Content
76%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 executable CLI commands and reasonable structure, but its multi-step workflow has implicit validation and a couple of orphaned step labels that weaken clarity around risky operations.
Suggestions
Replace the loose 'Step 2' / '1b' references with a clearly numbered sequence so the install→auth→connect→run flow is unambiguous.
Add an explicit validate/retry checkpoint after destructive proxy calls (e.g., 'verify the response status before reporting success; on error, inspect the error field and retry or surface to the user').
Tighten the connection-state section by leading with the decision table and trimming explanatory prose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient CLI commands with minimal padding; the prose around connection states is justified operational detail rather than explaining concepts Claude already knows. | 4 / 5 |
Actionability | It provides copy-paste-ready commands for install, login, connection ensure, action search/run with JSON params, and a full proxy-flag table — concrete and executable throughout. | 5 / 5 |
Workflow Clarity | A rough sequence (install → auth → connect → poll → search → run) exists with state-based branching, but the dangling 'Step 2' reference and the lack of explicit validate→fix→retry checkpoints for potentially destructive proxy/action operations leave validation gaps. | 3 / 5 |
Progressive Disclosure | The single SKILL.md is organized into clear sections (Overview, Working with, Install, Auth, Connecting, Searching, Popular actions, Best practices) with no bundle files needed; minor inconsistency from the orphaned '1b' / 'Step 2' labels keeps it just below excellent. | 4 / 5 |
Total | 16 / 20 Passed |