Use when work spans multiple sessions, has dependencies or blockers, or needs context that survives conversation compaction
2
AI 84
agent-browser
mraakashshah2/21/2026
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web a...
1
AI 94
systematic-debugging
mraakashshah2/21/2026
Use when encountering any bug, test failure, or unexpected behavior -- before proposing fixes
1
AI 93
git-commits
mraakashshah2/21/2026
Use when creating git commits -- determines type, scope, and message from staged changes
1
AI 92
workflow-routing
mraakashshah3/4/2026
Use when a user request arrives and the appropriate workflow or skill chain is not immediately obvious
1
AI 90
github
mraakashshah3/4/2026
Use when interacting with GitHub issues, PRs, CI runs, or the GitHub API via the gh CLI
1
AI 88
finishing-work
mraakashshah3/4/2026
Use when implementation is complete and all tests pass -- guides verification, integration options, and cleanup
1
AI 88
using-skills
mraakashshah3/4/2026
Use at the start of any task to check which skills might apply -- even 1% chance means invoke the skill
1
AI 88
verification-before-completion
mraakashshah3/1/2026
Use when about to claim work is complete, fixed, or passing -- before committing, creating PRs, or marking tasks done
1
AI 88
dispatching-parallel-agents
mraakashshah2/21/2026
Use when facing 2 or more independent tasks that can be worked on without shared state or sequential dependencies
1
AI 88
review-implementation
mraakashshah2/21/2026
Use when implementation phase is complete -- verifies code matches spec, identifies gaps, and tracks completion state
1
AI 88
create-handoff
mraakashshah3/15/2026
Use when ending a session, switching context, or needing to transfer work state to another session or agent
1
AI 87
tmux
mraakashshah2/21/2026
Use when you need an interactive TTY for REPLs, long-running processes, or orchestrating multiple coding agents in parallel
1
AI 87
executing-plans
mraakashshah3/4/2026
Use when you have a written implementation plan to execute, with review checkpoints between tasks
1
AI 85
completion-check
mraakashshah2/21/2026
Use when infrastructure or features are built but before declaring done -- verifies work is wired into the system and actively used
1
AI 83
refactor
mraakashshah3/4/2026
Use when improving existing code structure without changing behavior, after tests are green
1
AI 82
review-docs
mraakashshah3/15/2026
Use after code changes land -- checks documentation for staleness, contradictions, and missing coverage
1
writing-skills
mraakashshah2/21/2026
Use when creating new skills, editing existing skills, or verifying skills work
