Agent Building skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

skill-name

What this skill teaches and when to activate it. Include keywords agents use to match tasks. Max 1024 characters.

498 repo starsObserved in 2 repos
Agent Building

skill-optimize

[Skill Management] Optimize an existing agent skill

498 repo starsObserved in 2 repos
Agent Building

skill-plan

[Tooling & Meta] Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations.

498 repo starsObserved in 2 repos
Agent Building

skill-trainer-creator

Meta-skill for Epsilon Prime evolution. Analyzes existing knowledge bases and user requirements to design and train new specialized skills or update existing ones.

498 repo starsObserved in 2 repos
Agent Building

skill-validation

Validates and reviews skills against the Agent Skills specification. Checks YAML syntax, naming conventions, description quality, file structure, and best practices. Provides improvement suggestions with before/after examples and optionally applies fixes. Use when validating skills, reviewing skill quality, checking skills before commit, or when `--check-skill`, `--validate-skill`, or `--review-skill` is mentioned.

498 repo starsObserved in 2 repos
Agent Building

Skills Guide

Package expertise into discoverable, reusable capabilities that extend Claude's functionality. Use when creating new Skills, understanding how Skills work, or organizing existing capabilities.

498 repo starsObserved in 2 repos
Agent Building

smart-interview

Reset to smart interview depth (default). Use when user says '/smart-interview' or wants to reset interview mode.

498 repo starsObserved in 2 repos
Agent Building

smart-pole-instructor

Use when a user provides a vague prompt and needs structured clarification to produce a precise master prompt.

498 repo starsObserved in 2 repos
Agent Building

smolagents

Use Hugging Face Smolagents framework for code-based agentic research with tool support. Supports multiple LLM providers and web search.

498 repo starsObserved in 2 repos
Agent Building

sonnet

Override default model selection for specific subagents to use Sonnet instead of Opus. Use ONLY when the user explicitly requests to use Sonnet model for Plan, code-reviewer, code-simplifier, or Resolve Conflicts agents. Do not use this skill proactively - it requires explicit user instruction.

498 repo starsObserved in 2 repos
Agent Building