Content
58%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.
As a catalogue stub the body is admirably lean and well-organized, but it fails as actionable guidance: the entire "How to use" section defers to an external README with no concrete install command, path, or verification step. The structure is good; the executable substance is missing.
Suggestions
Replace `open https://github.com/openai/skills` with a concrete install command (e.g. a git clone of the upstream bundle and a copy into the agent's skills directory with the expected path).
Specify where the bundle's SKILL.md must land and what the skills directory looks like, instead of "install the upstream bundle into your active agent's skills directory".
Add a verification step, e.g. confirming the skill appears in the agent's skill list before invoking it by name.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~25-line body ("This catalogue entry advertises the skill in OpenDesign...") is lean with no concept explanations Claude already knows and no padding; every section serves the pointer-entry purpose. The only trim candidate is the "What it does" section repeating the frontmatter description verbatim, which falls short of anchor 4's "minor instances of over-explanation". | 5 / 5 |
Actionability | The core instruction "install the upstream bundle into your active agent's skills directory" has no executable steps, and the only command, `open https://github.com/openai/skills`, merely opens a browser with the comment "Inspect the upstream README for exact paths" deferring all specifics to an external page. This matches anchor 2 ("minimal concrete guidance; high-level hints but missing the specific steps") — anchor 3 would require actual task instructions with key details, which are absent. | 2 / 5 |
Workflow Clarity | A rough sequence exists (install the upstream bundle, then "ask the agent to invoke this skill by name (`sora`) or with one of the trigger phrases"), but the critical install step is undefined and there is no check that the skill is actually available. Anchor 2 ("rough sequence present but many gaps; steps poorly defined") fits; the simple-skill exception cannot apply because the single action is ambiguous, not unambiguous. | 2 / 5 |
Progressive Disclosure | The skill is under 50 lines, has no bundle files (references/, scripts/, assets/ are absent), and organizes content into clear sections ("What it does", "Source", "How to use") with a single one-level-deep external pointer (the upstream repo URL). Per the small-skill guideline, this earns anchor 5 with just well-organized sections. | 5 / 5 |
Total | 14 / 20 Passed |