agent-skills
A community-driven collection of skills, prompts, and workflows to help builders get the most out of Claude Code and other AI agents.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/thedesignproject/agent-skills with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/thedesignproject/agent-skills'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/thedesignproject--agent-skills)HTML
<a href="/listings/thedesignproject--agent-skills"><img src="/api/listings/thedesignproject--agent-skills/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# Install all skills — pick from an interactive list of every skill in the repo npx skills add thedesignproject/agent-skills # Install one skill npx skills add thedesignproject/agent-skills -s <skill-name> # Install several at once npx skills add thedesignproject/agent-skills -s figma-use -s frontend-design
Add `-g` to install globally instead of into the current project. See `npx skills add --help` for the full flag list.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 81 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # Agent Skills
- A collection of knowledge, tips, and resources for the builder community on AI, Claude Code, and other developer tools.
- ## What's inside
- Practical guides, skills, and references for getting the most out of AI-powered development tools.
- ## Download Build My Designer Brain
- [**Download the skill ZIP**](https://github.com/thedesignproject/agent-skills/raw/refs/heads/main/downloads/build-my-designer-brain.zip) · [Setup instructions](guides/build-my-designer-brain.md)
- Build your personal critique methods, AI working preferences, optional references and taste, and reusable lessons through a guided interview. No terminal needed for Claude upload.
- 1. Download the ZIP above. Keep it zipped for Claude.
- 2. In Claude, open **Customize → Skills → + → Create skill → Upload a skill** and select the ZIP. Enable the skill; file creation must be enabled.
- 3. Say: **“Use Build My Designer Brain to help me build my personal designer brain.”**
- For local coding agents, unzip the download and install the complete folder using the [tool-specific instructions](guides/build-my-designer-brain.md#install-the-shared-skill). ChatGPT installation differs by surface; the ZIP is not a published ChatGPT plugin.
- ## Quick start: NPX Installation (Recommended)
- ```bash
- # Install all skills — pick from an interactive list of every skill in the repo
- npx skills add thedesignproject/agent-skills
- # Install one skill
- npx skills add thedesignproject/agent-skills -s <skill-name>
- # Install several at once
- npx skills add thedesignproject/agent-skills -s figma-use -s frontend-design
- ```
- Add `-g` to install globally instead of into the current project. See `npx skills add --help` for the full flag list.
- ## Skills
- Each skill activates in one of two ways, shown in the **How to use** column:
- - **Slash command** — invoke it explicitly, e.g. `/create-prd path/to/transcript.md`.
- - **Auto** — the skill triggers on its own when your request matches what it does.
- | Skill | What it does | How to use |
- |-------|--------------|------------|
- | [accessibility](skills/accessibility/) | Audits and improves web accessibility following WCAG 2.2 — a11y reviews, screen reader support, keyboard navigation. | Auto — ask to "audit accessibility", "a11y audit", "WCAG compliance", or "make accessible". |
- | [agentic-design-systems](skills/agentic-design-systems/) | Designs, scaffolds, extends, or audits a component library whose primary consumer is an AI agent. Generates machine-readable metadata for components, variants, tokens, and anti-patterns. | Auto — ask to build or make a design system AI-readable, define a component metadata schema, or scaffold a UI library for an LLM. |
- | [ai-component-metadata](skills/ai-component-metadata/) | Generates AI-ready metadata for design system components. Analyzes structure and produces structured metadata so an agent knows when and how to use each one. | Auto — ask to generate AI-ready metadata for your design-system components. |
- | [build-my-designer-brain](skills/build-my-designer-brain/) | Builds and evolves a personal designer brain with critique methods, AI working preferences, optional references and taste, and reusable lessons. | Auto — ask to build or update your personal designer brain. Includes a guided interview with write-ins and ranked priorities. |
- | [business-kickoff-workshop](skills/business-kickoff-workshop/) | Prepares a customized 45-min Business Model Canvas workshop agenda from customer context before a call, or fills the BMC from a post-call transcript. | Auto — mention a kickoff call, BMC workshop, or business model canvas. |
- | [caveman](skills/caveman/) | Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping technical accuracy. Levels: lite, full, ultra. | `/caveman`, or say "caveman mode" / "be brief" / "less tokens". |
- | [create-prd](skills/create-prd/) | Generate structured PRDs from feature request transcripts or descriptions. Researches your codebase for accurate technical scoping and optionally creates Linear projects and issues. | `/create-prd path/to/transcript.md` (or paste the request). Customize `company-context.md` first. |
- | [create-skill](skills/create-skill/) | Authors new Cursor Agent Skills. Use when writing a new SKILL.md or asking how the skill format works. | Auto — ask to create a new skill or about `SKILL.md` structure. |
- | [extract-design-system](skills/extract-design-system/) | Extracts design primitives (color, typography, spacing) from a public website and generates starter token files. | Auto — ask to extract design tokens or a design system from a website URL. |
- | [figma-generate-design](skills/figma-generate-design/) | Translates an app page, view, or multi-section layout from code into Figma. Push existing pages into Figma without recreating by hand. | Auto — ask to build, write, or push a page/screen/modal to Figma. Pairs with `figma-use`. |
- | [figma-use](skills/figma-use/) | Mandatory prerequisite before any `use_figma` MCP call. Foundational context that prevents common write/read failures in Figma. | Auto — loads before any write or scripted read in a Figma file. |
- | [find-skills](skills/find-skills/) | Discovers and installs agent skills when you ask "is there a skill for X?" — surfaces things you didn't know existed. | Auto — ask "find a skill for X" or "how do I do X". |
- | [frontend-design](skills/frontend-design/) | Creates distinctive, production-grade frontend interfaces with high design quality. Avoids the generic "AI aesthetic" of identical sans-serif + flat color UI. | Auto — ask to build web components, pages, or applications. |
- | [marketing-psychology](skills/marketing-psychology/) | Applies psychology, mental models, and behavioral science to marketing — anchoring, social proof, scarcity, loss aversion, framing, nudge. | Auto — ask to apply psychology, persuasion, or behavioral science to marketing. |
- | [pr-branch-naming](skills/pr-branch-naming/) | Generate a conventionally-named branch and PR title from a feature description, with optional one-step branch checkout and draft PR creation. | `/pr-branch-naming [feature description]`, or ask "what should I call this branch / PR?" |
- | [presentation](skills/presentation/) | Create polished single-file HTML/CSS/JS slide deck presentations with animations, keyboard/click/swipe navigation, and progressive bullet reveal. | `/presentation [topic]`, or ask Claude to build a slide deck / pitch deck. |
- | [prompt-engineer](skills/prompt-engineer/) | Writes, refactors, and evaluates LLM prompts — templates, structured output schemas, evaluation rubrics, test suites. | Auto — ask to write, refactor, or evaluate prompts (chain-of-thought, few-shot, system prompts). |
- | [product-context-builder](skills/product-context-builder/) | Creates a connected context system across AGENTS.md, CLAUDE.md, PRODUCT.md, DESIGN.md, and project skills, grounded in the real repository. | Auto — ask to set up or improve AI context files for a product or repository. |
- | [web-design-guidelines](skills/web-design-guidelines/) | Reviews UI code against Web Interface Guidelines — UX, accessibility, design conventions. | Auto — ask to "review my UI", "audit design", or "check my site against best practices". |
- | [writing-skills](skills/writing-skills/) | Creates, edits, and verifies skills before deployment. Best practices, examples, graph conventions, subagent-based testing. | Auto — used when creating, editing, or testing skills. |
- ## Guides
- | Guide | Description |
- |-------|-------------|
- | [build-my-designer-brain](guides/build-my-designer-brain.md) | Install the personal designer-brain skill, run the interview, and reuse the resulting knowledge in project work. |
- | [pr-and-branch-naming](guides/github-for-designers/pr-and-branch-naming.md) | A simple convention for naming pull requests and branches when working on a client codebase, with an optional TDP prefix to make designer-authored work easy to spot. |
- ## Contributing
- Contributions are welcome! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
- Please note that this project follows a [Code of Conduct](CODE_OF_CONDUCT.md).
- ## License
- This project is licensed under the [MIT License](LICENSE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.