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, highly actionable CLI integration guide: concrete commands, a state-machine-driven connection workflow with polling and re-auth feedback loops, and a useful proxy fallback with a full options table. Weaknesses are moderate redundancy (duplicated discovery command, an empty 'Popular actions' section, a dangling 'Step 2' reference) and an intro paragraph that explains context Claude does not strictly need.
Suggestions
Populate 'Popular actions' with a handful of real action ids for the core entities (candidates, jobs, tasks) or remove the heading and keep a single action-discovery section.
Fix the dangling 'skip to **Step 2**' reference by numbering the workflow steps explicitly (1. Connect, 2. Discover actions, 3. Run or proxy).
Trim the ATS explainer paragraph and the duplicated 'action list' command, and tighten the Best practices commentary to bare imperative rules.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean commands, but includes removable padding: an intro paragraph explaining what an ATS is ('an applicant tracking system (ATS) used by HR departments...'), the same action-list command shown twice ('membrane action list --intent' in 'Searching for actions' and 'npx @membranehq/cli@latest action list --intent' in 'Popular actions'), and rationale commentary ('This will burn less tokens and make communication more secure'). This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') rather than 4, since the redundancy goes beyond minor trimming. | 3 / 5 |
Actionability | Nearly every section gives copy-paste executable commands: 'npm install -g @membranehq/cli@latest', 'membrane login --tenant --clientName=<agentType>', 'membrane connection ensure "https://www.clockworkrecruiting.com/" --json', 'membrane action run <actionId> --connectionId=... --input ...', plus a complete proxy options table. It stops short of anchor 5 because the 'Popular actions' section lists no actual action ids and no concrete end-to-end example for a common Clockwork Recruiting use case is shown. | 4 / 5 |
Workflow Clarity | The setup sequence is clear with explicit state-based checkpoints: poll with '--wait' until state leaves 'BUILDING', handle 'CLIENT_ACTION_REQUIRED' via a feedback loop ('After the user completes the action... poll again'), and check the 'error' field on 'CONFIGURATION_ERROR'/'SETUP_FAILED'. It is not anchor 5 because the instructions say 'skip to **Step 2**' yet no step is ever labeled Step 2 and the overall sequence is not numbered, leaving minor sequencing ambiguity. | 4 / 5 |
Progressive Disclosure | The single-file skill is well organized with clear headed sections (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) and no nested references, with bulk API detail delegated to dynamic CLI discovery rather than inlined. Minor gaps — the underdeveloped 'Popular actions' section and the duplicated command — keep it at anchor 4 rather than 5. | 4 / 5 |
Total | 15 / 20 Passed |