skills
A library of AI agent skills for research and design
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/dylanfeltus--skills)HTML
<a href="/listings/dylanfeltus--skills"><img src="/api/listings/dylanfeltus--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.
Via npx (recommended)
# Install all skills npx skills add dylanfeltus/skills # Install a specific skill npx skills add dylanfeltus/skills --skill visual-qa
Auto-detects your agent (Claude Code, OpenClaw, Codex, Cursor, etc.)
Manual
1. Copy the skill folder into your agent's skills directory 2. Reference the `SKILL.md` in your system prompt or project instructions 3. The agent follows the workflow and instructions defined in the skill
Each skill includes: - `SKILL.md` — Full instructions the agent reads (trigger conditions, API details, error handling, output format) - `README.md` — Human-facing docs
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 · 71 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # Skills Library
- A collection of reusable AI agent skills for research, intelligence gathering, design, and content creation. Drop a folder into your agent's skills directory and it just works.
- ## What are skills?
- Skills are structured instructions that give AI agents domain expertise and systematic workflows. Instead of prompting from scratch, you load a skill and get consistent, high-quality output. Works with OpenClaw, Claude Code, Cursor, and other LLM-based tools.
- ## Available Skills
- ### Research & Intelligence
- | Skill | Description | Auth Required |
- |-------|-------------|---------------|
- | [hn-search](./hn-search/) | Search & monitor Hacker News via the Algolia API | ❌ Free, no key |
- | [producthunt](./producthunt/) | Search Product Hunt launches via GraphQL V2 API | ✅ Free dev token (~2 min setup) |
- | [appstore-intel](./appstore-intel/) | App Store ratings, reviews, and metadata (iOS + Android) | ❌ Free, no key |
- | [trademark-search](./trademark-search/) | USPTO trademark availability search | ❌ Free, no key |
- ### Agent Commerce
- | Skill | Description | Auth Required |
- |-------|-------------|---------------|
- | [privacy-cards](./privacy-cards/) | Create virtual cards for agent purchases via Privacy.com API | ✅ Privacy.com API key |
- ### Design
- | Skill | Description | Auth Required |
- |-------|-------------|---------------|
- | [motion-design-patterns](./motion-design-patterns/) | Framer Motion patterns — springs, staggers, layout animations, micro-interactions | ❌ None |
- | [design-tokens](./design-tokens/) | Type scales, color palettes, spacing grids, WCAG contrast, dark mode derivation | ❌ None |
- | [creative-direction](./creative-direction/) | Image prompt templates, model selection, anti-generic patterns | ❌ None |
- | [visual-qa](./visual-qa/) | Screenshot review against design intent using vision models | ❌ None |
- ### Content & Quality
- | Skill | Description | Auth Required |
- |-------|-------------|---------------|
- | [recursive-improvement](./recursive-improvement/) | Generate → Evaluate → Improve loop for higher-quality output | ❌ None |
- ## Install
- ### Via npx (recommended)
- ```bash
- # Install all skills
- npx skills add dylanfeltus/skills
- # Install a specific skill
- npx skills add dylanfeltus/skills --skill visual-qa
- ```
- Auto-detects your agent (Claude Code, OpenClaw, Codex, Cursor, etc.)
- ### Manual
- 1. Copy the skill folder into your agent's skills directory
- 2. Reference the `SKILL.md` in your system prompt or project instructions
- 3. The agent follows the workflow and instructions defined in the skill
- Each skill includes:
- - `SKILL.md` — Full instructions the agent reads (trigger conditions, API details, error handling, output format)
- - `README.md` — Human-facing docs
- ## Contributing
- More skills coming soon. Follow [@dylanfeltus](https://twitter.com/dylanfeltus) for updates.
- ---
- *Built by [Stratus Labs](https://stratuslabs.io)*
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.