Content
72%Reviews 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 shim that points cleanly to an upstream bundle, but its install workflow is vague and lacks concrete executable steps beyond opening the repo URL.
Suggestions
Provide a concrete install command (e.g., `git clone` into the skills directory or a specific path) instead of deferring all detail to the upstream README.
Spell out the invoke step with an example trigger phrase so the workflow end-to-end is unambiguous.
Add a brief verification step (e.g., confirm the skill appears in the agent's skill list) so the sequence has an explicit checkpoint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~28-line body is lean, assumes Claude's competence, and does not explain concepts Claude already knows; each section earns its place, though the "What it does" section repeats the frontmatter description verbatim as a minor redundancy. | 3 / 3 |
Actionability | It offers one concrete command (`open https://github.com/raintree-technology/apple-hig-skills`) but the core instruction to "install the upstream bundle into your active agent's skills directory" is vague and defers specifics to the upstream README, leaving key details missing. | 2 / 3 |
Workflow Clarity | A loose sequence exists (advertise in Open Design, install upstream bundle, invoke by name/triggers) but the install step is unspecified and there are no validation checkpoints, so the sequence is present yet gappy rather than fully clear. | 2 / 3 |
Progressive Disclosure | No bundle files are present (references/scripts/assets are empty), and the under-50-line body is organized into well-signaled sections (What it does, Source, How to use) with a single one-level-deep external reference (the upstream URL), satisfying the simple-skill progressive disclosure anchor. | 3 / 3 |
Total | 10 / 12 Passed |