hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-design
hyper-design
Verified[Hyper] Use this skill when the user wants interface design work that must not look AI-generated - designing a new screen, page, or component, restyling an existing UI, building faux product UI for a hero, feature card, or demo, or auditing, cleaning, or verifying generic template patterns in an interface - driven by a written design direction, a numeric craft floor, static detection, and evidence-separated review, with briefs and reports saved under `.hyper/design/[slug]/`. Do not use it for backend or data work with no visual surface, accessibility-only or performance-only QA, brand strategy with no interface, or a reusable skill folder.
references/eval-rubric.md
View on GitHub# Evaluation Rubric
Use this reference when adding, reviewing, or interpreting `assets/evals/` cases.
## Detector oracle
Each detector rule needs a minimal positive fixture and a false-positive guard fixture. Assert only observable machine output:
- rule ID, source location, severity, engine, and evidence kind
- candidate exception status when explicit local context supports it
- absence of a finding when a fixture is meant to prove a guard
- stable summary counts only when unrelated rule additions cannot change them
Do not grade whether a source match proves visual quality, accessibility conformance, product fit, or AI authorship.
## Workflow oracle
Workflow JSONL cases cover trigger, mode, protected contracts, browser capability fallback, and unsafe requests. Every case must state the required action and forbidden outcome. Keep established cases; add a regression whenever a real failure appears.
## Human sampling
Before promoting a static rule to `P1` or an immediate tier, inspect at least five relevant and five exception-like examples. Record confirmed, false-positive, and ambiguous outcomes. A rule with more than 10% false positives in the reviewed sample remains review-only or is removed.
## Result boundaries
- Static detector output proves source signatures only.
- Rendered evidence requires a valid browser handoff capture.
- Screenshot evidence does not prove keyboard, semantic, accessibility, or task completion.
- `generic-output risk` is a prioritization label, never a claim of AI authorship.
## Sources
> Claims checked 2026-09-21. No external source was used in this file.
The detector, workflow, and human-sampling criteria are this package's own. The 10% false-positive threshold and the five-example sample size are values this package chose, not external guidance.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |