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.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 a lean, well-structured design reference that respects Claude's competence, but it leans heavily on abstract principles and maxims over concrete, executable guidance, and offers only an implicit before/after process rather than a sequenced workflow. It is genuinely useful as opinionated guidance but less actionable than a skill of this scope could be.

Suggestions

Add concrete, copy-paste-ready specifics under Visual Design — e.g., named characterful font pairings, example CSS-variable palette skeletons, or a minimal staggered-reveal keyframe snippet — so the directives become executable rather than aspirational.

Tighten the loose before/after shape into an explicit mini-workflow with a checkpoint, e.g., 'Before coding: lock Purpose/Tone/Constraints/Differentiation. After: run The Test — only ship if every element serves the purpose.'

Trim inspirational aphorisms ('Timid middle ground does not.', 'No two designs should converge on the same choices.') or convert them into concrete do/don't pairs to raise token efficiency.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — it never explains basics (what CSS variables, fonts, or APIs are) and uses tight bullets and bold labels. A few aphoristic lines ('Timid middle ground does not.', 'No two designs should converge on the same choices.') are inspirational rather than instructional and could be trimmed, matching 'efficient; minor instances of over-explanation' (4) rather than the fully lean 5.

4 / 5

Actionability

Concrete nuggets exist ('Avoid defaults (Arial, Inter, Roboto, system fonts)', 'Use CSS variables for consistency', 'Prioritize CSS-only solutions', 'If one endpoint uses create, don't use add elsewhere') but the bulk is abstract maxim ('create atmosphere and depth', 'Unexpected layouts. Asymmetry. Overlap.', 'fight generic AI aesthetics') without specific execution steps. This fits 'some concrete guidance but incomplete; missing key details' (3), above the high-level-hints-only 2 because of the named specifics.

3 / 5

Workflow Clarity

A loose before/after shape exists (the numbered 'Design Thinking' considerations to commit to a direction, then 'The Test' questions to ask after designing), but it is a reference/checklist rather than a sequenced workflow, and validation checkpoints are implicit rather than explicit. Matches 'sequence present but checkpoints missing or implicit' (3); not a single-action skill so the simple-skill 5 does not apply.

3 / 5

Progressive Disclosure

Well-organized with clear headers and subsections (Overview, Design Thinking, Visual Design with five labeled sub-parts, API Design, System Design, The Test, See Also) and one-level-deep cross-skill references in 'See Also'. At ~80 lines it exceeds the 'under 50 lines' auto-5 threshold, so it lands at 'good structure; most content appropriately placed; minor organization gaps' (4) rather than 5.

4 / 5

Total

14

/

20

Passed

Description

81%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 excels at trigger-term coverage and explicitly answering both what and when, with strong natural phrasing. Its main weakness is specificity — the capability is framed abstractly as 'design thinking' rather than as concrete actions the skill performs.

Suggestions

Replace or augment the abstract 'Intentional design thinking' framing with concrete verbs describing what the skill does, e.g., 'Crafts intentional visual, structural, and interaction decisions for UIs, APIs, and systems.'

Narrow the broadest triggers ('design an API', 'design a system') or qualify them to reduce overlap with general coding/architecture skills, e.g., 'design an API's interface and naming conventions'.

DimensionReasoningScore

Specificity

The stated capability is 'Intentional design thinking for interfaces, components, and systems' — it names the domain clearly but the action ('design thinking') is abstract rather than a concrete operation, and the listed verbs (build/design/create) describe user requests rather than what the skill does. Closer to 'names the domain but actions are minimal/generic' (2) than to 'names domain and 1-2 concrete actions' (3), since no concrete skill-performed actions are enumerated.

2 / 5

Completeness

Explicitly states what the skill does ('Intentional design thinking for interfaces, components, and systems') and when to use it ('Use when the user asks to...') with concrete trigger phrases, satisfying both the 'what' and 'when' at the top anchor.

5 / 5

Trigger Term Quality

Includes highly natural user phrases with synonym variation — 'build a UI', 'design a page', 'create a component', 'make this look good', 'design an API', 'design a system' — comprehensively covering how users actually request design help, matching the 'comprehensive coverage including synonyms' anchor.

5 / 5

Distinctiveness Conflict Risk

Largely distinct via aesthetic triggers ('build a UI', 'make this look good'), but 'design an API' and 'design a system' are broad and could overlap with general architecture/coding skills, giving minor overlap risk — matching 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict 5.

4 / 5

Total

16

/

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.

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.