Conciseness

The body is short and free of known-concept padding, but there is noticeable duplication: the Quick Reference bullets ("Use `<video>` instead of large GIFs for animations", "GIFs are significantly larger than MP4/WebM") restate the intro paragraph and the Fix section, and the thin "Explain" and "Code Review" sections add little new information. This fits the 3 anchor ('mostly efficient but includes some unnecessary explanation or could be tightened'). Not a 4 because the redundancy across intro/Quick Reference/Fix is more than minor trimming; not a 2 because the body is compact and does not explain basics Claude already knows.

Actionability

The Fix section gives concrete but incomplete guidance: "Convert animated GIFs to MP4 or WebM and use the `<video>` tag with `autoplay`, `loop`, `muted`, and `playsinline` attributes" names formats and exact attributes, yet the body contains no executable code or command — no ffmpeg conversion command and no <video> markup, both of which live only in references/rule.md. This matches the 3 anchor ('some concrete guidance but incomplete; missing key details'). Not a 4 because there is no inline code or command to execute; not a 2 because the guidance is specific about formats and attributes rather than a high-level hint.

Workflow Clarity

The Check → Fix → Explain sequence is clearly ordered for this simple task, and the Code Review section supplies a verification checkpoint ("describe the measurement method used to confirm the issue"), matching the 4 anchor ('clear sequence with most checkpoints present; minor validation gaps'). Not a 5 because verification is described loosely rather than as an explicit measure-then-confirm loop, and the Check step gives no measurement method (that detail is deferred to the reference); not a 3 because the sequence and checkpoints are present and unambiguous.

Progressive Disclosure

The body is a short overview with a clearly signaled one-level-deep reference that exists on disk: "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`", matching the 4 anchor ('good structure; most content appropriately placed; references mostly clear'). Not a 5 because the split is slightly uneven — the body's Code Review section largely duplicates the description's audit language instead of overview content, and the referenced file itself opens its code section with a stray empty '## Code Examples' heading followed by a lone '#' line, slightly muddying navigation into the bundle. Not a 3 because structure and signaling are good, the reference is real, and details are appropriately delegated.

Specificity

The description names the domain ("Convert animated GIFs to video") and 1-2 concrete actions ("auditing slow page loads, heavy assets, or rendering delays" and "Verify the actual bottleneck in DevTools, Lighthouse, or field data"), which matches the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because it does not list several specific actions — the core capability (converting GIFs, using FFmpeg, emitting a <video> tag) is only implied by the awkwardly embedded task title rather than stated as actions. It is not a 2 because tools are named and the auditing/verification actions are concrete rather than generic.

Completeness

Both 'what' and 'when' are present: the what is conveyed by the embedded phrase "related to Convert animated GIFs to video" plus the verification action, and the when is explicit via "Use when auditing slow page loads, heavy assets, or rendering delays". This matches the 4 anchor ('both present; one could be more explicit'). It is not a 5 because the what is grammatically mangled into a mid-sentence clause rather than a clear capability statement, and not a 3 because neither half is missing or merely implied.

Trigger Term Quality

Natural phrases users would say are present: "slow page loads", "heavy assets", "rendering delays", "animated GIFs", "video", plus tool names "DevTools, Lighthouse" — good keyword coverage matching the 4 anchor. It is not a 5 because common synonyms and extensions are missing ("animation", "MP4", "WebM", ".gif", "page weight"), and not a 3 because coverage goes beyond 'some relevant keywords' with multiple natural performance-related phrases.

Distinctiveness Conflict Risk

The GIF-to-video focus with named tools ("DevTools, Lighthouse") carves out a mostly distinct niche with only minor overlap risk against generic performance-audit skills — the 4 anchor. It is not a 5 because opening phrases like "slow page loads, heavy assets, or rendering delays" are shared vocabulary with general web-performance skills and could co-trigger them; not a 3 because the animated-GIF/video specifics keep it clearly distinguishable.