Content
82%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 copy-paste-ready Membrane CLI commands and a clear connection-readiness feedback loop. Its weak spots are minor: light padding in the intro, a dangling 'Step 2' reference, and slight redundancy between the 'Searching for actions' and 'Popular actions' sections.
Suggestions
Resolve the dangling 'Step 2' references by labeling explicit numbered steps (Step 1 connect, Step 2 search/run) so the workflow reads as a checklist.
Trim the POS introductory paragraph and 'rather than auth plumbing' filler to tighten conciseness toward a 5.
Merge or differentiate the 'Popular actions' and 'Searching for actions' sections to remove the duplicated `action list` command and improve navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean and command-focused with executable snippets throughout; only minor over-explanation ('Storyous is a point-of-sale (POS) system...', 'rather than auth plumbing') could be trimmed. It is efficient with minor padding, matching the 4 anchor rather than the pristine 5 or the noticeably-verbose 3. | 4 / 5 |
Actionability | It provides copy-paste-ready executable commands for every common case — install (`npm install -g @membranehq/cli@latest`), login, `connection ensure`, `connection get --wait`, `action list`, `action run`, `request` — plus a flag table. This matches the 'fully executable; copy-paste ready' 5 anchor. | 5 / 5 |
Workflow Clarity | The install → authenticate → connect → poll-until-ready → handle client action → search → run sequence is clear, with an explicit feedback loop (poll state, act on CLIENT_ACTION_REQUIRED, re-poll) and error-state handling. It falls short of 5 because of a dangling 'Step 2' reference and the absence of an explicit numbered checklist, and the destructive/batch cap does not apply to this setup workflow. | 4 / 5 |
Progressive Disclosure | No bundle files exist (references/scripts/assets absent); the single SKILL.md is well-sectioned into Overview, Auth, Connecting, Searching, Actions, Proxy, Best practices. Structure is good with minor gaps — the 'Popular actions' section repeats the `action list` command from 'Searching for actions' — matching the 4 anchor rather than a pristine 5 or a structure-poor 3. | 4 / 5 |
Total | 17 / 20 Passed |