create-commit
Create a commit. Use whenever a user explicitly asks to commit changes.
Discover DevOps skills, compare source repositories and read the instructions for each workflow.
Create a commit. Use whenever a user explicitly asks to commit changes.
When asked to create a pull request, follow these guidelines
When asked to commit the codebase, follow these guidelines
Sets up Jira MCP server integration for Claude Code. Use when setting up Jira, connecting to Atlassian, configuring MCP for ticket management, or adding Jira capabilities.
Creates well-formatted Claude Code skills from descriptions. Use when the user wants to create a new skill, generate a skill, or build a skill for a specific task.
Sets up Playwright MCP server integration for Claude Code. Use when setting up Playwright, browser automation, web testing, scraping, or adding browser control capabilities.
Expert in streamlining and enhancing the development of AI Agent Applications, including AI app / agent / workflow code generation, AI model comparison and recommendation, tracing setup, and evaluation planning...
Manage project dependencies across all apps. Use when installing, updating, or managing dependencies, or when user asks to install packages.
Deploy applications to Cloudflare Workers and/or Supabase Edge Functions. Supports unified multi-platform deployment. Use when deploying to production, publishing APIs/functions, or when user requests deploymen...
Deploy applications to Cloudflare Workers and/or Supabase Edge Functions. Supports unified multi-platform deployment. Use when deploying to production, publishing APIs/functions, or when user requests deploymen...
Manage project dependencies across all apps. Use when installing, updating, or managing dependencies, or when user asks to install packages.
Check and validate all required environment variables in .env file. Use when verifying environment setup or troubleshooting configuration issues.
Check and validate all required environment variables in .env file. Use when verifying environment setup or troubleshooting configuration issues.
This skill should be used when the user asks to "create a commit", "commit changes", "write a commit message", "make a commit", needs help with "conventional commits", or wants to understand commit message form...
Find relevant research and guide implementation based on it. Use when implementing features, fixing bugs, or exploring techniques where existing research in docs/research/ may provide guidance. Trigger phrases...
This skill should be used when the user asks to "use TDD", "write tests first", "test-driven", "add a test for", "fix bug with TDD", "implement using TDD", "red-green-refactor", or mentions developing features...
Search for Lean 4 and Mathlib theorems, lemmas, and definitions by type signature, name, or subexpression pattern. Use when the user asks to find a theorem, look up a Lean definition, search for lemmas, or need...
This skill should be used when the user asks to "refactor", "extract function", "rename", "improve code quality", "reduce duplication", or "remove code smell". Supports Lean 4 and general refactoring patterns.
This skill should be used when the user asks to "create an issue", "write an issue", "add an issue", "log an issue", "report a bug", "document a problem", or wants to track tasks, bugs, or feature requests as G...
Research web pages using agent-browser and summarize documentation or articles. Use when investigating URLs, checking page content, or summarizing documents.
Runs checks per AGENTS.md and writes the verification transcript to tasks/20_verification.md.
Refactors for readability after verification is green, re-running checks and updating 20_verification.md.
Enforce stage-by-stage implementation for multi-step task briefs. Use when acting as the implementor to deliver one stage at a time, pausing for explicit user confirmation before proceeding unless the user requ...
Creates a strict Task Brief and a handoff note using the tasks/ workflow.
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.