Content
65%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is exceptionally lean and well-sectioned, but its guidance stops short of executable: the render step names no command, there are no verification checkpoints, and the `source/` bundle it instructs Claude to read is absent from the skill directory. It reads as a template card rather than operational instructions.
Suggestions
Add the concrete render command (or renderer invocation) for step 4, e.g. the exact html-video / HyperFrames CLI call with output flags, so the workflow is executable rather than directional.
Include a verification checkpoint after rendering (confirm output file exists / spot-check duration and resolution) to close the workflow's validation gap.
Ship the `source/` bundle (at minimum `source/index.html`) or correct the reference — the workflow's first step points to a file that is not present in the skill directory.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is ~35 lean lines: a brief identity statement with concrete render specs ("MP4 / WEBM at 16:9, default 10s, 30fps"), a four-step workflow, and attribution — no explanations of concepts Claude already knows and no padding. Every token earns its place, matching the 'Lean and efficient' anchor; it is not a 4 because there is no over-explanation to trim. | 5 / 5 |
Actionability | Steps 1-2 give concrete, file-level guidance ("Read `source/index.html`", "Replace the sample copy ... keep the motion timing and visual signature intact"), but step 4 ("Render to MP4 via the html-video / HyperFrames renderer") gives no executable command or code — the key execution detail is missing. This matches 'Some concrete guidance but incomplete; missing key details' rather than 4, which requires mostly executable guidance with only minor gaps. | 3 / 5 |
Workflow Clarity | The four steps are clearly sequenced (read → customize → keep self-contained → render) and each step is well defined, but there are no validation or verification checkpoints anywhere — no check that the render succeeded or that the composition is render-safe. This matches 'Steps listed but validation gaps; checkpoints missing or implicit' rather than 4, which requires most checkpoints present. | 3 / 5 |
Progressive Disclosure | Sections are well organized for a short single-purpose skill (identity, best-for, workflow, attribution), but the body's central reference — the bundle "bundled under `source/`" and "Read `source/index.html`" — does not exist in the skill directory (no `source/`, `references/`, `scripts/`, or `assets/` present), so the one reference it relies on is unresolvable. Structure exists but the bundle navigation is effectively broken, matching 'Some structure but could be better organized' rather than 4, where references would be mostly clear and resolvable. | 3 / 5 |
Total | 14 / 20 Passed |