audit-project
Analyze current project's Claude Code configuration and suggest improvements
Discover Research skills, compare source repositories and read the instructions for each workflow.
Analyze current project's Claude Code configuration and suggest improvements
Bidirectional sync between local Claude Code skills (~/.claude/skills/) and the GithubSkills repository. Use when you need to push local skills to the repo, pull repo skills to local, or check sync status.
Applies project-specific coding conventions and patterns. Use when writing, reviewing, or modifying code to maintain consistency with the codebase style.
React Native - UI kit, NativeWind/Tailwind styling, hooks, component patterns. Use when working with React Native code.
TypeScript API client - types, React Query, mutations. Use when working with API client code or types.
Vue 3 frontend - composition API, TypeScript, Tailwind styling. Use when working with Vue components.
Rails migrations - schema changes, data migrations, migration commands. Use when creating or modifying database migrations.
Git conventions - commit messages, branch management, rebasing. Use when committing code or reviewing commit history.
Code refactoring - architecture, extraction patterns, naming. Use when improving code structure.
Checks for breaking changes in API serializers before production release. Use when reviewing PRs to production branch.
Maintain code quality with Ruff for Python and ESLint/TypeScript for frontend. Run linters, fix issues, and ensure consistent formatting. Use when linting code, fixing style issues, or preparing to commit.
Manage Vite development server for Gentle Disagree. Use when starting the application, after code changes, when servers crash, verifying servers are running, or troubleshooting errors. (project)
Quick database queries and notification testing for sbhq-mobile. Use when querying contests, users, notifications, or testing push notifications.
Reverse engineering binaries using radare2 (r2). Analyze executables, disassemble code, find functions, extract strings, patch binaries, debug programs, and explore firmware. Supports persistent sessions for la...
Creates, refines, ingests, and evaluates agent skills using archetype-driven design. Use when building skills from scratch, extracting knowledge from documentation, or auditing skill quality. Do not use for non...
General-purpose guidance for Claude Code (terminal) and Claude Dev (platform). Covers stable principles (progressive disclosure, hooks, security) and volatile details with lookup workflows.
Test Model Context Protocol (MCP) servers using the MCP Inspector CLI
This skill should be used when the user needs structured thinking frameworks to analyze decisions, problems, or tasks. Apply multiple decision-making methodologies (10/10/10, 5 Whys, Eisenhower Matrix, First Pr...
Start an AiGov session by reading AGENTS + EVALSETS and proposing the smallest next PR with verification and effort label.
Close an AiGov session by writing a worklog entry, updating STATUS.md, and printing a PR-ready summary with verification and risks. Use when the user asks to wrap up, end the session, or prepare a PR summary.
Enforce repo execution discipline: keep PRs small; run migration-smoke when invariants change; never hand-edit vendored contracts.
Verify which environment variable keys are present in .env files or shell environment without exposing their values. Use when you need to check env configuration or compare keys between .env files.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claud...
This skill should be used to remove AI-generated artifacts and unnecessary code before committing. It scans changed files for redundant comments, AI TODOs, excessive docstrings, and unnecessary markdown files....
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.