Name: figma
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

figma

Figma integration. Manage Files, Projects, Teams. Use when the user wants to interact with Figma data.

Quality

63%

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 ./skills/figma/SKILL.md

Quality

Content

63%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 highly actionable with concrete Membrane commands and a solid connection-state feedback loop, but it wastes tokens explaining what Figma is and inlines a large API reference table that belongs in a separate file. Tightening the intro and externalizing the actions catalog would meaningfully improve it.

Suggestions

Delete the opening "Figma is a web-based collaborative design tool..." paragraph and the "so you can focus on the integration logic rather than auth plumbing" fluff; Claude already knows what Figma is.

Move the 18-row "Popular actions" table into a references/ file (e.g., references/actions.md) and link to it from a short inline summary, improving progressive disclosure and token efficiency.

Replace the dangling "skip to Step 2" reference with an explicit numbered sequence (1. Install → 2. Authenticate → 3. Connect → 4. Search → 5. Run) so the end-to-end workflow is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body opens with "Figma is a web-based collaborative design tool..." explaining what Figma is and who uses it, which Claude already knows, plus marketing fluff like "so you can focus on the integration logic rather than auth plumbing"; the rest is mostly efficient, matching the mostly-efficient-but-includes-unnecessary-explanation anchor.	3 / 5
Actionability	Concrete executable commands appear throughout (npm install, membrane login, connection ensure/get --wait, action list/run with --input, request with flag table), covering common cases; minor gaps are unresolved placeholders (<agentType>, CONNECTION_ID, <id>) and the absence of a single fully-worked end-to-end example, fitting mostly-executable-guidance rather than the 5-anchor's copy-paste-ready complete coverage.	4 / 5
Workflow Clarity	The connection flow has a clear state-based feedback loop (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR with polling and re-check), giving most checkpoints; gaps are the un-numbered overall sequence and the dangling "skip to Step 2" reference whose Step 2 is never explicitly labeled, placing it at clear-sequence-with-most-checkpoints rather than the 5-anchor's explicit validation steps.	4 / 5
Progressive Disclosure	Section headers are well organized, but the 18-row "Popular actions" table is bulk API reference inlined in SKILL.md that belongs in a separate file, and no references/scripts/assets bundle exists despite the skill exceeding 50 lines, matching the some-structure-but-content-that-should-be-separate-is-inline anchor.	3 / 5
	Total	14 / 20 Passed

Description

62%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 answers both what and when with a clear Figma niche, but relies on a single generic verb ("Manage") and one abstract trigger phrase rather than enumerating concrete actions and natural trigger variations. It is solid but leaves room for more specific, user-natural language.

Suggestions

Replace the generic verb "Manage" with specific concrete actions (e.g., "Get file metadata, render images from nodes, post and retrieve comments, list team projects and components").

Expand the "Use when..." clause with concrete natural triggers (e.g., "Use when the user wants to read or comment on Figma files, render node images, or browse team projects and components").

Add file-extension or artifact synonyms where natural (e.g., "Figma files", "Figma designs", "Figma prototypes") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Manage Files, Projects, Teams" names the Figma domain and concrete entities, but the single verb "Manage" is generic rather than enumerating several specific actions, fitting the names-domain-and-1-2-concrete-actions anchor rather than the 4-anchor's several specific actions.	3 / 5
Completeness	It has both a clear "what" ("Figma integration. Manage Files, Projects, Teams.") and an explicit "when" ("Use when the user wants to interact with Figma data."), but the "when" is a single generic trigger rather than multiple concrete trigger phrases, so it sits at has-both-what-and-when rather than the 5-anchor's concrete trigger list.	4 / 5
Trigger Term Quality	"Figma" is a natural keyword a user would say, but the trigger phrasing "interact with Figma data" is somewhat abstract and misses common variations like "manage my Figma files" or "get data from Figma", matching the some-relevant-keywords-but-missing-variations anchor.	3 / 5
Distinctiveness Conflict Risk	"Figma" is a distinct niche with low conflict risk, but the generic "interact with Figma data" trigger leaves minor overlap risk with broader design-tool skills, placing it at mostly-distinct rather than the 5-anchor's minimal-conflict clear niche.	4 / 5
	Total	14 / 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: membranedev/application-skills
Path: skills/figma/SKILL.md
Commit: f484c82

Reviewed: ~19 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.