By litestar-org
Apply opinionated, first-party patterns across the entire Litestar development lifecycle—from API design and data access to deployment and testing—including a code review agent that enforces canonical patterns.
Auto-activate for advanced_alchemy imports, alembic/, SQLAlchemyAsyncRepositoryService, SQLAlchemyAsyncConfig, repository_type, service_class, filters, or storage. Not for raw SQLAlchemy.
Auto-activate for Google ADK, LlmAgent, Runner, SQLSpecSessionService, Vertex AI, SSE agent chats, tool calls, or Litestar model workflows. Not for offline ML training.
Auto-activate for guards=, Guard, ASGIConnection, JWTAuth, JWTCookieAuth, SessionAuth, role or tenant checks, or WebSocket auth. Not for frontend route protection.
Auto-activate for uv build, hatch build, PyApp, PYAPP_*, wheel assets, GitHub release matrices, cargo-zigbuild, or python-build-standalone. Not for runtime deployment.
Auto-activate for SQLAlchemyAsyncRepositoryService, SQLSpecAsyncService, create_filter_dependencies, LimitOffsetFilter, OffsetPagination, filters, or CRUD services. Not for raw drivers.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Opinionated, first-party agent skills, plugins, subagents, slash commands, and MCP servers for the Litestar framework and its ecosystem — publishable to every major AI agent and IDE from a single repo.
litestar-skills is a curated collection of agentic-development assets that teach AI coding agents how the Litestar team actually builds software. It covers the Litestar core plus first-party libraries (sqlspec, advanced-alchemy, litestar-granian, litestar-saq, litestar-vite, litestar-mcp, litestar-email, litestar-htmx, litestar-asyncpg, litestar-oracledb, and more).
v0.4.0 — early access. Multi-host plumbing, 28 skills, ~28,500 lines of canonical content. Full launch-skill catalog growing.
Breaking host identity note: host-facing marketplace, plugin, extension, managed-config, and skill namespace IDs are litestar. Existing installs under litestar-skills should be removed and reinstalled; no alias is shipped. The Python package and repository remain litestar-skills.
This repo documents hosts by the artifacts it ships:
| Host | Entry Point |
|---|---|
| Claude Code | .claude-plugin/plugin.json + marketplace metadata + .claude-plugin/agents/*.md |
| Antigravity CLI | plugin.json + hooks.json + agents/*.md + skills/ + hooks/ |
| Codex CLI | .codex-plugin/plugin.json + .codex/agents/*.toml |
| OpenCode | .opencode/plugins/litestar.js + .opencode/agents/*.md |
| Cursor | .cursor-plugin/plugin.json |
| VS Code / Copilot | Raw skills/ path via chat.skillsLocations |
| OpenClaw | .agents/skills/ + AGENTS.md |
Different hosts expose the same repo assets with different command surfaces. Keep four names separate:
| Concept | Canonical Value |
|---|---|
| Plugin / marketplace identity | litestar |
| Skill directory names | skills/<skill-name>/SKILL.md, e.g. skills/litestar-routing/SKILL.md |
| Hook and policy namespace | litestar:<skill-name>, e.g. litestar:litestar-routing |
| Command files | commands/litestar/{configure,new-app,new-domain,review}.toml |
| Harness | Skill Manual Trigger | Command Trigger | Reviewer Agent Trigger |
|---|---|---|---|
| Claude Code | /litestar:litestar for the hub skill; /litestar:litestar-routing for focused skills. Plugin policy uses Skill(litestar:<skill-name>). | /litestar:configure, /litestar:new-app, /litestar:new-domain, /litestar:review | Select litestar-reviewer from .claude-plugin/agents/ where Claude exposes plugin subagents. |
| Antigravity CLI | Skills load from the litestar plugin or .agents/skills/; use the displayed skill/template name in Antigravity. SessionStart hooks inject litestar:<skill-name> reminders when project signals are detected. | No TOML slash-command surface in the Antigravity plugin schema. Use prompts backed by the skills or reviewer agent. | litestar-reviewer from top-level agents/. |
| Codex CLI | Codex surfaces installed skills by displayed name. In $-trigger Codex surfaces, force the hub with $litestar:litestar and focused skills with $litestar:<skill-name>; natural language also works. | Codex plugins do not currently expose plugin-defined /litestar:* slash commands. Use natural language such as “Use Litestar review…” and the litestar skill router. | $agent litestar-reviewer from .codex/agents/. |
| OpenCode | opencode skill list shows project-local copied skills; use the displayed skill name in the OpenCode UI. Plugin reminders use litestar:<skill-name>. | No TOML command loader in the OpenCode plugin. Use natural-language prompts or project-local command support. | litestar-reviewer from .opencode/agents/. |
| Cursor | Skills are discovered from the plugin/rule path; use the displayed skill name in Cursor. | Host command support varies; shipped TOML commands remain under commands/litestar/. | No Cursor-specific reviewer dialect shipped. |
| VS Code / Copilot | Skills are discovered from chat.skillsLocations; use the displayed skill name in Copilot Chat. | No shipped command wrapper. | No VS Code-specific reviewer dialect shipped. |
| OpenClaw | Skills are discovered from .agents/skills/; use the displayed skill name. | No shipped command wrapper. | No OpenClaw-specific reviewer dialect shipped. |
Canonical agent source lives in tools/agent-sources/litestar-reviewer.yaml; run make agents after editing it, then make sync-codex-package before make lint so the generated Codex package copy stays current.
Pick your host and run the one command below. If you use several agents, skip to the multi-host installer.
/plugin marketplace add litestar-org/litestar-skills
/plugin install litestar@litestar
The /plugin commands run inside a Claude Code session — the installer can't automate this part.
npx claudepluginhub litestar-org/litestar-skills --plugin litestarComplete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development