CC figma-generate-library
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individual components with proper variant sets and variable bindings, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. Also use when the user asks to create or generate any component in Figma — even a single one — since components require proper variable foundations, variant states, and design token bindings to be production-quality. This skill teaches WHAT to build and in WHAT ORDER — it complements the `figma-use` skill which teaches HOW to call the Plugin API. Both skills should be loaded together.
The skill promises to build a Figma design system from scratch: variables, tokens, component library, variants, and bindings. The description cuts off mid-sentence, which already signals trouble. 16 files total, but code quality sits at 73 points and process score at 64. Broken references mean internal links are dead. It teaches workflow order, not API calls—supposedly complementary to another skill, but that's untested. Never ran on models.
If you want to automate component system creation, the skill provides structure. But with a truncated description and file errors, expect to patch the instructions yourself. Install if you're ready to troubleshoot along the way.
Build or update a professional-grade design system in Figma from a codebase.
As a process C 64/100 · Has gaps — References files that are not bundled: ../figma-use/references/gotchas.md
The same skill appears in 1 more place: mcp-server-guide
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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5999 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../figma-use/references/gotchas.md
Process rating: all ten parameters 64/100
- 0Tools and files. 1 referenced file(s) missing: ../figma-use/references/gotchas.md
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5999 tokens
- 85Steps. 69 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 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
- low 11 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 719: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 8 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.