Skill Claude CodeCodex
Guidance for TanStack Query, a library that fetches and stores server data in a web app. It covers queries, changes, cached data, loading more results, server rendering, and temporary optimistic changes.
Skill Claude CodeCodex
A tool for analysing test coverage, which shows how much of a codebase is exercised by tests. It also helps identify code that has no tests and decide what to test first.
Skill Claude Code
A development workflow for a time-management application, including agent registration and choosing a task.
Skill Claude CodeCodex
A local audio-transcription procedure using faster-whisper, a speech-to-text tool, on a GPU.
Skill Claude Code
A coordinator for the libs/ui shared user-interface component library. It receives requests, sorts them, and helps implement components used across the interface.
Skill Claude Code
A review of an application's interface and user experience. It checks accessibility against WCAG 2.1, responsive layouts, design-system consistency, and possible usability improvements.
Skill Claude Code
A development workflow for Umami, a self-hosted analytics tool that measures website use, across Letar projects.
Skill Codex
A print-layout procedure for folding business cards on a Canon TM-300 printer.
Skill Claude Code
A planning workflow for running Letar as a web studio. It covers supported clients, incoming work, and hourly pricing.
Skill Claude Code
A workflow for moving completed tasks and old CHANGELOG entries into archive files.
Skill Claude CodeCodex
A workflow for writing unit tests and end-to-end tests using test-driven development (TDD). TDD means writing a failing test first, making it pass, then improving the code.
Skill Claude Code
Guidance for editing a ZenStack v3 data model and its access rules. ZenStack extends a database schema with relationships, permissions, form metadata, custom procedures, and migrations.
Agent Claude Code
An agent that checks ZenStack access-control policies after changes to @@allow or @@deny rules. These rules control who may access or change data.
Agent Claude Code
An end-to-end test writer that generates Playwright tests for complete user journeys. End-to-end tests operate the application like a user, while Playwright is a tool for automating browsers.
Agent Claude Code
A coding agent that implements a completed task description from a Markdown file. It follows the stated design, writes code and tests, and does not choose the approach.
Agent Claude Code
A coding agent for refactoring a monorepo, a repository that contains multiple related projects or packages. It focuses on React components, hooks, server actions, data models, API routes, and moving shared code into library folders.
Agent Claude Code
A security review helper that checks an application for common web security problems, exposed secrets, and incorrect access rules. OWASP Top 10 is a widely used list of major web application risks.
Agent Claude Code
A test coverage analysis helper that finds code without enough tests and helps rank what to test first. Test coverage measures which parts of a program are exercised by tests.
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
Nx's MCP server: lets the agent read the Nx project graph, look up generators and run tasks in an Nx monorepo. Launched with cmd /c bunx [email protected] C:/web/letar --minimal false.
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
MCP server "letar" as configured in kamiletar/letar. Launched with bun .claude/mcp/letar.ts.
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
MCP server "letar-db" as configured in kamiletar/letar. Launched with bun .claude/mcp/letar-db.ts.
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
MCP server "agent-mail", hosted remotely at 127.0.0.1, as configured in kamiletar/letar.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: