Total 50,527 skills, AI & Machine Learning has 8482 skills
Showing 12 of 8482 skills
Audit a non-technical repo's folder structure for agent-navigability and propose a refactor plan. TRIGGER when user says "review structure", "audit folders", "audit my repo", "check organization", "is my repo agent-friendly", "clean up structure", or runs "/review-structure".
Build command-line interfaces for AI agents. Covers arguments, flags, subcommands, help text, output formats, error messages, exit codes, config/env precedence, and safe/dry-run behavior. Use when building a new CLI or refactoring an existing one for agent use.
Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Expert skill for using wanman, the open-source local agent matrix runtime that coordinates multiple Claude Code or Codex agents on your machine.
Generate and evaluate solution options
Orchestrate parallel implementation with coder/overseer pairs. Coders implement decomposed tasks using evanflow-tdd; overseers review each coder's output for bugs, gaps, errors, AND cohesion violations against a shared contract. A final integration overseer checks cross-coder cohesion. Use for plans with 3+ truly independent tasks that share an interface contract.
Configure human-in-the-loop gating for AI agent review actions in Claude Code. Use when setting up a project where an agent may post PR reviews, comments, merges, or edit CI configuration, and you want a cryptographically auditable approval trail with Cedar-enforced gates.
Unified review skill — auto-detects plan or code, assembles the right panel, runs a bounded review-fix loop with severity gating. Use when a plan or implementation needs review.
Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.
MCP client: connect servers, register tools (stdio/HTTP).