning green; the solution section carries forward the diagnosis conclusions and answers four things about the solution: what to build (four-layer reference architecture), what to build it with (selection decision tree), and in what order to build it (Phase 0-3...
moltbook
The social network for AI agents. Post, comment, upvote, and create communities.
reviewing-skills
Review Claude Code skills based on official best practices. Use when you need to review SKILL.md files, check skill quality, validate skill structure, or suggest improvements. Triggers: "review this skill", "check skill quality", "validate SKILL.md"...
nlm-skill
Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM…
groq-migration-deep-dive
Use when you are moving a codebase off OpenAI, Anthropic, or another LLM provider onto Groq (or between Groq model generations) and want a zero-downtime,…
groq-reference-architecture
Implement Groq reference architecture with model routing, streaming pipelines, and fallbacks. Use when designing new Groq integrations, reviewing project…
groq-webhooks-events
Build event-driven architectures with Groq streaming, batch processing, and async patterns. Use when setting up real-time SSE endpoints, batch processing…
ideogram-performance-tuning
Optimize Ideogram latency and throughput through route choice, bounded media, concurrency, async handling, and immediate storage. Use when improving an…
ideogram-rate-limits
Control Ideogram concurrency with a bounded queue, deadlines, backoff, and fair tenant admission. Use when preventing 429 responses or sizing generation…
juicebox-reference-architecture
Implement Juicebox reference architecture. Trigger: "juicebox architecture", "recruiting platform design".
langchain-core-workflow-a
Build LangChain LCEL chains with prompts, parsers, and composition. Use when creating prompt templates, building RunnableSequence pipelines, parallel/branching…
review-full
Whole-codebase review by nine specialized reviewer agents against a repomix-packed snapshot, then review-deep's scripted collate, verify, and report chain over…
prompt-validate
Validar prompts dirigidos a agentes de IA (Claude Code, Cursor, Copilot, etc.) contra reglas de redacción efectiva. Calcular un porcentaje de efectividad del…