Content
40%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 well-organized, brief catalogue entry that honestly defers content to the upstream repo, but it provides almost no executable guidance — no install command, no sample rules, and no invocation verification. As a result actionability and workflow clarity sit near the bottom of the scale.
Suggestions
Replace 'install the upstream bundle into your active agent's skills directory' with a concrete, copy-pasteable command (e.g. a git clone or install command with the exact target path).
Inline a short quick-start subset (5-10 of the highest-value rules) so the skill delivers value even before the upstream bundle is fetched.
Add a verification step to the workflow, e.g. checking that `platform-design` appears in the agent's skills listing before asking it to invoke the skill.
Drop the verbatim repeat of the frontmatter description in 'What it does' and use that space for the quick-start rules instead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and has no padding, but the 'What it does' section repeats the frontmatter description verbatim, and 'This catalogue entry advertises the skill in OpenDesign so the agent discovers it during planning' is meta-commentary that adds nothing to execution. Mostly efficient, with some content that could be tightened — anchor 3. | 3 / 5 |
Actionability | The only concrete command is `open https://github.com/ehmo/platform-design-skills`, which does not perform the skill's task. 'Install the upstream bundle into your active agent's skills directory' gives no install command or path, so the user/agent cannot execute the actual workflow from this file. This matches 'Minimal concrete guidance; high-level hints but missing the specific steps to execute'. | 2 / 5 |
Workflow Clarity | A rough sequence exists (inspect README → install bundle → invoke by name or triggers), but each step is vague: there is no install command, no verification that the skill is available, and no guidance on what to do once the skill is invoked. Steps are poorly defined and validation is absent — anchor 2. | 2 / 5 |
Progressive Disclosure | The body is under 50 lines with clean sections (What it does / Source / How to use) and appropriately defers the 300+ rules to an external upstream rather than inlining them — the pointer is clearly signaled and one level deep. It scores below 5 because there are no in-bundle reference files at all, so all substantive content lives outside the skill and navigation depends entirely on an external URL. | 4 / 5 |
Total | 11 / 20 Passed |