Content
92%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.
An exemplary instruction-only skill: every step is executable, validation and feedback loops are explicit, and the translation rules are concrete enough to apply mechanically. The only nit is a slightly redundant clarification around `--same` and a few long compound sentences that could be split without losing content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense, instruction-only prose that assumes Claude's competence (no explanation of MDX, Docusaurus, or translation basics), but contains minor trimmable redundancy: "Don't clear it with `--same`, which is for text meant to match English" partially restates the `--same` rule introduced two sentences earlier. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands with exact flags ("node website/translate/translate.mjs prepare --json", "--locale es", "finalize", "--same <id>", "node --test website/translate/mdx.test.mjs") and coverage of the common cases: new pages, updates with and without a diff, removed translations, and UI strings. | 5 / 5 |
Workflow Clarity | The procedure is clearly sequenced with an explicit validation feedback loop ("Fix each `✗` problem it prints and run it again until it passes"), a recovery path for stale data ("run `prepare` again and translate what it lists"), and pre-PR verification via the test suite and `check`, so the batch-operation cap does not apply. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files and no need for external references; sections (Procedure, Weekly run, Translation rules) are well organized and the one external pointer ("How the pieces fit: `website/translate/README.md`") is clearly signaled and one level deep, satisfying the simple-skill exception. | 5 / 5 |
Total | 19 / 20 Passed |