Browse published AI skills maintained by kurko. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
32Repository stars across indexed skills
126Repository forks
81Average repository stars per indexed skill
4Repository stars may repeat across skills from the same repository.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web appl...
Copy text to the system clipboard. Use when user asks to copy something, send to clipboard, or similar requests.
Review technical recommendations before presenting them to the user. Use BEFORE suggesting config changes, optimizations, refactors, or architecture decisions. Spawns a subagent to challenge assumptions and fil...
Review pull requests and uncommitted code changes. Use when user asks to review a PR, review changes, review uncommitted code, review a diff, or similar code review requests. Activates for phrases like "review...
Enforce TDD when fixing bugs - write a failing test first, then make it pass. Use when about to fix a bug, correct broken behavior, or resolve an issue in production code. Activates for phrases like "let me fix...
Skill on how to write a task. Use when user asks you to write a task (for Asana, Linear, Jira, Notion and equivalent). Also activates when user says "create task", "write task", or similar task creation workflo...
Write Ruby on Rails specs with RSpec following best practices for unit tests, request specs, feature specs, and job specs. Use when writing or modifying RSpec test files for Rails applications.
Stage and commit git changes with conventional commit messages. Use when user wants to commit changes, or asks to save their work, even when committing your own work after completing a task. Also activates when...
Use when the user asks you to interact, work, read, create or update tasks in ai-notes/**/*/todo.{md,txt} files, or when user asks you to look at the "todo file".
Read files with context-aware summarization. Use when managing large documents efficiently.
Create or improve agents following templates. Use when building company roles, consultants, or hub agents.
Review code for quality, correctness, and standards. Use before commits or when reviewing PRs.
Coordinate multi-agent discussions to reach decisions. Use when 2+ agents deliberate or for board meetings.
Master axiom loader - load this for all agents. Includes all foundational principles.
Create or improve Claude Code skills. Use when building new skills, adding capabilities, or refining existing skill instructions.
Tier 0 decision principles - load always. Defines how we think and decide.
Foundational principles for all agents - load always. Defines how we work together.
Create Product Requirements Documents. Use when defining requirements for a feature or product.
Create vision documents for features, products, or company direction. Use when starting something new.
Decompose complex problems with structured reasoning. Use for ambiguous problems, exploring perspectives, or reducing bias.
Structure documents with TLDR-first format. Use when creating any document, PRD, vision doc, or decision record.
Break PRDs into user stories with acceptance criteria. Use when preparing work for development.
Interact with project management tools (Linear, Asana, Jira). Use when creating tasks or syncing status.
Prioritize and organize work into actionable backlog. Use when preparing tasks for execution.
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.