CtrlK
BlogDocsLog inGet started
Tessl Logo

figma-extract

Pull a Figma file's node tree, design tokens, and embedded assets into the project cwd as a structured snapshot.

64

Quality

76%

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 ./plugins/_official/atoms/figma-extract/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 well-organized, lean specification with explicit convergence validation and error handling. The only weaker dimension is actionability, since it describes behavior in spec form rather than providing copy-paste executable code.

Suggestions

Add a minimal concrete invocation example (e.g. the exact `od plugin apply` command with a real fileUrl and token routing) to move actionability from spec-level to copy-paste ready.

Optionally show a one-line snippet of the expected `tree.json` / `tokens.json` shape so downstream atoms have a directly verifiable contract.

DimensionReasoningScore

Conciseness

The body is lean and structured (tables, a tree diagram, tight bullets) and assumes Claude's competence without explaining what Figma or OAuth is; every section earns its place, matching the level-3 anchor rather than the padded level-2 example.

3 / 3

Actionability

Concrete guidance exists ("od plugin apply --input fileUrl=…", JSON shapes, file paths), but the body is a spec describing behavior rather than copy-paste executable code, so it stops at the level-2 "some concrete guidance but incomplete" anchor.

2 / 3

Workflow Clarity

For this single-action atom the flow is unambiguous and includes an explicit convergence validation ("figma.tree.nodes >= 1") plus error recovery (emit error event, user fixes auth or picks another file), meeting the level-3 anchor for single-task skills.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the content is split into well-organized, self-contained sections (Inputs, Output, Convergence, Anti-patterns, Status), which per the simple-skill note earns level 3 on organization alone.

3 / 3

Total

11

/

12

Passed

Description

67%

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 distinctive, clearly conveying what the skill does with concrete actions. Its main gap is the absence of an explicit "Use when..." trigger clause, which limits completeness and natural-trigger coverage.

Suggestions

Add a "Use when..." clause naming natural user triggers, e.g. "Use when migrating a Figma file into the project, or when the user mentions Figma designs, design tokens, or exporting Figma assets."

Broaden trigger-term coverage with everyday phrasings like "Figma designs", "Figma to code", or "export Figma" so users' natural requests match the skill.

Keep the concrete action list but append the when-condition in the same sentence to satisfy both the what and the when at level 3.

DimensionReasoningScore

Specificity

"Pull a Figma file's node tree, design tokens, and embedded assets" names multiple specific concrete actions (node tree, tokens, assets), matching the level-3 anchor rather than the single-action level-2 anchor.

3 / 3

Completeness

The description clearly answers "what" but provides no "Use when..." trigger clause, so per the judging guidelines completeness is capped at 2 rather than reaching the explicit-both level 3.

2 / 3

Trigger Term Quality

"Figma file", "design tokens", and "assets" are relevant keywords a user might say, but coverage of common variations is incomplete and the phrasing leans technical; it does not reach the broad natural-term coverage of level 3.

2 / 3

Distinctiveness Conflict Risk

The Figma-extraction niche is specific and unlikely to trigger for unrelated skills; it is clearly distinguishable, matching the level-3 anchor.

3 / 3

Total

10

/

12

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.

Validation15 / 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
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.