CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

figma-generate-design

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code', 'convert this modal/dialog/drawer/panel to Figma'. This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma from code or a description. Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values.

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 high-quality workflow skill body: fully executable code at every step, hard-gated sequencing with per-section visual validation and an explicit error-recovery loop, and appropriate offloading of detail to real, clearly-labeled reference files. Its main costs are repeated emphasis of the same mandates (parallel capture, font assertion) and some long inline sections that could live in references.

Suggestions

Consolidate the parallel generate_figma_design capture mandate into one authoritative section and cross-reference it from Step 1 and Step 5 instead of restating the requirement three times.

State the font-family identification and assertion requirement once (Step 1 / Step 5) and drop the third restatement in Best Practices, keeping only a one-line pointer.

Move the icon SVG-import section and the image-transfer scripts into a reference file (e.g., references/icons-and-images.md) and link to them, slimming the Step 4/Step 5 inline content.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational knowledge (imageHash-only image fills, getLocalVariableCollectionsAsync being local-only, createNodeFromSvg width/height sizing) and contains no beginner-concept padding — matching the level-4 anchor of efficient with minor trimmable instances. Not 5 because key mandates are repeated verbatim in multiple places: the parallel generate_figma_design capture requirement appears in its own section plus Step 1 item 5 plus Step 5, and the font-family assertion appears in Step 1, Step 5, and Best Practices.

4 / 5

Actionability

Every step ships executable JavaScript for the Figma plugin API — component-key resolution from Code Connect URLs, bound-variable enumeration, wrapper sizing by container type with concrete dimensions, setProperties() text overrides, createNodeFromSvg icon import with the viewBox/width/height requirement — plus concrete search-term lists and parsing rules (hyphens to colons). This matches the level-5 anchor: copy-paste-ready code covering the common cases.

5 / 5

Workflow Clarity

Steps 1–6 are explicitly ordered ('Follow these steps in order. Do not skip steps.') with hard gates forbidding premature canvas mutation, per-section get_screenshot validation with a defect checklist (cropped text, overlaps, placeholder text, wrong font, blank images), and a STOP→read→inspect→fix→retry error-recovery loop noting script atomicity. This is the level-5 anchor: clear sequence, explicit validation, feedback loops.

5 / 5

Progressive Disclosure

The core workflow lives in SKILL.md with detail delegated to clearly-signaled one-level-deep references — references/componentization.md and references/discover-product-font.md both exist in the bundle, and the Reference Docs section annotates each ../figma-use reference with its content. This matches the level-4 anchor (good structure, most content appropriately placed, minor gaps): the icon-SVG-import section and the image-transfer scripts are substantial inline content that could be split out, and heavy reliance on a sibling skill's references outside this bundle is a small navigation risk.

4 / 5

Total

18

/

20

Passed

Description

96%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 strong description: it explicitly answers both what the skill does and when to use it, with an unusually rich set of natural trigger phrases and concrete action verbs. The only weakness is residual overlap with the sibling figma-use skill's own Figma-building triggers, which the scoping language mitigates but does not eliminate.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens' — covering the full discover→import→assemble pipeline. This matches the level-5 anchor (multiple specific concrete actions, comprehensive coverage) rather than level 4, whose coverage has minor gaps.

5 / 5

Completeness

Both 'what' (discovers design system components/variables/styles, imports them, assembles views section-by-section with tokens) and 'when' ('This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma') are explicitly stated with concrete trigger phrases — the level-5 anchor exactly.

5 / 5

Trigger Term Quality

Explicit trigger phrases are natural user phrasings with synonyms: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'convert this modal/dialog/drawer/panel to Figma'. This is comprehensive natural-term coverage per the level-5 anchor, not merely 'good keyword coverage' (level 4).

5 / 5

Distinctiveness Conflict Risk

The description clearly scopes to composed multi-section views and distinguishes itself from the sibling figma-use skill ('Use this skill alongside figma-use'), matching the level-4 anchor of mostly distinct with minor overlap risk. Not 5 because it shares 'build in Figma' language with figma-use itself, so a component-creation request could plausibly match either; not 3 because the multi-section vs. component boundary is explicitly drawn.

4 / 5

Total

19

/

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

relative_links

Relative link issues: 16 suspicious

Warning

Total

15

/

16

Passed

Repository

Devin-AXIS/iPolloWork

Path

examples/plugin-packages/figma/skills/figma-generate-design/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.