Discover data ai productivity tools skills, compare source repositories and read the instructions for each workflow.
Guide la création de commits bien formatés, push vers origin et création de Pull Requests documentées. Utilise ce skill lorsque l'utilisateur demande de commiter des changements, créer une PR, ou finaliser un t...
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive full-stack implementation plans with exact file paths, complete code examp...
Full autonomous feature development with single approval gate. Orchestrates: Research -> Plan -> APPROVAL -> Work (Atlas) -> Review -> Compound.
Semantic Versioning 기반 릴리스 관리. version.txt, CHANGELOG.md 자동 업데이트.
Setup and troubleshoot GitHub Actions workflows using anthropics/claude-code-action for automated PR reviews. Use when creating CI/CD workflows that leverage Claude for code review, research validation, or auto...
Use this skill when the user asks about "Cloud Tasks", "background jobs", "delayed processing", "rate limit handling", "async queue", "enqueue task", or any task queue work. Provides Cloud Tasks patterns for ba...
Automation architecture, workflow design, task execution strategy, and error recovery
Turn engineering work into clear, accurate, usable documentation and developer enablement assets (quickstarts, how-to guides, concept docs, API reference, samples, runbooks, troubleshooting, release notes, migr...
Implement Agent Skills for the user's project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI) to ensure compatibility and provides specialized templates.
Create new documentation pages interactively. Analyzes codebase and guides you through the process.
Generate structured prompts for autonomous AI work. Creates PROMPT.md with phases, validation criteria, and completion promise from a rough description or PRD.
Automates the import and normalization of Claude Code skills (Markdown files) into the Antigravity skill structure.
Search code semantically using AG4ONE Serena integration
Dispatch coding tasks to OpenCode or Claude Code on Perry workspaces. Use for development work, PR reviews, or any coding task requiring an isolated environment.
Skill for fetching and parsing content from GitHub repositories. Use when cloning repos, fetching raw files, parsing repository structure, and working with GitHub's API or raw content URLs.
Guides systematic code changes through planning, implementation, and verification phases while enforcing architectural patterns. This skill should be used when the user asks to "implement a feature", "make chan...
Convert Google Stitch HTML exports into reusable shadcn/ui React components. Use when user provides HTML file paths exported from stitch.withgoogle.com and needs TypeScript React components with CVA variants, p...
Guide for creating effective internal technical documentation (READMEs, ADRs, Contribution Guides). Use this skill when the user asks to write, refactor, or improve internal project documentation.
Analyze repository and generate documentation. Creates context memory for consistent AI assistance.
Solve coding problems using multi-agent retrieval, planning, coding, and debugging pipeline. Use when solving algorithmic problems, implementing features from specifications, or when code needs iterative refine...
Internal skill for overnight autonomous execution. Provides context and rules for unattended development.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development requests that would benefit from project-specific conte...
Expert architect for generating OpenCode commands, skills, and sub-agent configuration files. Uses opencode-mastery skill for accurate OpenCode documentation. Use proactively when user wants to create, build, o...
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.