Impeccable
Impeccable official site ↗Last checked against the official docs:
What it does
A design skill for AI coding agents that helps them build and fix interfaces that don't look like generic AI output. You get one /impeccable command with sub-commands such as critique, audit, polish, bolder, quieter, distill and harden, plus a live mode that swaps design variants into your running dev server. It also ships a detector CLI with deterministic rules for common AI-design tells and quality problems (no LLM or API key needed), and an optional design hook that checks each UI file the agent edits. It started from Anthropic's frontend-design skill. Apache-2.0 licensed.
Who it's for
People building websites and app screens with Claude Code, Cursor, Codex, Copilot, Gemini CLI, OpenCode or similar agents who keep getting the same samey layouts, fonts and colors.
How to set it up
From your project folder, run the installer. It detects your coding tools, asks whether to install for this project or globally, and offers the design hook where your tool supports one:
bashnpx impeccable installReload your coding tool, then run init once per project in the agent's chat. It reads your code, asks what it can't work out (who the product is for, what it needs to do) and writes PRODUCT.md. On Codex the prefix is $ instead of /:
text/impeccable initClaude Code alternative: add the plugin marketplace, then open /plugin and install Impeccable:
text/plugin marketplace add pbakaus/impeccablePoint a command at one narrow target. Narrow targets work better than whole pages:
text/impeccable critique the pricing cards /impeccable polish settings /impeccable harden checkoutRun the detector on its own, on source files or a rendered page (rules like low contrast only run on a URL). Exit code 2 means it found problems, which makes it usable in CI:
bashnpx impeccable detect src/ npx impeccable detect http://localhost:5173 npx impeccable detect --list-rulesThings to know before you use it: the design hook runs outside the model's approval prompts, so in Claude Code it runs even when you deny the model's own commands (pass --settings '{"disableAllHooks": true}' to switch hooks off for a run). The skill fetches design directions from impeccable.style, and sends an anonymous record of which ones were shown and picked unless you turn telemetry off with npx impeccable telemetry off or DO_NOT_TRACK=1. In live mode, Apply can fall back to running the codex or claude CLI with approvals and sandboxing turned off; set IMPECCABLE_LIVE_COPY_AGENT=chat (or off) before starting live mode to prevent that.
Check the official Impeccable docs for the latest steps.
Set it up / Fixes
Step-by-step guides for getting Impeccable running and fixing common errors.
Example prompts
/impeccable critique the onboarding flow and list the three changes that would help most./impeccable quieter the landing page hero, keep the copy as is.Run npx impeccable detect on src/components and fix every finding in the Button and Card components.Made Impeccable? Add the badge
If you like, show that Impeccable 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/impeccable/)HTML (for a website)
<a href="https://www.pluginstackai.com/plugins/impeccable/"><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.