Content
78%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 highly actionable with executable commands and clear per-script guidance, and workflow sequencing includes a sensible failure fallback. Its main weakness is progressive disclosure: it cites bundle files (requirements.txt, .env.example) that do not exist.
Suggestions
Add the missing requirements.txt and .env.example files referenced in the body, or remove the references to avoid broken navigation.
Tighten the 凭证配置 paragraph and 注意 notes to remove minor verbosity without losing the credential-handling guidance.
Consider splitting the long per-script parameter tables into a separate reference file if the skill grows, keeping SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Efficient use of arg tables and executable bash examples with no concept over-explanation; only minor wording in the credential-config and 注意 notes could be trimmed, so it sits just below the lean 5 anchor. | 4 / 5 |
Actionability | Each script gets copy-paste-ready bash commands with real flags, defaults, env-var alternatives, and multiple concrete example queries, matching the 'fully executable' anchor. | 5 / 5 |
Workflow Clarity | Clear run sequence with an explicit dependency-failure checkpoint and web-search fallback; read-only search limits the need for stronger validation loops, keeping it just under 5. | 4 / 5 |
Progressive Disclosure | Sections are well-organized and scripts live appropriately in scripts/, but the body references requirements.txt and .env.example that are not present in the bundle, so referenced paths are broken. | 3 / 5 |
Total | 16 / 20 Passed |