By ideaprism
Professional Agent Skills collection for full-stack development, logic planning, and multimedia processing.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
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.
Empower agents with professional capabilities in specific fields (such as full-stack development, complex logic planning, multimedia processing, etc.) through modular Skills definitions, allowing agents to solve complex problems systematically like human experts.
.
├── .claude-plugin/ # Claude plugin configuration files
├── skills/ # Antigravity Skills library
│ ├── skill-name/ # Individual skill directory
│ │ ├── SKILL.md # Core skill definition and Prompt (Required)
│ │ ├── scripts/ # Scripts relied upon by the skill (Optional)
│ │ ├── examples/ # Skill usage examples (Optional)
│ │ └── resources/ # Templates and resources relied upon by the skill (Optional)
├── docs/ # User manual and documentation guides
├── scripts/ # Maintenance scripts
├── skills_sources.json # Skills synchronization source config
├── skills_index.json # Skills metadata index
├── spec/ # Specification documents
├── template/ # New skill template
└── README.md
Antigravity Skills follow the universal SKILL.md format and can work seamlessly with any AI coding assistant that supports Agentic Skills:
| Tool Name (Agent) | Type | Compatibility | Project Path | Global Path |
|---|---|---|---|---|
| Antigravity | IDE | ✅ Full | .agent/skills/ | ~/.gemini/antigravity/skills/ |
| Claude Code | CLI | ✅ Full | .claude/skills/ | ~/.claude/skills/ |
| Gemini CLI | CLI | ✅ Full | .gemini/skills/ | ~/.gemini/skills/ |
| Codex | CLI | ✅ Full | .codex/skills/ | ~/.codex/skills/ |
| Cursor | IDE | ✅ Full | .cursor/skills/ | ~/.cursor/skills/ |
| GitHub Copilot | Extension | ⚠️ Partial | .github/skills/ | ~/.copilot/skills/ |
| OpenCode | CLI | ✅ Full | .opencode/skills/ | ~/.config/opencode/skills/ |
| Windsurf | IDE | ✅ Full | .windsurf/skills/ | ~/.codeium/windsurf/skills/ |
| Trae | IDE | ✅ Full | .trae/skills/ | ~/.trae/skills/ |
[!TIP] Most tools will automatically discover skills in
.agent/skills/. For maximum compatibility, please clone/copy into this directory.
First, clone this repository locally (it is recommended to place it in a fixed location for global reference):
git clone https://github.com/guanyang/antigravity-skills.git ~/antigravity-skills
We strongly recommend using Symbolic Links (Symlink) for installation, so that when you update this repository via git pull, all tools will automatically sync the latest features.
Enable skills only for the current project. Run in your project root:
mkdir -p .agent/skills
ln -s ~/antigravity-skills/skills/* .agent/skills/
Enable skills by default in all projects. Run the corresponding command based on the tool; common examples:
| Tool Name | Global Installation Command (macOS/Linux) |
|---|---|
| General | mkdir -p ~/.agent/skills && ln -s ~/antigravity-skills/skills/* ~/.agent/skills/ |
| Claude Code | mkdir -p ~/.claude/skills && ln -s ~/antigravity-skills/skills/* ~/.claude/skills/ |
| Antigravity | mkdir -p ~/.gemini/antigravity/skills && ln -s ~/antigravity-skills/skills/* ~/.gemini/antigravity/skills/ |
| Gemini | mkdir -p ~/.gemini/skills && ln -s ~/antigravity-skills/skills/* ~/.gemini/skills/ |
| Codex | mkdir -p ~/.codex/skills && ln -s ~/antigravity-skills/skills/* ~/.codex/skills/ |
If you primarily use Claude Code, you can install with one click via the plugin marketplace (this method automatically handles skill loading):
# 1. Start Claude Code
# 2. Add the plugin marketplace
/plugin marketplace add guanyang/antigravity-skills
# 3. Install the plugin from the marketplace
/plugin install antigravity-skills@antigravity-skills
Enter @[skill-name] or /skill-name in the chat box to invoke them, for example:
/canvas-design Help me design a 16:9 blog cover about "Deep Learning"
pdf2docx, pandas, etc.).Many skills in this project originate from excellent open-source communities. To keep in sync with upstream repositories, you can update them in the following ways:
npx claudepluginhub ideaprism/antigravity-skills --plugin antigravity-skillsMatt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Plugin-safe Claude Code distribution of Agentic Awesome Skills with 1,913 supported skills.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,884 supported skills.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses