Fable

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

Make your AI coding tools work as one team. Orchestrate jobs across Claude, Codex, Cursor, Devin, local models, and more. Carry your setup + context, track every cost.

Create an AI friend and build things together!

Master prompts to make Claude (and other AI models) review code for security, performance, accessibility, usability and quality — language-agnostic, with add-ons for 18+ stacks. Bilingual EN/ES.

Claude Code skill: Fable 5.1 decides, Opus 5 / Sonnet 5 / Haiku 4.5 execute. Five wiring patterns (advisor, architect+delegate, agent teams, workflows, /goal), effort routing, fallback traps, 16-block prompt kit, pinned agent lanes.

Claude Code skill that clones Fable 5's reasoning habits — the playbook Fable wrote about itself. A/B validated: 20/20 convergence, blind-judge parity. One-line install.

Autonomous high-reasoning operating mode for Claude Code — Fable 5's working behaviors as a drop-in skill

Claude Code skill + verifier for running Fable 5 background subagents: avoid silent Opus fallback, verify the real model, and structure slow hard work.

Personal agent operating system

Claude Code plugin installing the Fable Way working discipline: a Stop-hook calibration gate (done-claims must carry their evidence ledger), runner skills for scope/debug/review/verify/ship, and self-building per-project memory (.fable/). Built for Opus/Sonnet

Field-tested operating layer that transfers Claude Fable 5's working discipline to Claude Opus 4.8 via project instructions — with the eval harness that validated it (4 rounds, 46 artifact-verified runs).

Unlock the hidden Claude Fable 5.1 model on macOS

Make Opus work like Claude Fable 5 - a Claude Code plugin that injects Fable's working doctrine at session start, with per-task playbooks.

Agent skill for writing outcome-led Claude and Fable prompts for frontend design, UI/UX, image-to-code, and screenshot-led iteration.