From wtf
Interrupts ongoing tasks to summarize original request, actions taken so far, next steps, end goal, and confidence level. Triggers on phrases like 'wtf are you doing' or 'what's the plan'.
How this skill is triggered — by the user, by Claude, or both
Slash command
/wtf:are-you-doingThis 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 has hit the brakes. They want to know what's happening, what the plan is, and whether any of this makes sense before letting the agent continue.
The user has hit the brakes. They want to know what's happening, what the plan is, and whether any of this makes sense before letting the agent continue.
Take stock of the current state. Review the conversation to identify:
Lay it all out honestly:
**The Original Ask:** [What the user wanted]
**What I've Done So Far:**
- [Action 1 — and why]
- [Action 2 — and why]
**What I Was About To Do:** [Next planned step]
**The End Goal:** [What "done" looks like from here]
**Confidence Level:** [Honest assessment — am I on track or wandering?]
$ARGUMENTS ask about a specific aspect, focus the explanation there.npx claudepluginhub pacaplan/wtf --plugin wtfSummarizes recent verbose agent activity (tool calls, file changes, decisions) into Mission, Result, Wasted effort, Status format. Triggers on 'wtf did you say', 'tldr', 'summarize what you did'.
Makes completion state obvious at the end of every Claude Code response using a red/yellow/green status block convention.
Clarifies vague user requests via iterative Q&A loop and parallel subagent codebase exploration. Outputs scoped context brief for precise planning. Triggers on 'I want to...' or ambiguous scopes.