Content
51%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 a lean, well-organized catalogue stub: it cleanly describes what the skill is and where it comes from without padding. However, it contains essentially no executable guidance for the skill's actual task — no download commands, no install steps, no verification — instead deferring everything to an external repository, which caps both actionability and workflow clarity.
Suggestions
Add the concrete core workflow, e.g. yt-dlp examples: `yt-dlp -f "bestvideo+bestaudio" URL` and an audio-extraction variant, so the body is actionable on its own.
Replace 'install the upstream bundle into your active agent's skills directory' with actual copy/clone commands and a verification step (e.g. checking the skill appears in the skills directory) to close the validation gap.
Drop the duplicated description in 'What it does' (or the repeated upstream URL) to tighten the token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and free of explanations of concepts Claude already knows, but it carries minor redundancy: the 'What it does' section repeats the frontmatter description verbatim, and the upstream URL appears twice (frontmatter-echoed 'Source' section and the bash block). This matches anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') rather than 5, where every token would earn its place. | 4 / 5 |
Actionability | The only concrete command is 'open https://github.com/...' — an instruction to go read an external README — and the actual task guidance is entirely abstract ('install the upstream bundle into your active agent's skills directory', 'ask the agent to invoke this skill by name'). No download command, tool, or example appears in the body, matching anchor 2 ('minimal concrete guidance; high-level hints but missing the specific steps to execute') rather than 3, which would require at least some task-relevant concrete guidance. | 2 / 5 |
Workflow Clarity | A rough sequence exists (inspect upstream README → install bundle → invoke by name or triggers) but the steps are poorly defined — 'install the upstream bundle' has no concrete commands or paths — and there is no validation that the install worked. This matches anchor 2 ('rough sequence present but many gaps; validation absent'); it is not 3 because even the listed steps lack executable detail, and not 1 because a sequence is present. | 2 / 5 |
Progressive Disclosure | The skill is under 50 lines, has no bundle files (references/, scripts/, assets/ are all absent), and is organized into clear single-purpose sections ('What it does', 'Source', 'How to use'). Per the rubric's simple-skill guideline, a short skill with no need for external references scores 5 with just well-organized sections; the single outbound link is clearly signaled and one level deep, not nested. | 5 / 5 |
Total | 13 / 20 Passed |