CD figma-use-slides
This skill helps agents use Figma's use_figma MCP tool in the Slides context. Can be used alongside figma-use which has foundational context for using the use_figma tool.
The skill teaches an agent to work with Figma MCP in a Slides context—supplements the foundational figma-use with presentation-specific instructions. In practice: grade C, quality 72%, process 43%. Seven files, but half have broken references or missing files. No critical bugs, lint is clean. Model never ran, sandbox untested.
For an agent, this means: instructions exist but incomplete. If you already use figma-use and specifically need slide handling, you can try it. If you lack confidence in the base skill or need a working guarantee, it's too early. Fixing broken references and running on models would have been worth it before release.
This skill helps agents use Figma's usefigma MCP tool in the Slides context.
As a process D 43/100 · Unfinished process — References files that are not bundled: ../figma-use/SKILL.md
The same skill appears in 1 more place: opencode
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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5411 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../figma-use/SKILL.md
Process rating: all ten parameters 43/100
- 0Tools and files. 1 referenced file(s) missing: ../figma-use/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5411 tokens
- 85Steps. 47 steps, 1 vague phrases
- 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
- 100Progress reporting. Reports progress
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 170: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.