Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Phase 2 of disciplined development. Creates implementation plans based on approved research. Specifies file changes, function signatures, test strategy, and step sequence. Requires human approval before impleme...
Blocks destructive git and filesystem commands before execution. Prevents accidental loss of uncommitted work from git checkout --, git reset --hard, rm -rf, and similar destructive operations. Works as a Claud...
Phase 5 of disciplined development. Validates system against original requirements through system testing and user acceptance testing (UAT). Uses structured stakeholder interviews to gather sign-off and traces...
Leverage personal notes and documentation through Terraphim's role-based search. AI agents can search developer's local knowledge organized by domain (Rust, frontend, architecture) using the terraphim-agent REP...
Phase 3 of disciplined development. Executes approved implementation plans step by step. Each step includes tests, follows the design exactly, and produces reviewable commits.
Open source contribution best practices. Creating quality pull requests, writing good issues, following project conventions, and collaborating effectively with maintainers.
Generates Rust code for GPUI desktop UI components following Zed editor patterns. Use when building desktop applications with gpui crate, creating themed UI components, implementing autocomplete/completions, bu...
Guide for creating new Transmissions applications with decision support for core vs remote development
Guide for creating custom Transmissions processors with factory registration for core and remote development
提取 YouTube 视频字幕并转换为 Markdown
使用 markitdown 将各种文件格式转换为 Markdown
Use when collaborating with other AI assistants (Codex, Gemini, Aider, Cursor, OpenCode), delegating tasks, or requesting code review.
Refine and structure prompts for LLMs to ensure clarity, reliability, and optimal performance. Use when writing system prompts, complex instructions, or debugging agent behaviors.
Writes technical prose (READMEs, ADRs, code comments) in the project's established human voice. Use when creating or editing .md files, writing Swift doc comments, authoring ADRs, or reviewing technical writing...
Curates context, optimizes prompts with XML, and manages extended thinking for Anthropic Claude models. Use when building Claude-based agents, designing system prompts, or handling long-context tasks.
Decide how to codify knowledge for reuse. Use when evaluating whether a pattern, solution, or insight should be formalized—and in what form (types, code structure, CLAUDE.md, README, skill, or code comments).
Author and structure effective Agent Skills. Use when creating new skills, refining existing ones, or auditing skill structure and best practices.
Create distinctive, production-grade frontend interfaces. Use when building web components, pages, or applications with React-based frameworks. Includes Tailwind CSS v4, Motion animations, and visual design phi...
Review Go code for this project following Clean Architecture principles, Go best practices, and project conventions. Use when reviewing code, pull requests, or checking code quality.
Generate mock implementations using mockery for testing. Use when creating mocks, updating mock interfaces, or setting up test doubles.
Guide for adding new feature modules following Clean Architecture pattern. Use when creating new features, modules, REST endpoints, or business logic components in this Go project.
Write unit tests and integration tests for Go code using testify, go-sqlmock, and mockery. Use when writing tests, creating test files, or testing repositories, use cases, and handlers.
Create REST API endpoints with proper validation, error handling, and Swagger documentation. Use when adding new routes, HTTP handlers, or REST API functionality.
Create and manage database migrations using golang-migrate. Use when creating tables, modifying schemas, adding columns, or managing database structure changes.
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.