SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

SwarmClaw
CLI skill to manage SwarmClaw agent fleets: agents, tasks, chats, schedules, memory, goals, connectors, and system health via a JSON-friendly CLI.

the-claude-protocol
Bootstraps a lightweight multi-agent orchestration using Beads CLI and per-task git worktrees; includes orchestrator patterns, supervisors, and hooks to enforce

prose
Run, lint, and manage OpenProse contract-markdown workflows and ProseScript; interpret `prose` commands and execute or validate multi-step agent orchestrations.

happycapy-skills
A configurable multi-agent swarm that autonomously finds issues, writes fixes/tests/docs, opens PRs, and iteratively responds to review feedback for open-source

epistemic-protocols
Orchestrates delegated, multi-issue workflows: categorizes issues by project northstar, fans out per-category PRs, then inscribes reviewer rejections back to is

claude-plugins
Utility skill and script to locate files inside the Claude Code plugins cache, resolving latest-version paths so orchestrations can find plugin tools and SKILL.

deepswarm
Orchestrate large-scale parallel AI workers for batch and multi-turn tasks with auto-calculated worker counts, stagger, and tiered model delegation for cost-eff

citadel
Generates structured Product Requirements Documents from natural-language app descriptions, asking clarifying questions, researching references, and producing m

myclaude
Orchestrates a five-phase, multi-agent feature development workflow (Understand, Clarify, Design, Implement, Complete) using codeagent-wrapper; manages task wor

myclaude
A framework for long-running, multi-session agent tasks: progress checkpointing, failure recovery, task dependency management, and concurrency controls.

myclaude
Run and orchestrate codeagent-wrapper tasks across multiple AI backends (Codex, Claude, Gemini, OpenCode) for parallel code analysis, large refactors, and multi

code-virtuoso
Interactive guided tool that helps design focused sub-agents (specialist, role, or team-lead) with correct frontmatter, tool permissions, and system prompts.

awesome-omni-skills
Master orchestrator for test-driven development workflows: enforces red-green-refactor discipline, coordinates multi-agent TDD workflows, and preserves provenan

openclaw-master-skills
IM-first messaging and orchestration layer for OpenClaw: topic & P2P messaging, task and pipeline workflows, delegation, and a WebSocket-first autopoll runtime.

deep-recon
Orchestrate parallel multi-agent reconnaissance rounds to explore a topic deeply and produce a structured recon document (vault/Obsidian friendly).