AI Agent Skills

Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the…

Design, Test and Document APIs in plain Markdown. Compose Requests with API blocks. Reuse, Replace & Version everything just like code. Offline, Truly Git Native, No Loc…

CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness

Easily install and test mobile applications with a single click.

Audit URLs using Lighthouse and test performance with Lighthouse CI.

JD-driven Chinese resume optimization skill for China job seekers. 解析岗位 JD、诊断简历缺口、生成真实可信的中文定制简历、ATS 纯文本版和面试追问。

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the…

Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evid…

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguou…

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thr…

React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

Repository analysis, pull request review, issue triage, and release workflow automation.

Open-source @agent mentions for Slack and GitHub. OpenTag routes tagged requests to Codex, Claude Code, then returns results in thread.

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, pu

Cluster a GitHub issue backlog by root cause into a small set of plan-master issues, redirect children with a standardized comment, and bundle architectural-fix PRs that…