action-prefix-system
3025Skill Claude CodeCodex
Explain and apply the UPPERCASE action-prefix directive system (BACKGROUND, ISSUE, BUG, TASK, REMINDER, FEATURE).
not rated 2 3d ago A 25 tokens
original MIT
skill-builder
3026austinpeechatt/claude-code-skills
Skill Claude CodeCodex
Use when creating new skills, optimizing existing skills, or auditing skill quality. Guides skill development following Claude Code official best practices.
not rated 2 6mo ago A 28 tokens
generate-agents-md
3027Skill Claude CodeCodex
Create or improve a project-specific AGENTS.md file for software repositories. Use when a user wants durable setup, testing, architecture, safety, and workflow instructions for AI coding agents.
not rated 2 4mo ago A 41 tokens
original MIT
data-agent-template
3028Skill Claude CodeCodex
Build and deploy methodology-aware data agents on Trino/Iceberg with structured reasoning, MLflow tracing, and 7-dimension evaluation — guided by settled decisions and requirements recorded in the RAC corpus.
not rated 2 2mo ago A 0 tokens
Skill Claude CodeCodex
Derive fine-grained, reusable skill-construction lessons from branch/commit/test structure and convert them into actionable skill design artifacts.
not rated 2 2d ago A 32 tokens
AGPL-3.0
agent-factory
3030Skill Claude CodeCodex
Manage Agent Factory (af) sessions, tabs, scheduled tasks, and the daemon via the af CLI.
not rated 2
changed 5d ago C 24 tokens
AGPL-3.0
skill-writer
3031Skill Claude Code
MUST be activated when creating, editing, or maintaining agent skills (SKILL.md, skill structure, triggers, or workflows). Use whenever writing or revising a skill package, skill description, or activation behavior.
not rated 2 18d ago A 47 tokens
original MIT
karpathy-guidelines
3032Skill Claude CodeCodex
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls. Apply when doing non-trivial implementation work.
not rated 2 3mo ago A 39 tokens
ai-agent-workshop
3033Skill Claude CodeCodex
Use this skill to guide a workshop attendee through building their first AI employee inside Claude from scratch. Trigger this skill whenever someone says "start the workshop", "help me build my agent", "I'm in the workshop", "set up my AI employee", "build my Claude Project", or uploads this skill file and asks what…
not rated 2 3mo ago A 130 tokens
hermes
3034Skill Claude CodeCodex needs its repo
Working knowledge of the Hermes agent platform (NousResearch hermes-agent fork at enduru). Use when editing or debugging hermes-agent code, authoring hermes plugins (plugin.yaml + init.py), navigating the v15/v16 upstream-merge regression history, or planning operator/customer fleet rollouts. Auto-invokes on mentions…
not rated 2 3mo ago A 131 tokens
original MIT
hammerin-claude
3035masimoneext-sketch/hammerin-claude
Skill Claude CodeCodex
Orchestratore multi-agente per sviluppo software — metodo Capocantiere. Opus progetta, comanda e ispeziona; Sonnet esegue blocchi chiusi con contratto firmato. Usa questa skill quando l'utente chiede di sviluppare una nuova funzionalità, una pagina con API, una feature full-stack, un refactor multi-file, un audit di…
not rated 2 5mo ago A 195 tokens
scaffold-agent
3036Skill Cursor needs its repo
Maintains and extends the scaffold-agent npm CLI that generates onchain AI agent monorepos (Foundry/Hardhat + Next.js/Vite/Python), including -y flags, agent.json --from-config, --dump-config, --swarm, Shroud/1claw, and embedded Next/Vite templates. Use when editing this repository, changing CLI behavior or templates…
not rated 2
changed 13d ago A 101 tokens
original MIT
hermes
3037Skill Claude CodeCodex
This skill should be used when self-hosting, installing, configuring, operating, updating, troubleshooting, or learning to use NousResearch Hermes Agent, including CLI usage, gateway and Slack setup, plugins, tools, skills, profiles, memory, MCP, cron, Kanban, delegatetask subagents, dashboards, and tmux-managed…
not rated 2 4mo ago A 72 tokens
original MIT
develop-skills
3038Skill Claude CodeCodex
A Chinese-language guide to developing agent skills, including setup, the difference between skills and tools, pricing case studies, integration, and agent coordination.
not rated 2 6mo ago A 56 tokens
Skill Claude CodeCodex
Autopilot issue resolution loop: scan, dispatch implementer and reviewer sub-agents per ready-for-agent issue, then run global meta-review. Use when processing autopilot issues from any source.
not rated 2 yesterday A 46 tokens
ralph-loop
3040autogame-17/ralph-loop-codex-skill
Skill Claude CodeCodex
Run a real Codex Desktop Ralph Loop using heartbeat thread wakeups, per-loop persistent state, multi-session isolation, max-iteration safety, verification, and honest completion promises. Use when the user asks for Ralph Loop, Ralph Wiggum technique, loop until done, autonomous iterative implementation, or asks Codex…
not rated 2 3mo ago A 77 tokens
whatsapp-agent-setup
3041Skill Claude CodeCodex
Connect a WhatsApp number to an OpenClaw agent without the Meta API, using whatsapp-web.js (Puppeteer). Use this skill when asked to set up WhatsApp for an agent, connect a dedicated number to OpenClaw, build a WhatsApp listener/responder, integrate WhatsApp without Business API, create a bot that receives and sends…
not rated 2 4mo ago D 181 tokens
book-to-skills
3042hoangngochuong24947-gif/skillify-textbooks
Skill Codex
A method for turning a book into reusable instructions, documents, or a thinking system for coding agents.
not rated 2 6mo ago A 67 tokens
skill-dev-driver
3043Skill Claude CodeCodex
A project-development skill that remembers goals, past work and solutions, and can call other specialist skills.
not rated 2 6mo ago A 78 tokens
Skill Claude CodeCodex
SafeClaw validates every tool call, message, and agent action against OWL ontologies and SHACL constraints before execution. It acts as a governance gate between your AI agent and the tools it uses.
not rated 2 2mo ago A 0 tokens
harness-engineering
304501clauding/harness-engineering
Skill Codex
Design, debug, and harden the harness around coding agents in medium or large repositories. Use when Codex, Claude Code, Cursor, Windsurf, Copilot, or custom agents need AGENTS.md or CLAUDE.md cleanup, repo knowledge routing, skills, hooks, review and eval loops, migration governance, subagent boundaries, worktrees…
not rated 2 6mo ago A 120 tokens
skill-graph-builder
3046sungatetop/skill-graph-builder
Skill Claude CodeCodex
A tool for turning technical specification documents into small, independent skills and mapping how those skills connect. A skill is a reusable package of instructions for completing a specific task.
not rated 2 5mo ago A 106 tokens
skill-market-upload
3047LSTM-Kirigaya/skill-market-cli
Skill Claude CodeCodex
Instructions for using skill-market-cli to upload a local coding-agent skill to Skill Market.
not rated 2 3mo ago A 3 tokens
adkcourse
3048gca-americas/virtual-ta-skills
Skill Claude CodeCodex
A comprehensive virtual TA skill for the "ADK Agentic Pattern with Memory & MCP" codelab. Covers 7 sessions building progressively complex ADK agent architectures — from single agents through Sequential, Parallel, Loop, Custom (BaseAgent), Routing, Agent-as-Tool, Long-Term Memory (DatabaseSessionService), and MCP…
not rated 2 1mo ago A 73 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: