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.
A well-structured, highly actionable skill body with concrete commands, tables, and worked examples supported by safety and compatibility checkpoints. The main improvement opportunities are trimming the lighter advisory sections and moving some reference-style detail into separate files.
Suggestions
Tighten the "When to Use This Skill" and "Ask Before Searching" sections to reduce advisory padding.
Move the per-source install detail and the large source-identifier table into a references file, keeping SKILL.md as a concise overview with one-level-deep links.
Add an explicit validate-retry loop for script inspection (inspect → flag issue → fix/skip → re-inspect) to strengthen the workflow checkpoint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete commands and tables and avoids explaining concepts Claude already knows, though sections like "When to Use" and "Ask Before Searching" add minor padding that could be trimmed. | 4 / 5 |
Actionability | It provides copy-paste-ready commands (hermes/clawhub/letta/git) with flags, source tables with example identifiers, and worked install examples covering the common cases. | 5 / 5 |
Workflow Clarity | The Search Strategy and Complete Example lay out a clear sequence with a compatibility-review checkpoint and a script-inspection safety step, but the validation is advisory rather than a strict validate-fix-retry loop. | 4 / 5 |
Progressive Disclosure | Content is well organized into clearly labeled sections with no nested references, but the fairly long monolithic body (no bundle files present) could split some per-source reference material into separate files. | 4 / 5 |
Total | 17 / 20 Passed |