AD html-demo
Show an app working on a web page by drawing it live in HTML instead of recording it. A Mac-style window plays the app step by step, and every frame is a pure function of one clock, View(t), drawn on a fixed 1200 × 750 stage that one CSS scale fits to any width. The pointer is scripted, labels and pictures come from the real app, a steps bar sits under the window, it plays only while on screen, and reduced motion gets designed end frames. Use when someone wants a product demo, an animated app window or hero, a feature walkthrough, "the UI animated and simulated in HTML", "like a screen recording but HTML", an interactive product tour on a landing or download page, or wants to replace screen recordings, GIFs or MP4s of their UI with crisp live HTML. Also use to build many such windows at once with helper agents, or to scrub, freeze and screenshot them.
Show an app working on a web page by drawing it live in HTML instead of recording it.
As a process D 41/100 · Unfinished process — References files that are not bundled: scripts/step-window.css
How to improve
- 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/step-window.css
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: scripts/step-window.css
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 40 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3374 tokens
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 863: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 8 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.