Content
75%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 highly actionable with concrete, executable CLI commands and a well-validated connection workflow. Its main weaknesses are a redundant intro/concept explanation and a duplicated action-discovery section, plus a broken 'Step 2' cross-reference.
Suggestions
Remove or condense the opening 'Reclaim is a time management and scheduling tool...' paragraph, which restates general knowledge Claude already has.
Merge the 'Searching for actions' and 'Popular actions' sections, which both demonstrate `membrane action list --intent=QUERY`, into one discovery section.
Fix the 'skip to Step 2' reference — there is no labeled Step 2 — by either numbering the steps explicitly or pointing to a concrete section heading.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with concrete CLI commands, but it opens by explaining what Reclaim is ('Reclaim is a time management and scheduling tool that integrates with your calendar...') which Claude largely knows, and the 'Searching for actions' and 'Popular actions' sections duplicate the same discovery command, so it could be tightened. | 3 / 5 |
Actionability | Provides fully executable, copy-paste-ready membrane CLI commands (login, connection ensure, action run, request) with a complete flag table and JSON-output examples covering the common cases, matching the 'fully executable; copy-paste ready' anchor. | 5 / 5 |
Workflow Clarity | The connection flow is clearly sequenced with explicit validation checkpoints (poll --wait, state checks for READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a feedback loop (re-poll after the user acts), but the 'skip to Step 2' reference points to a non-existent Step 2, leaving a minor navigation gap. | 4 / 5 |
Progressive Disclosure | The single SKILL.md is well-organized with clear section headers and no nested references, and there are no bundle files to navigate; over 50 lines so the simple-skill exception does not apply, but structure and placement are good with only minor gaps (duplicated discovery section). | 4 / 5 |
Total | 16 / 20 Passed |