PluginStackWhat it does
GitHub's open-source toolkit for spec-driven development: you write down what to build and why, then have your coding agent turn that spec into a plan, a task list and working code, one reviewed step at a time. The Specify CLI (specify) sets up a project with the commands for your agent, and extensions add other workflows such as bug fixing (assess, fix, test). It works with GitHub Copilot, Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Cline, Kilo Code, Goose and others. MIT licensed.
Who it's for
Anyone who wants an AI agent to build a feature from a written spec and plan instead of one long prompt, and to review each stage before code gets written.
How to set it up
You need Python 3.11+, uv and a supported AI coding agent (Linux, macOS or Windows). Install the CLI and create a project. Swap copilot for your agent's integration key, such as claude, cursor-agent, codex, gemini or opencode:
bashuv tool install specify-cli specify init my-project --integration copilot cd my-projectStart your coding agent in the project folder and run these in the agent's chat (not your terminal), one at a time, reviewing each result before the next. Create the constitution once per project and repeat the rest for each feature:
text/speckit-constitution Create principles focused on code quality, testing, and maintainability. /speckit-specify Build a photo organizer with albums grouped by date. /speckit-plan Use Vite with vanilla JavaScript. Store metadata in SQLite. /speckit-tasks /speckit-implement /speckit-convergeThe command prefix depends on the agent (Codex, for example, uses $speckit-specify). Repeat implement and converge until converge reports Converged. To fix a bug without the full feature flow, add the bug extension from the project folder:
bashspecify extension add bugAlready installed an old version? uv tool install keeps the installed copy, so upgrade with uv tool install --force specify-cli. Very old CLIs fail with "No such option: --integration". Check what you have with specify version. Community extensions and presets in Spec Kit's catalogs aren't audited, so read their code before installing.
Check the official Spec Kit docs for the latest steps.
Set it up / Fixes
Step-by-step guides for getting Spec Kit running and fixing common errors.
Example prompts
/speckit-specify Add a CSV export to the reports page so users can download the filtered table./speckit-plan Keep the existing Next.js App Router setup and don't add new dependencies./speckit-bug-assess "Submitting an empty password crashes the login form." slug=login-crashMade Spec Kit? Add the badge
If you like, show that Spec Kit is listed and hand-checked here. It's optional: listings are free and we never ask for a link back.
Get the Markdown or HTML
Markdown (for a GitHub README)
[](https://www.pluginstackai.com/plugins/spec-kit/)HTML (for a website)
<a href="https://www.pluginstackai.com/plugins/spec-kit/"><img src="https://www.pluginstackai.com/badge/hand-checked.svg" alt="Hand-checked on PluginStack" width="226" height="28"></a>Free: MCP Starter Checklist
After you set this tool up, use the one-page checklist so your next MCP server doesn't fail on first connect.
More Rules & Prompts
- Anthropic
Agent Skills (Anthropic)
Anthropic's public repository of Agent Skills: folders with a SKILL.md file (plus optional scripts and resources) that Claude loads when a task needs them. It includes example skills, the document skills behind Claude's file creation, a skill template and a copy of the Agent Skills spec (the open standard lives at agentskills.io). Many skills are Apache-2.0; the document skills are source-available, not open source.
- Agentic AI Foundation (Linux Foundation)
AGENTS.md
A simple open format for giving coding agents project instructions: one AGENTS.md markdown file in your repo with setup commands, test steps and code style. It is now stewarded by the Agentic AI Foundation under the Linux Foundation, and the agents.md site lists many tools that read it, including Codex, Cursor, goose, OpenCode, Aider, Zed, Kilo Code and GitHub Copilot's coding agent. The site and repo are MIT licensed. Claude Code reads it too when a project has no CLAUDE.md.
- Google (Android)
Android Skills
Google's official Agent Skills for Android development: SKILL.md instructions that ground coding agents in current Android guidance for tasks where Google's evaluations show LLMs underperform. Examples include migrating XML views to Jetpack Compose, upgrading to AGP 9, setting up Navigation 3, making an app edge-to-edge, auditing R8 configuration and fixing ANRs. They follow the open Agent Skills standard, so they work with Claude Code, Codex, Gemini/Antigravity and other agents that support skills. Apache-2.0.
- Anthropic
Anthropic Knowledge Work Plugins
Anthropic's open-source set of role plugins built for Claude Cowork that also install in Claude Code. Each plugin bundles slash commands, skills and connector (MCP) settings for one kind of work: sales, finance, data, legal, marketing, customer support, product management, engineering, design, HR, operations, bio research, small business and more. Plugins are plain Markdown and JSON, so you can read and edit them, or fork one as a template for your own team. The repository's marketplace also lists plugins from partners. Apache-2.0.
- Anthropic
Claude Code Plugins (official marketplace)
Anthropic's official plugin marketplace for Claude Code. A plugin bundles skills, subagents, hooks and MCP or LSP servers so you install them in one step. It lists plugins Anthropic maintains (such as commit-commands, code-review, feature-dev and the language-server plugins) alongside plugins from partners and other authors. Claude Code adds this marketplace for you the first time you start an interactive terminal session. The repo is Apache-2.0; each plugin has its own license.
- Cloudflare
Cloudflare Security Audit Skill
An agent skill from Cloudflare that runs a structured security audit of a codebase instead of a one-shot "look for bugs" prompt. It works in phases: map the architecture and keep a coverage ledger, hunt for issues area by area, have a fresh sub-agent try to validate each candidate, write findings as JSON checked against a schema (confirmed, needs validation or rejected), verify each record again, then produce a written report. Cloudflare says it grew out of the internal vulnerability harness described on its blog in June 2026. It is a single skill (security-audit), MIT licensed.