AA video-interaction-mapper
This skill should be used when the user asks to analyze a UI screen recording and map interaction states into Figma. Trigger for requests such as "put video frames in Figma", "extract states from my recording", "map interactions from video to Figma", "analyze this screen recording", "create a storyboard from my video", "deconstruct this interaction in Figma", "annotate the UI states in my recording", or "pull the key moments from this video into Figma". Also trigger when the user references a video file (.mp4, .mov, .webm, .avi) together with Figma, design review, interaction analysis, prototypes, or UI states. The skill extracts key visual moments from a video, infers interaction triggers, and builds an annotated Figma Design storyboard using native Figma annotations and uploaded screenshot assets.
The skill promises to extract key frames from video and map them as UI states in Figma. The description cuts off mid-sentence, but the files are in place: seven files, five scripts, no critical errors. Scores are solid—quality 92, process 81, safety 100.
In practice, it should catch video files mentioned alongside Figma or interaction analysis, then pull frames and build a state layout. Testing found no breakage and no safety issues. Worth installing—the skill is ready to go.
This skill should be used when the user asks to analyze a UI screen recording and map interaction states into Figma.
As a process A 81/100 · Runs to the end — weak spots: running it twice
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 81/100
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 33 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3014 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 810: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.