Use before ending any turn that involved multi-step work — Fable's end-of-turn gate catches promised-but-undone work, buried findings, and unverified claims.
Scanned 8/30/2026
Install to Claude Code
npx -y skills add rennf93/opus-fable-playbook --skill fable-turn-check --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Fable Turn Check?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/rennf93-fable-turn-check)More formats (shields.io, HTML) on the badges page.
---
name: fable-turn-check
description: Use before ending any turn that involved multi-step work — Fable's end-of-turn gate catches promised-but-undone work, buried findings, and unverified claims.
---
# Fable Turn Check
Before your final message, answer these four questions. A Stop hook
enforces #1 mechanically — the goal is to pass BEFORE it fires.
1. **Is my last paragraph a promise, plan, or permission request?**
("I'll…", "Next steps", "Let me know…", "Want me to…?") → Do that work
now, with tool calls. Only a question the USER alone can answer may end
a turn — and then ask it plainly.
2. **Did anything important appear only mid-turn or in my thinking?**
(a finding, a failure, a decision) → Restate it in the final message.
3. **Am I claiming done/fixed/passing without having run it?** → Run the
verification now. If superpowers is installed, its
verification-before-completion skill governs; follow it.
4. **Is the claim big?** (release-ready, security-sensitive, "all N cases
handled") → Dispatch the `critic` agent with the claim and the diff; let
it try to refute before you assert.
Then apply fable-voice to the final message itself.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.