Content
67%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 well-structured, mostly actionable guide built around concrete Membrane CLI commands and a state-based connection workflow, weakened mainly by minor padding and an unlabeled "Step 2" reference.
Suggestions
Trim the introductory explanation of what Resurface is and remove filler phrases ("so you can focus on the integration logic rather than auth plumbing") to improve token efficiency.
Label the post-connection workflow explicitly as "Step 2: Search and run actions" so the repeated "skip to Step 2" references resolve to a real section.
Add one fully-substituted end-to-end worked example (a concrete connectionId and action run) so the action guidance is copy-paste ready without placeholder inference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly concrete commands, but the intro paragraph ("Resurface is an API usage intelligence platform...") and phrases like "so you can focus on the integration logic rather than auth plumbing" are explanatory padding that could be trimmed, fitting the mostly-efficient-but-could-be-tightened anchor rather than the efficient anchor at 4. | 3 / 5 |
Actionability | Provides many concrete, copy-paste-ready commands (install, login, connection ensure, action run, request) plus a flags table, but uses unsubstituted placeholders (CONNECTION_ID, <actionId>, <id>) and offers no full end-to-end worked example, so it is mostly-executable with minor gaps rather than fully copy-paste at 5. | 4 / 5 |
Workflow Clarity | The connection flow is a clear state-machine sequence with explicit checkpoints and a feedback loop (polling after CLIENT_ACTION_REQUIRED until READY), but the text repeatedly says "skip to Step 2" without ever labeling a Step 2, a minor sequencing gap that keeps it below the explicit-checklist anchor at 5. | 4 / 5 |
Progressive Disclosure | The single SKILL.md is well-organized into clear sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) with no bundle files to reference, giving good structure with only minor organization gaps; not a 5 because the detailed clientAction schema and flags table are inlined where a one-level reference could help. | 4 / 5 |
Total | 15 / 20 Passed |