CD figma-use
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically.
The skill promises to set up context before any Figma API call—supposedly preventing bugs when creating nodes, working with variables, and building components. Rated C with an «ok» verdict. The catch: the sandbox failed to run scripts, so actual functionality remains untested. The package contains 21 files and one script; code quality scores 66 percent, process maturity 47 percent. No critical errors found, but broken_references flag signals incompleteness.
If the description holds, the skill triggers before use_figma on every operation. That means an extra call layered before each action. Without a working sandbox, it's unclear whether it genuinely prevents bugs or just adds abstraction overhead. Install it, but test on your files first to confirm it runs clean.
MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call.
As a process D 47/100 · Unfinished process — References files that are not bundled: ../figma-generate-design/SKILL.md, ../figma-generate-library/SKILL.md, ../figma-use-slides/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: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8257 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../figma-generate-design/SKILL.md - warning
missing-refreference to a missing file: ../figma-generate-library/SKILL.md - warning
missing-refreference to a missing file: ../figma-use-slides/SKILL.md
Process rating: all ten parameters 47/100
- 0Tools and files. 3 referenced file(s) missing: ../figma-generate-design/SKILL.md, ../figma-generate-library/SKILL.md, ../figma-use-slides/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 8257 tokens: crowds the task out of the window
- 60Steps. 43 steps, 4 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
- 100Progress reporting. Reports progress
- 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
- +1No license
- +2Single-language instructions
- +3Description length 546: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Скриптов, которые можно было бы запустить, в скилле нет.
19 Oct 2026