jupes/agent-forge-harness / .agents/skills/ui-originality-criteria
ui-originality-criteria
VerifiedEvaluate or guide UI design through coherence, originality, craft, and usability. Use during visual design or product UI review.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.7 KB |
SKILL.md
View on GitHub---
name: ui-originality-criteria
description: Evaluate or guide UI design through coherence, originality, craft, and usability. Use during visual design or product UI review.
---
# ui-originality-criteria
Use when **building or reviewing** user-visible UI (marketing pages, dashboards, app shells, flows). Encodes the four grading dimensions from [Anthropic — Harness design for long-running application development](https://www.anthropic.com/engineering/harness-design-long-running-apps) so subjective quality stays **gradable** and **anti-“AI slop”**.
Pair with `.claude/protocols/evaluation-rubric.md` for harness-wide severity (BLOCKER / HIGH / …); this skill is the **product-design lens**.
---
## The four dimensions
### 1. Design quality (coherent whole)
**Question:** Does the layout feel like one intentional system—not a pile of unrelated components?
**Strong:** Color, type, spacing, imagery, and motion share a clear mood; hierarchy tells a single story.
**FAIL signals:** Mismatched radii/shadows; competing focal points; “default component” look with no unifying thread.
---
### 2. Originality (deliberate choices)
**Question:** Would a human designer see **custom decisions**, or stock templates / library defaults / clichéd AI patterns?
**Strong:** Distinct typography pairing, palette, or layout rhythm tied to the product’s domain.
**FAIL signals:** Unmodified stock cards; purple-on-white hero gradients “because SaaS”; generic three-column icon grids with lorem tone; interchangeable with ten other AI landing pages.
---
### 3. Craft (technical execution)
**Question:** Are fundamentals solid—type scale, spacing rhythm, contrast, alignment?
**This is competence, not creativity.** Most honest implementations pass unless something is broken.
**FAIL signals:** Illegible contrast; broken hierarchy; ragged grids; tap targets too small; obvious misalignment.
---
### 4. Functionality (usability without relying on beauty)
**Question:** Can a user understand what the UI does, find primary actions, and complete tasks without guessing?
**FAIL signals:** Hidden primary actions; misleading labels; dead ends; keyboard traps; unclear empty/error states.
---
## Weighting (from the article)
When **both** generator and evaluator see these criteria, bias feedback toward **design quality** and **originality** first—Claude often scores **craft** and **functionality** well by default. Use **craft** and **functionality** as hygiene gates, not as excuses to ship bland work.
---
## Generator rules
1. Pick **one** clear visual metaphor (e.g. “mission control”, “workshop”, “terminal calm”) and thread it through nav, surfaces, and accents.
2. Choose patterns that fit the audience, brand, and task; justify distinctive choices through usability rather than novelty alone.
3. After a first pass, self-check against all four bullets in writing before requesting evaluator review.
---
## Evaluator rules
1. **Assume** generic patterns until disproven—require evidence (screenshots, DOM notes, contrast checks).
2. Cite **which dimension** each finding belongs to.
3. If UI-heavy AC exists, treat **Originality** + **Design quality** gaps as at least **HIGH** when the spec asked for a distinctive or branded experience.
---
## References
- Anthropic article (full context): https://www.anthropic.com/engineering/harness-design-long-running-apps
- Harness evaluator rubric: `.claude/protocols/evaluation-rubric.md`
- Example dashboard applying this lens: `docs/index.html` (Agent Forge static dashboard — NASA retro / space-console theme)
## Completion
Assess all four dimensions against the rendered UI and audience. Each finding cites observable evidence and a practical correction; record untested states.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |