Browse Skills

Provides patterns for designing reliable LLM agents with tool use, including loop termination, error handling, human checkpoints, and recognizing when an agent isn't needed.

Design and dispatch subagents for context isolation, parallel work, or verification. Use when delegating tasks to a separate agent with its own context is more efficient than processing in the main context.

Provides guidance for creating reusable slash commands for AI agents, covering argument handling, workflow composition, and distinguishing commands from skills.

Use when reviewing or improving an existing agent skill. Covers triggering accuracy, content quality, redundancy with the base model, and measuring whether the skill actually changes behavior.

A guide for creating skills that trigger reliably and change an AI agent's behavior. Use when writing or debugging a skill, focusing on scoping, description writing, and progressive disclosure.

Packages skills, commands, hooks, and MCP servers into an installable plugin. Use it when creating manifests, bundling capabilities, testing clean installs, or publishing updates.

Enforce rules deterministically in AI agents using lifecycle hooks. Automate formatting, block dangerous commands, and inject context without depending on model memory.

A method for agents to persist critical state—facts, failures, conclusions—in a file that survives context compaction and session ends, with strategies for retrieval and preventing stale data.

Write short, accurate instruction files for coding agents, including commands, conventions, and hard constraints. Use it when setting up or refreshing CLAUDE.md, AGENTS.md, or similar files.

Implements a Visionary/Integrator workflow between Fable and Codex to start projects, refactor code, validate plans, and delegate builds.

Guides customization of Native Instruments Traktor Pro's interface using QML, with documentation, API references, code patterns, and AI prompt templates for creating, combining, and troubleshooting controller UI mods.

Format or validate a manuscript for Nature Portfolio journals (Nature, Nature Communications, etc.) according to author guidelines, with superscript references, word limits, and reporting summaries. Not for Nature Food.