Content
78%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 SKILL.md body is a concise, well-organized router with concrete constraints and a genuinely useful audit script, and it correctly delegates the composition contract to hyperframes-core. Its main weakness is that the bundle as provided does not ship the files it routes to — the routing table, indexes, and adapter references point to paths absent from the bundle, breaking progressive disclosure and leaving the default compose workflow without its referenced material. Actionability and workflow clarity are good but stop just short of fully executable end-to-end guidance.
Suggestions
Ship the referenced files (rules-index.md, blueprints-index.md, adapters/*.md, transitions/*, techniques.md) in the bundle, or restructure the routing table to point only at files that exist so navigation resolves.
Add a minimal inline example of the default compose step — a short paused-GSAP-timeline snippet gluing 2-3 rules — so the primary workflow is executable without loading external files.
Close the feedback loop after the animation-map audit: state what to do when the audit reports dead zones, stagger inconsistency, or lifecycle warnings (e.g. which rule/index to revisit), and sequence the hyperframes-cli lint/validate step into the workflow rather than leaving it only in See Also.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a lean router: "Pick 2-4 rules from rules-index.md, glue them together with a single paused GSAP timeline, done" and "Don't restate those here" defer to hyperframes-core rather than restating its contract. It never explains concepts Claude already knows (what GSAP is, what animation is), and the only explanatory passages (e.g. why getBoundingClientRect desyncs) convey non-obvious project-specific rationale. Every token earns its place. | 5 / 5 |
Actionability | Mostly executable guidance: a copy-paste runnable script command ("node skills/hyperframes-animation/scripts/animation-map.mjs <composition-dir> --out ..."), a concrete routing table with specific paths, and precise constraints ("Spatial motion uses GSAP transform aliases only (x, y, scale, rotation)"). It falls short of 5 because the default workflow's core step — "glue them together with a single paused GSAP timeline" — has no inline example and depends entirely on external files that are not present in the bundle. | 4 / 5 |
Workflow Clarity | A clear decision structure is present: a default path (compose atomic rules), explicit criteria for when to load a blueprint ("The scene matches an existing pre-designed multi-phase template... and reusing its phase pipeline saves real authoring time"), runtime selection guidance, and a post-authoring validation checkpoint ("Use it to audit choreography (dead zones, stagger consistency, lifecycle warnings) after authoring"). It misses 5 because there is no explicit feedback loop for acting on audit findings and no end-to-end sequencing that ties authoring to the hyperframes-cli lint/validate steps mentioned only in See Also. | 4 / 5 |
Progressive Disclosure | The routing-table design is well structured with clearly signaled, one-level-deep references and even anti-speculative-reading advice ("Do not read it speculatively; load it when you've already decided"), which would merit 4-5. However, scored against the actual bundle, nearly every referenced path — rules-index.md, rules/<name>.md, blueprints-index.md, blueprints/<id>.md, transitions/overview.md, transitions/catalog.md, techniques.md, and all 13 adapters/*.md — does not exist in the bundle (only scripts/animation-map.mjs and scripts/package-loader.mjs are present), so most navigation routes do not resolve. | 3 / 5 |
Total | 16 / 20 Passed |