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 solid, command-first guide: it covers authentication, connection lifecycle with state-based checkpoints, action discovery and execution, and a proxy fallback with real copy-paste commands. Main weaknesses are padding in the intro/entity sections, inconsistent CLI invocation (`membrane` vs `npx @membranehq/cli`), and broken step references ('Step 2' is referenced but never defined).
Suggestions
Fix the broken navigation: either define a numbered 'Step 2' (e.g. '## Step 2: Search and run actions') or replace 'skip to **Step 2**' with the actual section names.
Trim the marketing intro and the filler lines ('Use action names and parameters as needed', the Agent Types aside), and pick one invocation form (`membrane` vs `npx @membranehq/cli`) and use it consistently.
Expand the skeletal entity overview into one line per entity (Link, Clicks, Workspace, Member, Bundle) describing what each represents, or remove it in favor of pointing to `membrane action list` discovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The bulk is efficient command-driven guidance, but there is unnecessary padding: the marketing sentence "It's used by marketers, businesses, and individuals to shorten, track, and optimize their links", the vague entity list ending "Use action names and parameters as needed", and the ungrammatical Agent Types aside ("Those will be used to adjust tooling to be used best with your harness") could all be trimmed. It fits anchor 3 ('mostly efficient but includes some unnecessary explanation') better than anchor 4, which requires only minor over-explanation. | 3 / 5 |
Actionability | Concrete executable commands cover every phase: `npm install -g @membranehq/cli@latest`, `membrane login`, `membrane connection ensure ... --json`, polling with `--wait`, `membrane action run ... --input '{...}'`, and the proxy flag table. Minor gaps keep it from anchor 5: `membrane` vs `npx @membranehq/cli` are used inconsistently, and 'QUERY' placeholders are left to interpretation. | 4 / 5 |
Workflow Clarity | The install → login → connection → discover → run sequence is clear, and the connection-state section provides real checkpoints with a feedback loop ('After the user completes the action... poll again'). It misses anchor 5 because the body says "skip to **Step 2**" twice but no Step 2 heading exists, leaving the sequence's numbering incoherent. | 4 / 5 |
Progressive Disclosure | No bundle files exist and the single SKILL.md is a well-organized, appropriately sized CLI guide — good structure with clear headers (install, auth, connection, actions, proxy, best practices). It is anchor 4 rather than 5 because of the dangling 'Step 2' references and the inconsistent command invocation, which slightly hinder navigation; the proxy flag table is borderline content that could live in a reference file. | 4 / 5 |
Total | 15 / 20 Passed |