CtrlK
BlogDocsLog inGet started
Tessl Logo

design

Intentional design thinking for interfaces, components, and systems. Use when the user asks to "build a UI", "design a page", "create a component", "make this look good", "design an API", "design a system", or any task where aesthetic or structural design decisions matter.

75

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The body is concise, directive, and well-sequenced with explicit pre/post design checkpoints, making it a strong instruction-only skill. Its main gap is progressive disclosure: everything lives inline with no reference files to offload detail.

Suggestions

Move detailed Visual Design or API/System Design guidance into reference files (e.g., VISUAL.md, API.md) and link them one level deep from the overview.

Add one or two concrete worked examples (a sample font pairing or palette) to lift actionability from directive to copy-paste ready.

DimensionReasoningScore

Conciseness

The body is lean directive prose ("Commit to a cohesive palette", "Never default to flat solid backgrounds") with no padding or explanations of concepts Claude already knows; not 2 because nearly every line instructs rather than over-explains.

3 / 3

Actionability

For an instruction-only skill the guidance is concrete and actionable with specific do/don't directives ("Pair a display font with a refined body font", "If one endpoint uses `create`, don't use `add` elsewhere"); not 2 because directives are specific rather than vague, though it lacks worked examples.

3 / 3

Workflow Clarity

Provides a clear pre-implementation sequence (Purpose, Tone, Constraints, Differentiation) and a post-design validation checkpoint ("The Test" with four questions) forming a feedback loop; not 2 because validation is explicit rather than implied.

3 / 3

Progressive Disclosure

The content is well-organized into clear sections with a See Also for navigation, but it is a single ~80-line inline file with no bundle files splitting detail into one-level-deep references; not 3 because content that could be separate (detailed Visual/API guidance) is inline.

2 / 3

Total

11

/

12

Passed

Description

92%

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 strong, third-person, and clearly pairs a what-statement with an explicit "Use when" trigger clause backed by many natural user phrases. Its only weakness is the broad scope, which raises some overlap risk with adjacent skills.

Suggestions

Narrow the trigger scope or add disambiguating language to reduce overlap with naming/architecture/review skills.

Consider dropping the most generic trigger ("make this look good") in favor of more design-specific phrasings.

DimensionReasoningScore

Specificity

Lists multiple specific concrete triggers such as "build a UI", "design a page", "create a component", "design an API", and "design a system", matching the anchor for several concrete actions; not 2 because the set is comprehensive rather than partial.

3 / 3

Completeness

Explicitly answers what ("Intentional design thinking for interfaces, components, and systems") and when via an explicit "Use when the user asks..." clause; not 2 because the when is explicit rather than implied.

3 / 3

Trigger Term Quality

Quotes natural phrases a user would actually say ("build a UI", "make this look good", "design a page") giving good coverage of common variations; not 2 because it spans multiple natural phrasings rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

The design niche is fairly distinct but the breadth across interfaces, components, systems, and APIs plus broad triggers like "make this look good" could overlap with naming, architecture, or review skills; not 3 because it is not a tight, conflict-free niche.

2 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tslateman/duet
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.