CD 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, form, dashboard, list, table, card, header, message preview, or other composed product UI in Figma from code or a description—even when the user calls that composed UI a component. 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.
This skill promises to automate converting UI elements from code or description into Figma—pages, modals, forms, tables, anything component-based. Triggers catch commands like 'write to Figma' or 'convert this page'.
Files contain broken references and missing resources. Code quality scores 63, process maturity 49. No critical errors found, but model runs and sandbox tests are absent. The skill targets a broad platform range including Claude and Cursor.
Install it as a companion to figma-use if incomplete documentation doesn't deter you. Expect some functions to need clarification or refinement during actual use.
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma.
As a process D 49/100 · Unfinished process — References files that are not bundled: ../figma-use/SKILL.md, ../figma-generate-library/SKILL.md, ../figma-code-connect/SKILL.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9541 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../figma-use/SKILL.md - warning
missing-refreference to a missing file: ../figma-generate-library/SKILL.md - warning
missing-refreference to a missing file: ../figma-code-connect/SKILL.md - warning
missing-refreference to a missing file: ../figma-use/references/variable-patterns.md - warning
missing-refreference to a missing file: ../figma-use/references/text-style-patterns.md - warning
missing-refreference to a missing file: ../figma-use/references/effect-style-patterns.md - warning
missing-refreference to a missing file: ../figma-use/references/component-patterns.md - warning
missing-refreference to a missing file: ../figma-generate-library/references/component-creation.md - warning
missing-refreference to a missing file: ../figma-use/references/component-patterns.md - warning
missing-refreference to a missing file: ../figma-use/references/component-patterns.md - warning
missing-refreference to a missing file: ../figma-use/references/gotchas.md - warning
missing-refreference to a missing file: ../figma-use/SKILL.md - note
edit-residuethe text marks something as outdated (lines 420): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 0Tools and files. 12 referenced file(s) missing: ../figma-use/SKILL.md, ../figma-generate-library/SKILL.md, ../figma-code-connect/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Execution cost. Instruction body is 9541 tokens: crowds the task out of the window
- 60Steps. 69 steps, 13 vague phrases
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 960: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 26 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.