figma-extract

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

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/atoms/figma-extract/SKILL.md

Quality

Content

67%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.

A well-structured, concise specification of a single-purpose atom with clear inputs, outputs, and a convergence checkpoint, but it is descriptive rather than executable and lacks a numbered, validated workflow sequence.

Suggestions

Add a short, numbered "Run" or "How to invoke" sequence with the concrete commands so the content moves from descriptive to executable.

Include a minimal code or CLI example (e.g. the exact `od plugin apply` invocation and expected output) to raise actionability.

Consider moving the full output-tree block and anti-patterns into a reference file and linking to it, keeping SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no explanations of what Figma or tokens are), with every section earning its place; only minor phrases like the spec citation framing could be trimmed, so it is a 4 rather than a 5.	4 / 5
Actionability	Concrete details exist (specific flags like "od plugin apply --input fileUrl=…", "oauth.route='connector'", the JSON output shape, and the "figma.tree.nodes >= 1" evaluator) but there is no executable code or copy-paste command sequence for Claude to run, leaving it as descriptive guidance rather than fully actionable.	3 / 5
Workflow Clarity	The flow is clear (inputs -> fetch/walk tree -> record unsupported nodes -> lift tokens -> rasterize assets) with an explicit convergence checkpoint and error-recovery path; it stops short of 5 because the steps are described as a spec rather than an explicit numbered sequence with per-step validation.	4 / 5
Progressive Disclosure	No bundle files exist and the body is organized into well-labeled sections (Inputs, Output, Convergence, Anti-patterns, Status) with no nested references; it is not a 5 only because the content slightly exceeds the ~50-line simple-skill threshold and a couple of sections (e.g. the full output tree) could arguably live in a reference file.	4 / 5
	Total	15 / 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.

A tight, specific description of what the atom does, but it omits any explicit "when to use" trigger guidance, which caps its completeness and limits trigger-term richness.

Suggestions

Append a "Use when..." clause naming the triggering scenario (e.g. figma-migration, importing a Figma file, extracting design tokens) so completeness can rise above 3.

Add natural synonyms and cue phrases users would say ("Figma", "Figma export", "pull from Figma") to broaden trigger-term coverage.

Tie the description explicitly to the figma-migration pipeline stage to sharpen distinctiveness against generic import skills.

Dimension	Reasoning	Score
Specificity	The description names the Figma domain and three concrete actions ("node tree, design tokens, and embedded assets") plus a concrete destination ("project cwd as a structured snapshot"); it falls short of 5 only because coverage is a single condensed list rather than an exhaustive enumeration.	4 / 5
Completeness	There is a clear "what" but no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; the "when" is only weakly implied by the domain terms.	3 / 5
Trigger Term Quality	Natural terms like "Figma file", "node tree", "design tokens", and "embedded assets" appear, giving good keyword coverage, but synonyms (e.g. "Figma", "Figma export") and a file/url extension cue are absent so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear Figma-extraction niche with distinct triggers and minimal conflict risk, but because no explicit trigger phrasing narrows the scenario it is not a definitive 5.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/figma-extract/SKILL.md
Commit: 1a7a23d

Reviewed: about 7 hours ago

Table of Contents

Discovery Implementation Validation

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.