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, actionable reference with a strong connection-state workflow and feedback loops, undermined mainly by prose padding and a couple of broken cross-references. It is solidly above average and would reach the top band by trimming background/editorializing and fixing the dangling Step 2 anchor.
Suggestions
Cut the introductory "RootFi is a SaaS platform..." paragraph and editorializing lines ("This is the fastest way to get a connection," "burn less tokens") that restate concepts Claude can derive from the linked docs.
Fix the dangling "skip to Step 2" reference by labeling the action-discovery section as Step 2 or removing the forward reference, and standardize on either `membrane` or `npx @membranehq/cli` consistently.
Move the proxy flags table and best-practices list into a one-level-deep reference file (e.g. ADVANCED.md) signaled from the body to improve progressive disclosure for this larger-than-50-line skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly command-focused and efficient, but it includes unnecessary prose such as the opening "RootFi is a SaaS platform that helps businesses..." background, editorializing like "This is the fastest way to get a connection," and a padded "Best practices" section, fitting score 3's "mostly efficient but includes some unnecessary explanation." | 3 / 5 |
Actionability | It provides concrete, executable commands throughout (install, login, connection ensure, action list/run, request with a flags table), but minor gaps—the dangling "skip to Step 2" with no labeled Step 2 and mixed membrane/npx invocations—keep it at score 4 rather than fully copy-paste-ready score 5. | 4 / 5 |
Workflow Clarity | The connection flow is clearly sequenced with a state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and explicit poll-after-action feedback loops, but the broken "Step 2" reference and the absence of any verify step after running actions or proxy requests leave minor validation gaps at score 4. | 4 / 5 |
Progressive Disclosure | Content is well-organized into clear sections with no nested references (no bundle files exist), but at ~150 lines the proxy options table and best-practices material are inlined rather than split into one-level-deep reference files, fitting score 4's "good structure; minor organization gaps" over score 5's ideal split. | 4 / 5 |
Total | 15 / 20 Passed |