ai-agent-skills

Use this skill when creating, reviewing, or converting tool and function definitions for AI agents. Triggers include "write a tool definition", "create a function schema", "review this tool", "convert MCP tool", "improve tool description", "design agent tools", "build a LangChain tool", "add capability to my agent", or any task involving JSON Schema tool definitions, function calling schemas, MCP tool specs, or LangChain tools.

Use this skill after data analysis to design and build context loading strategies for AI agents. Triggers include "engineer the context", "build a context loader", "optimize context window", "what should the agent see", "design context strategy", "load data efficiently", "manage context budget", "compress context", or any task involving deciding what goes into an agent's context window, in what order, and how to maximize signal-to-noise ratio within the token budget.

Use this skill whenever an agent needs to create, modify, rewrite, evaluate, or review any prompt. Triggers include "write a prompt for...", "create a system prompt", "update this prompt", "improve this prompt", "rewrite the system prompt", "optimize this prompt", "change this prompt to...", "make this prompt better", "fix this prompt", "review this prompt", "is this a good prompt", "evaluate this prompt", or any task where the agent is about to write or edit a prompt string in code, config, or instructions. This skill enforces proven prompting best practices as mandatory rules for all prompt operations.

Use this skill when designing, reviewing, or debugging multi-agent systems. Triggers include "design an agent system", "how should I structure my agents", "review this agent architecture", "why is my agent looping", "add another agent", "single vs multi-agent", or any task involving agent orchestration, handoffs, tool selection, memory design, or multi-agent coordination.

The meta-skill for building AI agents end-to-end. Use this skill when someone asks "build me an agent", "create an agent that does X", "I need an agent for...", "help me build an AI agent", "set up an agent system", or any task that requires designing, implementing, and shipping a complete agent from scratch. This skill orchestrates all other skills in the correct order to deliver a working agent.

Use this skill before building any agent that works with data. Triggers include "analyze this data", "what's in this folder", "understand the problem", "understand the data first", "do EDA", "profile this dataset", "what data do I have", "what are we solving", "define the problem", or any task where you need to understand the problem and raw data before designing an agent or solution. This is always Phase 0.

Use this skill when building stateful agent workflows with LangGraph. Triggers include "use LangGraph", "build a graph workflow", "add human-in-the-loop", "create a state machine agent", "chain agents together", "build a multi-agent graph", "add checkpointing", "create agent with memory", "build a deep agent", or any task involving stateful orchestration, cycles, conditional routing, subgraphs, or complex agent pipelines beyond simple ReAct agents.

Use this skill when configuring LLM API calls through model gateways and routers. Triggers include "call an LLM", "set up OpenRouter", "configure model gateway", "add LLM to my agent", "switch models", "set up LLM factory", "create LLM client", "use LangChain with OpenRouter", or any task involving LLM API configuration, model selection, gateway routing, streaming, or provider-agnostic LLM access.

Use this skill when designing evaluation frameworks, writing test cases, or analyzing results for AI agent systems. Triggers include "evaluate this agent", "how do I test my agent", "build an eval", "measure agent quality", "create test cases", "is my agent working well", "benchmark this prompt", or any task involving agent evaluation, metrics, grading rubrics, or performance measurement.

Use this skill when adding safety rails, input validation, or output checks to AI agent systems. Triggers include "add guardrails", "make this agent safe", "validate agent output", "prevent prompt injection", "add safety checks", "rate limit the agent", "restrict agent actions", or any task involving agent safety, input sanitization, output filtering, or action gating.

Use this skill when writing new SKILL.md files, reviewing existing skills, or preparing skills for distribution. Triggers include "create a new skill", "write a SKILL.md", "review this skill", "publish this skill", "is this skill well-written", "make a skill for...", or any task involving authoring, evaluating, or distributing agent skill files.