CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-design

Define or review a visual system, DESIGN.md, or redesign direction. Use for typography, layout, color, motion, and interaction design decisions.

57

Quality

64%

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 ./skills/oma-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 skill body is a well-structured overview with notably concrete guardrails and explicit failure-recovery branches, but it duplicates its own trigger information across multiple sections and keeps its main workflow at a high altitude, deferring operational detail to reference files. Progressive disclosure is good in principle, though the resources/ vs reference/ split is confusing and no bundle files exist to verify the referenced paths.

Suggestions

Consolidate the duplicated trigger content — "Intent signature", "When to use", and the frontmatter description all restate the same triggers; keep one.

Make validation checkpoints executable: name the concrete checks in "run the design checklist" and "Phase 6 mechanical checks" instead of pointing at external files, or inline a short version of the checklist.

Unify the reference directories (merge "reference/" into "resources/" or rename one) and link the reference paths so navigation is unambiguous, and ship the referenced files in the bundle so the pointers resolve.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and the guardrails are dense, but trigger information is repeated across "Intent signature", "When to use", and the frontmatter, and sections like "Control-flow features", the "Resource scope" table, and the outputs YAML block are process metadata rather than instruction. It is not a 2 because there is no concept-explanation padding, and not a 4 because the duplicated trigger lists and metadata sections could be noticeably tightened.

3 / 5

Actionability

Some guidance is genuinely concrete — the exact system font stack, the CJK priority order "Pretendard Variable > Noto Sans CJK > system-ui fallback", the semantic color naming example, and the executable `bunx getdesign@latest list` command. However the core workflow steps are abstract ("Inspect relevant existing context", "Use the chosen direction") and only one command appears in the entire body, with most operational detail deferred to reference files that are not present in the bundle.

3 / 5

Workflow Clarity

Entry, Transitions, Failure and recovery, and Exit give a clear sequence with explicit recovery branches ("If vendor seed fetch fails, choose retry, continue without seed, or abort"; "If accessibility checks fail, revise before handoff"; "If design context is insufficient, ask for one focused clarification"). It falls short of 5 because checkpoints like "run the design checklist" and "audit against them in Phase 6" are pointers to external content rather than explicit validation steps.

4 / 5

Progressive Disclosure

The References section lists twenty files, each with a one-line purpose label (e.g., "resources/redesign-protocol.md: existing-site redesign"), which is well-signaled and one level deep. It is not a 5 because the paths split confusingly between two similarly named directories ("resources/" and "reference/"), the references are plain text rather than links, and the Scheduling metadata (intent signature, expected inputs/outputs) is inline content that could live elsewhere or be trimmed.

4 / 5

Total

14

/

20

Passed

Description

70%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 concise, uses third person, and answers both what and when with an explicit "Use for" clause. Its main weakness is thin action coverage — "define or review" undersells the skill's actual operations — and a few missing natural trigger synonyms.

Suggestions

List more concrete actions to raise specificity, e.g., "Define or review a visual system, create or audit DESIGN.md, select typography and color, and direct redesigns."

Add high-frequency trigger synonyms such as "design system", "UI audit", "brand style", and "accessibility review" to the when-clause.

State the trigger phrasing as user requests ("Use when the user asks for...") to make the when-clause fully explicit.

DimensionReasoningScore

Specificity

"Define or review" are only two fairly generic actions, even though the objects are concrete ("visual system, DESIGN.md, or redesign direction"). This matches the anchor for naming the domain with 1-2 concrete actions; a 4 would require several distinct specific actions such as auditing, creating, or selecting typography.

3 / 5

Completeness

The what is clear ("Define or review a visual system, DESIGN.md, or redesign direction") and the when is explicit ("Use for typography, layout, color, motion, and interaction design decisions"). It is not a 5 because the when-clause lists topics rather than concrete user trigger phrases (e.g., "Use when the user asks for...").

4 / 5

Trigger Term Quality

"typography, layout, color, motion, and interaction design" plus "redesign" and "DESIGN.md" are natural terms users would say, giving good keyword coverage. It falls short of 5 because common synonyms like "design system", "UI", "brand", or "accessibility" are missing.

4 / 5

Distinctiveness Conflict Risk

"DESIGN.md" and "visual system... redesign direction" establish a clear niche with distinct triggers, but broad design language ("layout, color, interaction design") creates minor overlap risk with frontend-implementation or general design-adjacent skills, so it is not a 5.

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.