CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-design

AI design specialist skill with DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance. Covers typography, color systems, motion design (motion/react, GSAP, Three.js), responsive-first layouts, and accessibility (WCAG 2.2).

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/runs/oma/.agents/skills/oma-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is strongly actionable with concrete design guardrails, explicit validation checkpoints, and well-signaled one-level-deep references, but it carries significant removable scaffolding (SSL-primitive tables, scheduling boilerplate) and inconsistent resource organization. Trimming the meta-workflow sections and consolidating the duplicated resource listings would materially improve token efficiency.

Suggestions

Remove or collapse the 'Scheduling'/'Intent signature'/'Logical Operations' scaffolding (including the SSL-primitive table), which restates the workflow in non-operational jargon — the Scenes/Canonical path sections already cover it.

Consolidate the '### Resources' and '## References' lists into one section with a consistent directory name ('resources/' vs 'reference/' vs 'examples/' are currently mixed), and drop the inline Anti-Pattern Quick Reference since resources/anti-patterns.md already holds the full catalog.

Fix heading levels so Typography/Color/Layout/Motion/Components nest under the Anti-Pattern Quick Reference heading instead of sitting as siblings, and introduce the 7 phases before guardrail #1 references 'Phase 1 (Setup)'.

DimensionReasoningScore

Conciseness

Concrete content (exact font stacks, timing budgets, DO/DON'T lists) is diluted by meta-scaffolding that adds tokens without operational value, such as the 'Scheduling'/'Intent signature' boilerplate and the 'Logical Operations' table mapping actions to invented 'SSL primitives' (READ, INFER, CALL_TOOL).

3 / 5

Actionability

Provides mostly executable guidance: exact system font stack, CJK font priority order, 375px minimum, 150ms/200-500ms/800ms motion budgets, a runnable `bunx getdesign@latest list` command, and a copy-pasteable '## Reference Sites' markdown snippet; minor gaps remain (no inline DESIGN.md template or shadcn install example).

4 / 5

Workflow Clarity

Sequencing is explicit (PREPARE→FINALIZE scenes, canonical path, 7-phase summary) with a VERIFY phase and real feedback loops ('If accessibility checks fail, revise before handoff'; vendor-fetch retry/continue/abort with default), but three parallel restatements of the same workflow and a forward reference to 'Phase 1 (Setup)' before phases are introduced create minor ambiguity.

4 / 5

Progressive Disclosure

Detailed material is appropriately split into clearly labeled, one-level-deep references with per-file descriptions, but the inline Anti-Pattern Quick Reference duplicates resources/anti-patterns.md, two separate resource lists use inconsistent directory names ('resources/' vs 'reference/'), and no bundle files are present in the skill directory to verify the referenced paths resolve.

4 / 5

Total

15

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and reasonably distinctive with good natural keyword coverage, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause naming design-system creation, DESIGN.md audits, and typography/color/motion decisions would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a design system, DESIGN.md creation or audit, typography/color/motion direction, or an accessibility/anti-pattern review of UI work.'

Include the phrase 'design system' and common synonyms ('UI design', 'visual direction') in the description so natural user phrasing matches the skill.

Lead capabilities with concrete third-person verbs ('Creates, audits, and revises DESIGN.md...') instead of noun-phrase domains.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('DESIGN.md management, anti-pattern enforcement, optional Stitch MCP integration, and component library guidance') with specific coverage areas (WCAG 2.2, GSAP, Three.js), but they are named as domains rather than concrete actions, leaving minor gaps.

4 / 5

Completeness

The 'what' is clear and multi-part, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Natural terms users would say are present ('typography', 'color', 'motion', 'accessibility', 'DESIGN.md', 'responsive'), but common phrasings like 'design system', 'UI', and synonyms such as 'a11y' or 'visual' are missing.

4 / 5

Distinctiveness Conflict Risk

Distinctive markers like 'DESIGN.md', 'Stitch MCP', and 'anti-pattern enforcement' carve a clear niche, though the broad term 'design' leaves minor overlap risk with generic frontend/UI skills.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
first-fluke/oh-my-agent
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.