Loading...
Loading...
Found 128 Skills
Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.
Build AI agents and agentic workflows. Use when designing/building/debugging agentic systems: choosing workflows vs agents, implementing prompt patterns (chaining/routing/parallelization/orchestrator-workers/evaluator-optimizer), building autonomous agents with tools, designing ACI/tool specs, or troubleshooting/optimizing implementations. **PROACTIVE ACTIVATION**: Auto-invoke when building agentic applications, designing workflows vs agents, or implementing agent patterns. **DETECTION**: Check for agent code (MCP servers, tool defs, .mcp.json configs), or user mentions of "agent", "workflow", "agentic", "autonomous". **USE CASES**: Designing agentic systems, choosing workflows vs agents, implementing prompt patterns, building agents with tools, designing ACI/tool specs, troubleshooting/optimizing agents.
Example skill template. Replace this description with keywords and triggers for your actual skill. This description determines when the skill auto-loads based on conversation context.
Apply production-ready LangChain SDK patterns for chains, agents, and memory. Use when implementing LangChain integrations, refactoring code, or establishing team coding standards for LangChain applications. Trigger with phrases like "langchain SDK patterns", "langchain best practices", "langchain code patterns", "idiomatic langchain", "langchain architecture".
Design and scaffold the code execution pattern for MCP-based agent systems. Use when building agents that interact with many MCP tools, when intermediate data is too large for model context, when you need loops/conditionals across tool calls, or when PII must stay out of the model context. Based on Anthropic's engineering guidance.
Create and improve OpenAkita skills. It is used when you need to: (1) create new skills for repetitive tasks, (2) improve existing skills, (3) encapsulate temporary scripts into reusable skills. Skills are the core mechanism of OpenAkita's self-evolution.
LangGraph framework for building stateful, multi-agent AI applications with cyclical workflows, human-in-the-loop patterns, and persistent checkpointing.
Detecting whether agent iterations are converging toward a stable solution or hitting a ceiling. Covers convergence signals, ceiling detection, non-convergence diagnosis, test pass rate as a convergence metric, and forward progress tracking for large projects. Trigger phrases: "convergence", "is the agent converging", "ceiling detection", "when to stop iterating", "diminishing returns"
This skill should be used when the user asks to "create a skill" or "make a command". Make sure to use this skill whenever the user mentions skill creation, command authoring, slash commands, or building Claude extensions — even if they don't explicitly say "create-skill". Not for repairing or auditing existing skills — use repair-skill.
Set up automated agent-driven development with Ralph. Run AI agents in a loop to implement features from user stories, verify acceptance criteria, and log progress for the next agent.
Comprehensive guide for building full-stack applications with Convex and TanStack Start. This skill should be used when working on projects that use Convex as the backend database with TanStack Start (React meta-framework). Covers schema design, queries, mutations, actions, authentication with Better Auth, routing, data fetching patterns, SSR, file storage, scheduling, AI agents, and frontend patterns. Use this when implementing features, debugging issues, or needing guidance on Convex + TanStack Start best practices.
Epistemic verification framework for AI-generated assertions. Requires evidence before acting on LLM claims about code behavior, system state, API responses, or factual statements. Use when an AI agent makes claims that will drive decisions, before acting on research results, or when an agent asserts something is true without showing evidence.