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 content is highly actionable with real, copy-paste script commands and a clear workflow, organized into well-signaled sections; its main gaps are a broken snippet reference and minor padding.
Suggestions
Create the referenced './snippets/common-configs.md' (or a snippets/ directory) so the config-snippet reference resolves to a real file.
Remove the redundant Capability Summary line that duplicates the frontmatter description to save tokens.
Add an explicit verification checkpoint in the Workflow (e.g., 'Confirm the fetched doc addresses the user's question before answering').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and assumes Claude's competence (no explanation of what OpenClaw is), with only minor padding such as the Capability Summary duplicating the frontmatter and decorative emoji headers. | 4 / 5 |
Actionability | Provides copy-paste ready, verified-real script commands (e.g., './scripts/search.sh discord', './scripts/fetch-doc.sh gateway/configuration') plus a concrete JSON config snippet covering common cases. | 5 / 5 |
Workflow Clarity | A clear 5-step Workflow sequence (identify → search → fetch → reference snippets → cite URL) is present; this is a read-only doc-lookup skill so no destructive/batch validation is required, but explicit checkpoints like confirming the fetched doc answers the question are missing. | 4 / 5 |
Progressive Disclosure | Well-organized sections with clearly signaled one-level-deep references to real scripts in ./scripts/, but the referenced './snippets/common-configs.md' does not exist in the bundle and no references/ or assets/ directories are present. | 4 / 5 |
Total | 17 / 20 Passed |