PolymathWizard/BHIL-HELM-Sci-Fi-Visualizer
35 stars · Last commit 2026-08-28
Sci-fi dashboard framework for Claude Code. Profile data, match a design language, build a single-file HTML mockup with real bindings, QA it against WCAG AA and an IP checklist, gate it SHIP/HOLD/REWORK. 15 token sets, 4 subagents, 6 slash commands, stdlib-only validators. MIT + CC BY 4.0.
README preview
# BHIL-HELM  **Heuristic Engine for Layered Mockups.** Turn client data into eye-catching, functional, Claude Code friendly interactive dashboards styled in science-fiction design languages. Evidence-tiered. IP-clean. Regenerable. [](LICENSE) [](LICENSE-CONTENT) Read [ABOUT.md](ABOUT.md) for the full story of the framework, or open the [visual reference pack](research/reference-pack/README.md) that the catalog was distilled from. Fictional user interfaces are the most effective communication design under time compression ever produced: a film screen has one second to read as complex and clear. HELM keeps that discipline and strips the tropes that make screen UIs anti-usable in real products. The result is a dashboard that serves a decision, looks like a command surface, and can be rebuilt by the client's own Claude Code without the lab in the loop.  *The starter build. Tactical HUD language, wall-display density, SYNTHETIC badge, evidence labels on the STATED target and the INFERENCE metric, shape-coded status rail, decorative ambient stream. Rendered without the CDN to show the inline fallback.* ## Sample dashboard library These ten panels are BHIL concept renders: launch imagery that shows the target fidelity HELM aims at, not builds produced by the pipeline. Each is annotated with the data shape it represents, the matching rule that would fire, and the decision question a HELM build of it would have to answer. Any brand marks, platform names, and faces inside the renders are illustrative placeholders. Full-resolution PNGs are in `assets/samples/`.