From wtf
Triages project issues like build/test failures, merge conflicts, uncommitted work, stale branches, and delivers prioritized action plans with concrete steps when stuck or overwhelmed.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wtf:should-i-doThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
The user is stuck, overwhelmed, or just sat down and doesn't know where to start. Assess the situation and give them a concrete action plan.
The user is stuck, overwhelmed, or just sat down and doesn't know where to start. Assess the situation and give them a concrete action plan.
Assess the current state. If $ARGUMENTS describe the situation or point to something specific (a PR, a branch, a project), start there and gather context accordingly. Otherwise, run a quick local reconnaissance: git status, recent changes, failing tests, error output in the conversation — whatever's relevant.
Identify all the problems. Catalog everything that needs attention:
$ARGUMENTSTriage and prioritize. Not all problems are equal:
Deliver the action plan:
**Situation Assessment:** [One sentence — how bad is it, really?]
**The Triage:**
1. [BLOCKING] [First thing to fix — with specific command or action]
2. [URGENT] [Second priority — concrete next step]
3. [IMPORTANT] [Can wait but shouldn't wait long]
4. [NOISE] [Things to ignore for now, and why]
**Start Here:** [The literal first command to run or action to take]
pytest tests/test_auth.py — the fixture is missing a mock" is.git add away from being done" is more useful than a triage list.npx claudepluginhub pacaplan/wtf --plugin wtfAnalyzes git status, PRDs, feature trackers, and work orders to identify next development task and resume work via TDD workflow.
Investigates and resolves GitHub issues with systematic triage, root cause analysis, test-driven fixes, and pull request management. Use when given an issue ID or URL.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.