Building agents commands

zhiganov/skill-drift

Command Claude Code needs its repo

Report which skills are stale, unlinked, or have no recorded provenance (read-only).

AgenticPawan/FullStack-Pilot

Command Claude Code

Brutal pre-submission audit of a Claude Code plugin marketplace — vulnerabilities, wiring integrity, standards compliance, skill gaps.

hashgraph-online/hol-claude-skills

Command Claude Code

Start a chat conversation with an HOL agent.

JayOfemi/claude-harness-forge

Command Claude Code

Operate the model-routing seats: report where they stand, pin or free a seat, or turn routing off.

albiol2004/trio-agent-loop

Command Claude Code

Run one or more iterations of the Trio agent loop using the loop/ mailbox files. /trio = one supervised iteration; /trio auto = keep iterating in-session until SHIP, BLOCKED, or NEEDSHUMAN.

NieZhuZhu/ai-harness-doctor

Command Claude Code

Run AI Harness Doctor full pipeline.

six-ddc/skills

Command Claude Code

Fable orchestrator mode — the main model plans/dispatches/adjudicates/synthesizes; work is routed by role (deep-reasoner / fast-worker / verifier / Explore) and scaled by model tier via the Agent model override, which takes precedence over the agent's pinned model; verification intensity scales with risk.

samqin123/Claude_skill_pool

Command Claude Code

An autonomous coding command that turns a product requirements document (PRD) into a task list and runs coding sub-agents to complete it.

xcodethink/open-claude-code-skills

Command Claude Code

A test mode for a conversation that turns everyday requests into precise instructions before serious work begins.

CreateDer/agents

Command Claude Code

Please analyze the GitHub issue: $ARGUMENTS then choose related subagents to implement the issue.

cagastelum23-netizen/claude-agents-template

Command Claude Code

Orquestador principal de la arquitectura multi-agente. Descompone tareas en dominios, rutea a leads especializados, maneja fast-lane para respuestas directas, y sintetiza resultados de múltiples agentes. Se activa cuando el usuario quiere usar el sistema multi-agente completo.

21digitalai/claude-code-framework

Command Claude Code

Delegate investigation and implementation to agents, keeping main context clean.

Fused-Gaming/Fused-Gaming-Skill-MCP

Command Claude Code

Coordinate AI swarms across multiple repositories, enabling organization-wide automation and intelligent cross-project collaboration.

rhan1/crewline

Command Claude Code

Spawn an executor session in a new named Warp tab and hand it a self-contained spec.

rosudrag/ai-praxis

Command Claude Code

You are the orchestrator. Your job is to stay thin, preserve context, and delegate all heavy lifting to sub-agents. NEVER do deep file reading, code analysis, or implementation directly — always spawn agents for that.

cerb/cerb.github.io

Command Claude Code

This page describes the llm.agent automation command in Cerb, which interfaces with Large Language Models (LLMs) to maintain conversation history and manage tool use. The command automatically handles authentication, API calls, chat history, and tool invocation. To use this command, you provide a systemprompt, one or…

maike009/context-engineering-intro-CN

Command Claude Code

This command is designed to create a comprehensive Product Requirement Prompt (PRP) for building Model Context Protocol (MCP) servers referencing this codebase patterns mirroring tool setups for the users specific requirements.

RohitBind123/claude-setup

Command Claude Code needs its repo

Start the NanoClaw agent REPL — a persistent, session-aware AI assistant powered by the claude CLI.

GMartin-Data/dotfiles

Command Claude Code

Interview structurée pour produire un CLAUDE.md projet (avec détection d'instance Cruft / PRD / arborescence pour alléger les phases pré-déterminées).

Vincent-chao-lang/context-engineering-kit

Command Claude Code

A project-initialization command that creates or completes a Context Engineering directory structure for AI-assisted collaboration. The description is in Chinese and gives no further implementation details.

naoufalelh/cursor-langgraph-starter

Command Claude CodeCursor

Create a new evaluator for assessing agent performance.

vdeaugustine/Coding-Reference-Documentation

Command Claude Code

We want to work on this task: $ARGUMENTS.

exponen-agi/recursive-agentic-improvements

Command Claude Code

Build any AI agent for any domain in any supported framework. The skill researches what tools and patterns actually exist before writing a single line of code.

farfarawaylabs/agentspack

Command Claude Code

Create or update a skill by delegating to the create-cross-platform-skill skill.