Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
让 Codex、Claude Code 等 AI Agent 成为你的跨平台电脑维修助手:64 个按需加载的 Playbook,覆盖诊断、清理、性能、网络与安全维护——C 盘爆满、电脑卡顿、流氓软件、应用迁移、数据恢复都能直接问;先取证、再计划,确认后修改。
SkillAGPL-3.0★ 406No key
top for Claude Code - live sessions, models, context, and the subagents they spawn
SkillApache-2.0★ 3Few starsNo key
Production ops discipline skill for fast AI agents: GPT-style strictness on changes, Opus speed on reads.
SkillMIT★ 1Few starsNo key
Complete Kaggle integration plugin/skill for AI coding agents — competition reports, dataset/model downloads, notebook execution, and badge collection. Works with Claude Code, Gemini CLI, Cursor, Code
SkillMIT★ 106No key
Even your AI needs a second opinion. A self-hosted MCP server on Google Cloud Run that lets Claude, ChatGPT, Cursor, and Gemini CLI peer-review their work with a different frontier model — Claude Opus
SkillApache-2.0Few starsNo key
Verify the LLM endpoint you're actually using: model authenticity, billing inflation, relay provenance, performance and silent downgrades. Single binary, no dependencies, HTML report with CI-friendly
SkillApache-2.0★ 5No key
The cloth between the tool and the model — tool-output thinning and cost observability for Claude Code and Codex. Fail-open hooks, nothing lost.
SkillMIT★ 4Few starsNo key
Token efficiency toolkit for Claude Code — budget tracking, burn rate monitoring, waste auditing, cost comparison, and auto-guard hooks. Save money on AI coding. Created by the Pitch to Prototype clas
SkillMIT★ 5No key
Refine an Agent Skill via the skill-forge judge → hitl loop, in a sandboxed Docker container. npx-installable.
SkillMITFew starsNo key
Agent Skill: build a self-service touchscreen booking kiosk — seven-step walk-up flow, on-screen keyboard, inactivity auto-reset, server-priced bookings with capacity transactions and stock locks, pay
SkillMITFew starsNo key
Orchestrate DeepSeek-API-backed Claude Code subagents from a parent Opus session. Bash+tmux on macOS/Linux, PowerShell+ConPTY on Windows.
SkillMITFew starsNo key
Open-source multi-provider AI backend with automatic 14-engine failover. 36 engines across 7 providers. OpenAI-compatible proxy. Zero-cost frontier AI. Built by Sarma Linux.
SkillMIT★ 7No key
Sub-agent tiers for Claude Code - the Lead stays the brains (plans, routes, verifies) and buys each job from the right model per call. Guard hooks hard-stop force-pushes and secrets before they run. P
SkillMIT★ 1Few starsNo key
An experimental Claude Code skill for orchestrating authorized web application penetration tests on Kali Linux
SkillMIT★ 4Few starsNo key
You are here: project state, wrap-then-/clear, a tiny per-repo brain, and hands-free runs until the PR is green. For Claude Code. Stdlib Python; macOS, Linux, Windows.
SkillMIT★ 1Few starsNo key
Automatic context monitoring for Claude Code — never get interrupted by mid-task compaction again.
SkillMIT★ 17No key
Claude Code OAuth quota in your status line — Windows (PowerShell) and Linux (or WSL2)
SkillMIT★ 6No key
SkillMIT★ 8No key
Self-improving measurement layer for Claude Code. Reads JSONL session data, computes effectiveness metrics, writes behavioral rules into CLAUDE.md. Companion to claude-daily-journal and claude-insight
SkillMIT★ 3Few starsNo key
🦾📡 Run Claude Code on free inference — local models (Apple-Silicon MLX support, CUDA support on Linux, Windows port coming soon), and free-tier cloud APIs (NVIDIA, Gemini, Groq, & more). Dispatch fr
SkillMIT★ 4Few starsNo key
A ten-agent startup team for Claude Code: orchestrator, CEO, PM, designer, backend, frontend, QA, DevOps, growth and finance subagents.
SkillMITFew starsNo key
The open source orchestration & observability your ai agent workflows (hermes, openclaw, claude-code, codex, pi, gpt, opus, fable, kimi, etc.)
SkillMIT★ 2Few starsNo key
Who stands behind it