Content
82%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 strong, action-oriented CLI reference with executable examples and clear multi-step workflows for each capability. Main improvements would be consolidating repeated guidance and making validation steps concrete.
Suggestions
Consolidate the repeated 'prefer Hermes native tools' and paid-tier reminders into a single 'When to use' section to remove redundancy.
Make validation explicit by adding a concrete check command (e.g., how to verify enriched.csv succeeded) rather than only stating 'Validate the output file before reporting success'.
Consider moving the per-subcommand flag detail into a reference file if the file grows further, keeping SKILL.md as a tight overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean executable commands with little concept-explanation, though the 'prefer Hermes native tools' and paid-tier reminders are repeated across several sections and could be consolidated. | 4 / 5 |
Actionability | Abundant copy-paste-ready commands with real flags cover each subcommand's common cases (search, extract, research, enrich, findall, monitor), matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | Numbered workflows (launch --no-wait -> poll -> summarize; enrich inspect -> suggest -> run -> validate) and an exit-code error-recovery loop provide clear sequencing with checkpoints, though validation steps are stated more than concretely commanded. | 4 / 5 |
Progressive Disclosure | No bundle files exist, but the single file is well-organized with clear section headers and a quick-reference command tree for navigation; inlining is reasonable for a concise command catalog, with only minor organization gaps. | 4 / 5 |
Total | 17 / 20 Passed |