Claude-facing adapter to the canonical get-fable coding lifecycle. Use the root skill pack and registry as the semantic source of truth.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add imMamdouhaboammar/get-fable --skill get-fable --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Get Fable?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/immamdouhaboammar-get-fable-get-fable)More formats (shields.io, HTML) on the badges page.
---
name: get-fable
description: Claude-facing adapter to the canonical get-fable coding lifecycle. Use the root skill pack and registry as the semantic source of truth.
---
# get-fable Claude adapter
Do not maintain an independent workflow here.
Canonical sources:
- `skills/get-fable/SKILL.md`
- `skills/get-fable/registry.json`
- root `skills/fable-*/SKILL.md`
- root `AGENTS.md`
When direct canonical skill loading is unavailable, preserve the registry-v2 rules: route by missing evidence, keep broad work bounded, use test-first checks for testable behavior, keep delegation ownership explicit, distinguish review/security/release/handoff/eval jobs, record mutation freshness, and diagnose repeated failure before another repair.
Substantial completion requires passing completion-capable evidence for the current mutation generation. Research, receipts, and handoff records cannot substitute for behavior verification.
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!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
