Claude Skills by jjilli

Battle-tested engineering patterns and seam traps distilled from long multi-round fable-flow builds. Consult when planning tracks, implementing a track, or reviewing — especially for the recurring integration failure (tests green per track, broken where tracks or the live runtime meet), the reusable patterns that make later rounds cheaper (provider-adapter, enqueue-only worker, guarded migration, invariant validators), and the verification discipline that a green test suite alone does not giv...

Reference for prompting Claude Fable 5 — how Fable prompting differs from Opus/Sonnet-era prompting, effort-level selection, and the verbatim steering snippets. Use when writing or editing prompts, subagent definitions, or slash commands that target Fable 5, or when a Fable-driven pipeline misbehaves (overplanning, over-asking, unverified progress claims, unrequested refactors).

How to make frontends that look genuinely designed instead of generic "AI slop", and how to verify UI work the pipeline can't catch with a test suite. Load whenever a task builds or restyles a user-facing surface — a page, a component, a full redesign, a dashboard, a marketing site. Covers distinctive typography, committed color, atmosphere, one orchestrated motion, information architecture for "anyone can use", and visual verification via a headless-browser screenshot.

Relentless, one-question-at-a-time interview that stress-tests a plan or design before any code is written. Invoke ONLY when the user explicitly asks for it — they say "grill me", "grill the plan", "grilling", or otherwise ask to be grilled / to pressure-test the design. Do NOT auto-invoke it for ordinary planning or clarification; the default new-project brainstorm (card-based multiple-choice questions) is a separate, lighter thing. This is the opt-in deep interrogation.