CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

design-extract

Extract design tokens (color / typography / spacing) from imported source code, screenshots, or Figma exports into the canonical token bag token-map consumes.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/atoms/design-extract/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 tight, well-structured spec: concrete input enumeration, an exact output contract with a worked schema example, explicit convergence criteria, and genuinely useful anti-patterns. The only notable gaps are the unspecified screenshot-extraction path and the absence of a recovery loop for malformed sources, plus a little design-rationale padding in the intro.

DimensionReasoningScore

Conciseness

The body is lean with no explanation of concepts Claude already knows, and the output schema and anti-patterns earn their tokens. Minor trimmable padding: the 'Spec §10 / §21.3.2' pointers and the rationale sentence 'the input shape is intentionally generic so the same atom serves both code-migration and figma-migration' read as design justification rather than instruction — one notch below 'every token earns its place'.

4 / 5

Actionability

A fully concrete I/O contract: exact output path and directory tree, a complete JSON entry schema with example values, and concrete anti-patterns with real syntax ('color: #fff' in JSX, deduping 'bg-blue-500' vs 'bg-blue-600'). Minor gap: screenshot input is listed but never specified, keeping it below fully executable anchor 5.

4 / 5

Workflow Clarity

Clear sequence of Inputs -> Output -> Convergence, and the Convergence section is an explicit validation checkpoint ('completes when code/tokens.json exists'; empty bags emit a warning and downstream handling is specified), which handles the batch-scan case. Missing an explicit fix/retry loop for malformed or unparseable sources keeps it below anchor 5.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the body is under 50 lines with clean, well-labeled sections (Inputs, Output, Convergence, Anti-patterns, Status). Per the rubric's simple-skill note, well-organized sections with no need for external references score 5.

5 / 5

Total

17

/

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 concise and specific, naming concrete token kinds, input sources, and the downstream consumer. Its main weakness is the absence of an explicit 'Use when...' trigger clause and of common synonyms (theme, CSS variables, Tailwind) that users would naturally say. Distinctiveness is good given the niche pipeline context.

Suggestions

Append an explicit trigger clause, e.g. 'Use when migrating a codebase's styles, importing a Figma theme, or when token-map needs a token bag from scattered CSS/Tailwind/SCSS sources.'

Add natural synonyms users would say, such as 'theme', 'CSS variables', 'Tailwind config', and 'design system', to improve trigger term coverage.

Sharpen the 'what' with one more concrete action verb (e.g. 'scan and dedupe') so the capability list reads as multiple specific actions rather than a single parameterized one.

DimensionReasoningScore

Specificity

One concrete, well-parameterized action ('Extract design tokens (color / typography / spacing) from imported source code, screenshots, or Figma exports into the canonical token bag') with concrete token kinds and source formats. Not a list of multiple distinct actions (anchor 5), but clearly above the '1-2 concrete actions, not comprehensive' anchor 3.

4 / 5

Completeness

A clear 'what' (extract tokens into the canonical token bag) plus an explicit 'when' surface ('from imported source code, screenshots, or Figma exports'), but the 'when' is source-listing rather than a trigger phrase like 'Use when...', which keeps it below the anchor-5 example. It sits above anchor 3 because the source enumeration does convey usage context explicitly.

4 / 5

Trigger Term Quality

Good natural keywords: 'design tokens', 'color', 'typography', 'spacing', 'Figma', 'screenshots', 'source code'. Missing common variations users would say, e.g. 'theme', 'CSS variables', 'Tailwind config', or file extensions — matches 'good keyword coverage; a few natural terms missing'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (token extraction feeding the named `token-map` consumer) that is mostly distinct, with only minor overlap risk against closely related sibling atoms like `figma-extract` or `code-import`. Not a fully isolated niche with explicit distinct triggers (anchor 5), but well above 'somewhat specific, could still overlap' (anchor 3).

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

nexu-io/open-design

Path

plugins/_official/atoms/design-extract/SKILL.md

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.