By ElvinOuyang
AI development skills: prompt evaluation, spec-driven tests, and token-efficient project setup
Test AI system prompts that involve tool calls by packaging them as a skill with mock callable tools, running evals inline (no extra API cost) or via model-specific subagents, and grading assertions against tool-call logs. Use this skill whenever you want to evaluate whether a system prompt causes a model to call the right tools with the right parameters — including comparing behavior across models like Haiku vs Sonnet.
Use when the user asks to add tests, expand test coverage, gate quality with tests, test against specs, write unit tests for deterministic behavior, or verify the app matches its design specs. Also use when the user says "cover the app with tests", "make sure the specs are enforced by tests", or "what test gaps do we have". Use this for any project with design specs, PRDs, or implementation plans that define testable behavior.
Use when setting up a new project's CLAUDE.md, when the user asks to reduce token usage, add token efficiency rules, or optimize Claude Code output verbosity. Also use when creating CLAUDE.md from scratch for any project.
A Claude Code plugin marketplace with curated skills for iOS development, web development, and AI agent workflows.
Add this marketplace to Claude Code:
/plugin marketplace add ElvinOuyang/claude-skill-collection
Then install the plugins you need:
/plugin install ios-dev-toolkit@claude-skill-collection
/plugin install web-dev-toolkit@claude-skill-collection
/plugin install ai-dev-toolkit@claude-skill-collection
/plugin install openclaw-config@claude-skill-collection
To enable auto-updates: /plugin > Marketplaces tab > select this marketplace > Enable auto-update.
iOS/SwiftUI development skills for building, polishing, and deploying iOS apps.
| Skill | Description |
|---|---|
| axe | iOS Simulator automation via AXe CLI |
| ios-animate | Enhance SwiftUI views with purposeful animations, haptics, and motion |
| ios-audit | Technical quality checks: accessibility, performance, HIG compliance |
| ios-critique | UX evaluation with quantitative scoring and persona-based testing |
| ios-polish | Final quality pass for spacing, typography, color, and animation |
| ios-simulator-nav | Navigate iOS Simulator with AXe label-based taps |
| ios-testflight-deploy | TestFlight deployment workflow with failure recovery |
Web development skills for mobile workflows, testing, and UI verification.
| Skill | Description |
|---|---|
| web-mobile-playwright-tests | Convert mobile workflow docs into Playwright test projects |
| web-mobile-workflow | Generate mobile browser workflow documentation via Playwright |
| web-ui-spec-checker | Check running web app UI against design specs |
Skills for iterating on AI agent prompts, generating tests, and optimizing projects.
| Skill | Description |
|---|---|
| prompt-eval | Test AI system prompts with mock tools and eval assertions |
| spec-driven-tests | Generate tests from specs, PRDs, and implementation plans |
| token-efficient-setup | Set up CLAUDE.md with token efficiency rules |
| Skill | Description |
|---|---|
| openclaw-config | Configure OpenClaw self-hosted AI gateway via Docker |
claude-skill-collection/
├── .claude-plugin/
│ └── marketplace.json
└── plugins/
├── ios-dev-toolkit/
│ ├── .claude-plugin/plugin.json
│ └── skills/
├── web-dev-toolkit/
│ ├── .claude-plugin/plugin.json
│ └── skills/
├── ai-dev-toolkit/
│ ├── .claude-plugin/plugin.json
│ └── skills/
└── openclaw-config/
├── .claude-plugin/plugin.json
└── skills/
After pushing changes to this repo, bump the version in the relevant plugin.json. Users with auto-update enabled will get the new version at Claude Code startup. Manual update:
/plugin marketplace update claude-skill-collection
All rights reserved. No license is granted at this time.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub elvinouyang/claude-skill-collection --plugin ai-dev-toolkitWeb development skills: mobile workflows, Playwright test generation, and UI spec checking
Configure OpenClaw self-hosted AI gateway via Docker
iOS/SwiftUI development skills: animation, audit, critique, polish, simulator nav, TestFlight deploy, and AXe automation
A la carte AI skills for LLM-assisted development
Unified capability management center for Skills, Agents, and Commands.
4つの専門エージェント(アーキテクト・リサーチャー・ライター・レビュアー)がチームで高品質なスキルを設計・作成する
Comprehensive development infrastructure for Claude Code projects. Includes 12 AI skills, task coordination hooks, project templates, and a visual dev-manager dashboard.
Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling
Create, test, measure, and iteratively improve Claude Code skills with category-aware design, gotchas-driven development, progressive disclosure coaching, and automated description optimization.