Loading...
Loading...
Found 284 Skills
Set up and run an autonomous experiment loop for any optimization target. Use when asked to start autoresearch or run experiments.
Use Gemini CLI to simplify the current pull request by safely reducing unnecessary scope, complexity, and noise while preserving the intended outcome.
Sync project state with Linear — detect gaps, consolidate objectives, clean up, route to next action
A comprehensive Git command assistant and workflow guide. Trigger whenever the user asks how to perform a specific Git operation, wants to know what a Git command does, needs help fixing a Git mistake, or wants guidance on Git best practices (like branching, rebasing, or squashing).
Automated release pipeline that merges main, runs tests, performs pre-landing review, bumps version, updates changelog, creates bisectable commits, and opens a pull request. Use this skill when the user says "ship it", "ship this", "release this", "prepare for release", "open a PR", "push and PR", "land this", "get this ready to ship", "create release", "/ship-workflow". Handles the full lifecycle from pre-flight checks through PR creation.
Initialize a new project — repo, structure, CI, and first commit
Create a pull request with Conventional Commits formatting, a templated body, and local verification. Use when the user asks to create a PR, open a PR, submit changes for review, or put code up for review.
Create pull requests using GitHub CLI with proper templates and formatting
Create an annotated Git tag to mark a project milestone, documenting achievements and next-phase plans. Use when completing a phase, releasing a version, or marking a research checkpoint with a structured summary.
Intelligently analyze code changes and split them into multiple logical commits based on functionality and change types. This skill should be used when users want to commit code changes, especially when there are multiple unrelated changes in the working directory.
Write systems code in the style of Linus Torvalds, creator of Linux and Git. Emphasizes pragmatic excellence, performance awareness, subsystem design, and uncompromising code review. Use when writing kernel-level code or high-performance systems.
Safely clean merged and stale git branches with explicit confirmations.