self-improve
4297nirarad/playwright-ai-qa-agent
Cursor rule Cursor
Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices.
not rated 5 5mo ago A 2,736 tokens
original MIT
skill-creator
4298Skill Claude CodeCodex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
not rated 5 4mo ago A 45 tokens
self_improve
4299Cursor rule Cursor
description: Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices. globs: / alwaysApply: true.
not rated 5 1y ago A 530 tokens
copy · 100% MIT
dream-team
4300Plugin Claude Code
Bundles 13 skills, 5 commands, 9 agents, 5 hooks · 691 tokens together
Effective Claude workflows - /solo for 90% of tasks, /team for complex features. Based on official Anthropic patterns.
not rated 5 9mo ago A
tokens not measured
skill-sync
4301Skill Codex
One source of truth for local AI agent skills: audit Codex, Claude, Hermes, OpenClaw, OpenCode, workspace skills, and shared roots; score hygiene, diff conflicting installs, classify drift as pristine/dirty/local-only against recorded baselines, deduplicate into one canonical source with symlinks, and migrate the same…
not rated 5 2mo ago A 177 tokens
original MIT
chainlink-for-agents
4302smartcontractkit/chainlink-for-agents
Skill Claude CodeCodex
Register an agent, create chain wallets, discover available workflows, sign Chainlink for Agents requests, handle x402 USDC payments, and sign EIP-712 operation data locally. Use for the Chainlink for Agents /v1 API, agent wallets, workflow execution, EIP-712 signing, and x402 payments. Do NOT use for generic REST…
not rated 5 3mo ago A 84 tokens
original MIT
hulk
4303Skill Claude CodeCodex
Autonomously implement a planned feature end-to-end as a senior engineer, drive it to a clean state through an iterative QA + Design/Product + Engineer review loop, prove it actually runs with /verify, take it to a green reviewed PR with /thor, and finish with a standup-style session log. Use this when the user hands…
not rated 5 1mo ago A 0 tokens
harness-engineering
4304Skill Claude CodeCodex
Pipeline completo de desenvolvimento de software com IA — PRD → Arquitetura → Tasks → Código → Review → Testes → Docs → CI/CD → Iteração. Baseado nas práticas de Harness Engineering da Anthropic, OpenAI e Thoughtworks/Martin Fowler: guias (feedforward) + sensores (feedback) que se auto-corrigem antes de chegar ao…
not rated 5 4mo ago A 213 tokens
original MIT
find-skills
4305Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
not rated 5 27d ago A 67 tokens
original MIT
autoskillit
4306Plugin Claude Code
Bundles 121 skills, 1 MCP server · 5,116 tokens together
Orchestrated skill-driven workflows using Claude Code headless sessions.
not rated 5 today A
tokens not measured
original MIT
handoff
4307TheSylvester/agentic-coding-tools
Skill Claude CodeCodex
Synthesize self-contained implementation prompt(s) that hand a task to a fresh coding agent with an empty context window, decomposing into a phased chain or parallel set when the task is too large for one. Use when the user says "write a handoff prompt", "generate a prompt", "distill this for a fresh agent", or asks…
not rated 5 1mo ago A 78 tokens
original MIT
pi-dispatch
4308Skill Claude CodeCodex
Orchestrate pi coding agents with DAG-aware dependency resolution, git worktree isolation, automatic retry, and structured JSON output. Use this skill when: - spawning pi agents for any subtask - tasks have dependency ordering (A must finish before B starts) - parallel agents need isolated git workspaces - you need…
not rated 5 2mo ago A 73 tokens
original MIT
curate-skills
4309JustinGastby/Hermes-Mind-Skill
Skill Claude CodeCodex
Review the project's accumulated Skills and propose archiving long-unused ones or merging near-duplicate ones into a single broader skill. Use when nudged by the Stop hook's curator sweep (mentions skills that haven't been used in a while), when the user asks to clean up / compress / prune skills, or when creating a…
not rated 5 1mo ago A 79 tokens
original MIT
fortytwo-mcp
4310Fortytwo-Network/fortytwo-mcp-skills
Plugin Claude Code
Bundles 1 skill · 149 tokens together
Fortytwo Prime: collective multi-agent inference for high-stakes questions. ALWAYS use when the user says "Ask Fortytwo", "Ask Prime", "Ask Fortytwo Prime", or calls askfortytwoprime. When the user doubts your answer ("try again", "that's wrong", "are you sure?"), wants more depth ("go deeper", "elaborate", "full pic.
not rated 5 5mo ago A
tokens not measured
original MIT
meeting
4311Pattyboi101/oats-autonomous-agents
Skill Claude CodeCodex
Facilitate a structured CONVERSATIONAL meeting between department agents via claude-peers — named phases (Diverge, Clarify, Challenge, Build, Stress Test, Converge, Decide) with state machine navigation. Agents push back on each other and build on each other's ideas. Minimum path: Diverge → Challenge → Build → Stress…
not rated 5
+1 4mo ago A 101 tokens
original MIT
rules-agents
4312Skill Claude CodeCodex
Use when installing rulesagents into a Bazel repo, verifying the setup, discovering skills from registries or custom repos, adding local skills, and configuring agent profiles and runners.
not rated 5 4mo ago A 39 tokens
original Apache-2.0
skill-evolution
4313Skill Codex
A proposal process for improving a reusable coding skill or the rules that decide when an agent uses it. It uses repeated failures, user feedback, and test results to suggest bounded improvements without applying them.
not rated 5 24d ago A 51 tokens
original MIT
Skill Claude CodeCodex
Build, configure, and extend HermesPet — a native macOS AI companion living in the Dynamic Island with multi-engine support, desktop pets, and advanced system integration.
not rated 5 1mo ago A 41 tokens
dungnotnull/pro-gamer-eye-hand-training-agent-skill
Skill Claude CodeCodex
The pro-gamer-eye-hand-training system uses a centralized skill registry pattern for managing skill lifecycle, discovery, execution, and validation. This document defines how skills are registered, resolved, executed, and validated using JSON schemas for type safety.
not rated 5 1mo ago A 0 tokens
original MIT
4ier/openclaw-feishu-group-chat
Skill Claude CodeCodex
Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format messages for the platform. Use when connecting OpenClaw to Feishu and you want your agent to be a competent group participant, not just a responder.
not rated 5 6mo ago A 75 tokens
dungnotnull/fighting-game-combo-optimizer-agent-skill
Skill Claude CodeCodex
The fighting-game-combo-optimizer uses a dynamic skill registry that provides.
not rated 5 1mo ago A 0 tokens
original MIT
codemode-x
4318Plugin Claude Code
Compress any API, database, or docs into 2 MCP tools (cmxsearch + cmxexecute). One config file, universal SDK, sandboxed TypeScript execution.
not rated 5 2mo ago A
tokens not measured
herderp
4319Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 268 tokens together
MCP tools for the herdr CLI, plus session necromancy: find, read, and anchor-extract a previous Claude Code agent session from a herdr space.
not rated 5 1mo ago A
tokens not measured
shipcraft
4320Plugin Claude Code
Bundles 3 commands, 10 agents · 258 tokens together
Ship fast, craft well. Agents spécialisés et workflows automatisés pour Claude Code.
not rated 5 4mo ago A
tokens not measured
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: