langgraph-patterns
Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the-loop, and advanced control flow
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Agents & models
25,344 results
mcp-2025-patterns
Current best practices for Model Context Protocol server design, implementation, and integration. Updated patterns for 2025 MCP ecosystem including…
mcp-architecture
Design and implement Model Context Protocol servers for standardized AI-to-data integration with resources, tools, prompts, and security best practices
openai-agentkit
Build production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestration, handoffs, and routines
rules
Rule files the always-on AGENTS.md index points to. Not user-invoked. Other skills link here so the rules install with npx skills.
kata-audit-milestone
Verify milestone achievement against its definition of done, checking requirements coverage, cross-phase integration, and end-to-end flows. Triggers include…
session-handoff
Use only when the user asks to write a handoff, continuation prompt, or session transfer file so another agent, model, or harness can continue the current…
flow-next
Manage .flow/ tasks and specs. Triggers: 'show me my tasks', 'list specs', 'what tasks are there', 'add a task', 'create task', 'what's ready', 'task status',…
memory
Records and appends every user-agent customer support interaction to the memory.md log in the workspace.
copilot-agent-patterns
GitHub Copilot custom agent design patterns, best practices, collaboration workflows, and agent orchestration
playwright-mcp
Live browser interaction via Playwright MCP — navigate pages, click buttons, fill forms, take screenshots.
software-engineering
Orchestrate a multi-agent software project (web app/page, tool, game, library, etc.) with a team of specialized subagents — design, bpm, art, audio, qa — in…
workflow-retro
Daily retro of every agent session on the PC and the MacBook: fix my skills, propose the rest.
publish-to-marketplaces
Publish and update agent skills on agentskill.sh and skills.sh marketplaces. Covers SKILL.md preparation, submission, verification, and ongoing sync. Use when…
audit-oe
Audit OpenEvidence MCP citations with transitive citation detection, cross-citation contradiction scanning, provenance analysis, and multi-dimensional accuracy…
learn
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's…
iblai-vibe-agent-billing
Add the agent Billing tab (LLM spend limits for the agent and per user, with usage bars, block/alert enforcement, and near-limit alert thresholds) to your…
iblai-vibe-agent-voice
Add the agent Voice tab (pick the agent's voice and configure voice calls) to your Next.js app
iblai-vibe-history
Add the user profile History surface (review and export conversations with AI agents — Conversations tab with filters and a two-column transcript preview, an…
iblai-vibe-memory
Add the organization-wide Memory settings surface (manage every user's global memories and every agent's memories from one place — Global and Agent tabs with…
agents
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous…
migrate-skill-to-agent
Skill directory `.claude/skills/{name}` from `.agents/skills/{name}` Move to, and `.claude/skills/{name}` と `.codex/skills/{name}` A migration skill that creates symbolic links from both. The skill entity…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's…
exa-architecture-variants
Choose among direct Search, staged Contents, Answer, Agent, Monitors, Websets, and Batch using explicit latency, verification, volume, and lifecycle criteria.…