Building agents

Health-Yang/MineEcho

Skill Claude CodeCodex

A skill-system guide for finding and describing available skills. It is used when someone asks what the agent can do or is unsure which skill fits a task.

RLabs-Inc/gemini-mcp

MCP server Claude CodeCodexCursor +2

Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI. Runs locally from the @rlabs-inc/gemini-mcp npm package. Needs 2 environment variables to run.

agenticmail/agenticmail

Plugin Claude Code

Bundles 3 skills · 64 tokens together

Give every Claude Code agent its own real email address and phone number. Self-hosted, runs entirely on the user's machine. Coordinate work across multiple agents using ordinary email threads.

HezaoHezao/poirot

Skill Claude Code

Author SKILL.md: frontmatter, structure, writing principles.

Birfy/agentdescent

Plugin Claude Code

Bundles 1 skill, 1 command, 1 hook, 1 MCP server · 133 tokens together

Evolve skills, agents, prompts, code and plugins against examples with a parallel, merge-based optimiser.

Evol-ai/SkillCompass

Plugin Claude Code

Bundles 1 skill, 14 commands, 3 hooks · 52 tokens together

Local-only skill quality and security evaluator for Claude Code/OpenClaw. Scores six dimensions, runs local validators, and stores reports and snapshots under .skill-compass/.

Alignbase/sunpeak

Skill Claude CodeCodex

Use when working with sunpeak, or when the user asks to "build an MCP App", "build a ChatGPT App", "add a UI to an MCP tool", "create an interactive resource for Claude Connector or ChatGPT", "build a React UI for an MCP server", or needs guidance on MCP App resources, tool-to-UI data flow, simulation files, host…

dean9703111/ai-agent-skill-for-video-workflow

Skill Claude CodeCodex

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Hmbown/aleph

Plugin Claude Code

Bundles 1 skill, 1 agent, 1 hook, 1 MCP server · 49 tokens together

Recursive Language Model MCP server for large local data. Keep files, repos, logs, and documents in external memory; search, peek, compute, and recurse without dumping whole contexts into the prompt.

rllm-org/hive

Plugin Claude Code

Bundles 3 skills, 3 commands · 271 tokens together

Hive agent skills for collaborative evolution. /hive-setup installs hive-evolve, registers your agent, and clones a task. /hive runs the autonomous experiment loop. /hive-create-task guides you through designing and publishing a new task.

hueyexe/opencode-ensemble

Skill Claude CodeCodex

Use when coordinating multiple coding agents, delegating independent software work, managing OpenCode Ensemble teams, choosing teammate roles or models, reviewing teammate output, or deciding whether parallel execution is appropriate.

jfarcand/mirroir-mcp

MCP server Claude CodeCodexCursor +2

MCP server "mirroir" as configured in jfarcand/mirroir-mcp. Launched with ${workspaceFolder}/.build/release/mirroir-mcp --yolo.

ethanhq/cc-fleet

Plugin Claude Code

Bundles 3 skills, 1 hook · 355 tokens together

Run any model with an Anthropic- or OpenAI-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) — even your Codex subscription — as real Claude Code workflows, agent-team teammates, or one-shot subagents, driven exactly like native ones. Your main session's own auth is untouched (OAuth subscription or API key…

run-llama/flow-maker

Cursor rule Cursor

This document explains the core concepts of the @llamaindex/workflow-core library for TypeScript, which is used by typescript-compiler.ts to generate executable agent scripts. The library uses a functional, event-driven paradigm.

damianvtran/local-operator

Agent Claude Code

Use Local Operator agent profiles, roles, and subagents: discover, create, select, interact, delegate, and choose the correct collaboration mode.

AI45Lab/SAfactory

Skill Claude CodeCodex

Use this skill when helping users onboard a benchmark or environment into SAfactory, run SAfactory Docker-mode evaluation, or start SAfactory GRPO/RL training. It guides Codex to inspect the SAfactory repository, read the relevant docs, follow the established Geo3K baseline and myenv placeholder workflows, configure…

gugug168/cute-claude-hooks

Skill Claude Code

A Chinese-language customization guide and hook package for Claude Code. Hooks are scripts that run around tool actions, such as before or after a command, and can change prompts and interface text.

cafeTechne/antigravity-link-extension

MCP server Claude CodeCodexCursor +2

MCP server and OpenAPI-backed mobile companion for controlling Antigravity IDE sessions. Runs locally from the antigravity-link-extension npm package. Needs 2 environment variables to run.

modem-dev/baudbot

Skill Claude CodeCodex

Control agent role — monitors email inbox and delegates tasks to worker sessions. Activate with /skill control-agent.

FerroxLabs/ijfw

Cursor rule Cursor

Active every response. No revert. No filler drift. Off: "ijfw off" / "normal mode".

spire-studio/cloakbot

Skill Claude CodeCodex

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

cathrynlavery/codex-skill

Plugin Claude Code

Bundles 1 skill, 1 hook · 67 tokens together

Give Claude Code a second opinion using OpenAI Codex - automatic plan review via hooks.

ferdinandobons/AWSBedrockAgentCoreSkill

Plugin Claude Code

Bundles 1 skill · 370 tokens together

Authoritative, source-cited playbook that lets a coding agent autonomously design, configure, deploy, and troubleshoot production-grade AI agents on AWS - Strands Agents SDK, Amazon Bedrock (Converse, Guardrails, Knowledge Bases), and Bedrock AgentCore (Runtime, Memory, Gateway, Identity, Browser/Code Interpreter) …

y49/tlive

Plugin Claude Code

Bundles 1 skill, 3 commands, 12 hooks · 111 tokens together

tlive hooks + skill + commands — IM approvals, session monitoring, web terminal.