MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
Create Git branches, commits, pushes, and GitHub pull requests for Next.js. Use when the user asks to create a branch, commit current changes, open a PR or draft PR, publish a pull request, or recover
OfficialSkillMIT★ 143k in collectionNo key
Monorepo for SAP MCP servers (API Hub, Road Map Explorer, SAP Notes) and their shared SAP authentication module — npm workspaces.
SkillApache-2.0★ 26No key
Self-hostable, MCP-native testing platform. Manual test management, deterministic runs, optional AI. Your stack, your LLM, your data.
SkillApache-2.0★ 37No key
Your AI coding agent writes code fast — we make sure the web product actually works. Paste a URL, the agent clicks through signup/checkout/dashboards like a real user, reports failures with screenshot
Node.jsMIT★ 16No key
Local-first, open-source alternative to Anthropic's Claude Design. MIT-licensed, BYO agent CLI — Claude Code, Kimi, Codex, or any SDK-compatible model. Composable skills · three edit paths · designs a
SkillMIT★ 11No key
Frontend design skill for Claude Code, Codex, and Gemini CLI. Eight aesthetic anchors, each locking palette, typography, and texture to specific CSS tokens. Pick one per brief.
SkillMIT★ 142No key
Orchestrates the iterative PR review loop: fetch → triage → implement → resolve threads → re-fetch until clear. Use when a PR has active review.
OfficialSubagentApache-2.0★ 415 in collectionNo key
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management. Enables LLMs to fetch PR details, analyse diffs, manage issues, and handle releases through a standard
Hosted by authorApache-2.0★ 6No key
Stealth browser for AI agents that runs on small local models. Read any site as Markdown, log in without an LLM, MCP server included.
PythonMIT★ 7No key
Code review for your own machines and your own agents. Reviews live where the code does — reached over SSH, WSL or your own tailnet. Desktop app or just a browser tab. No server, no account.
SkillGPL-3.0★ 18No key
Edit a running web app from inside the page: pick elements, screenshot, preview changes, approve one, and it lands in your source.
SkillMIT★ 9No key
Fetch objective metrics for OSS repositories. Built for AI agents.
SkillMIT★ 3Few starsNo key
Gamified AI SEO audit app that turns website issues into 16-bit dungeon battles for local Codex, Claude, and Gemini CLI workflows.
SkillMIT★ 4Few starsNo key
Agent skill that records browser demos and adds them to pull requests with GitHub CLI --attach
SkillMIT★ 3Few starsNo key
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwri
OfficialSkillMIT★ 143k in collectionNo key
Full STRIDE-A threat model analysis and incremental update skill for repositories and systems. Supports two modes: (1) Single analysis — full STRIDE-A threat model of a repository, producing architect
OfficialSkillMIT★ 40k in collectionNo key
Open-source, local-first 3D parametric CAD that runs in the browser for people and permissioned typed agents, powered by OpenCascade WASM.
SkillAGPL-3.0★ 514No key
Turn pull requests and code diffs into interactive HTML walkthroughs that explain the logical flow of a change.
SkillMIT★ 15No key
Guided, evidence-anchored reviews of agent-written code, read and answered in the browser
SkillMIT★ 3Few starsNo key
MCP server that bridges why-did-you-render data from the browser to coding agents
Node.jsMIT★ 1Few starsNo key
Who stands behind it
