Content
61%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 Membrane CLI commands and a solid connection-state feedback loop, but it loses conciseness to a marketing-style intro and lacks validation checkpoints for destructive action/proxy operations. It is well-structured for a single-file skill though no reference files are used.
Suggestions
Cut the opening "Dataddo is a no-code data integration platform... used by data analysts, marketers..." paragraph, which explains background Claude already knows.
Add a verification step after `membrane action run` and after proxy requests (e.g. check the response status/error field and retry or surface failures) to support destructive operations.
Consider moving the proxy flags table and clientAction field reference into a separate reference file to keep SKILL.md a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient commands and tables, but the opening marketing paragraph ("no-code data integration platform... used by data analysts, marketers...") and explanatory prose like "This is the fastest way to get a connection" add unnecessary context Claude does not need, fitting the mostly-efficient-but-could-be-tightened anchor. | 3 / 5 |
Actionability | It provides concrete, copy-paste-ready commands throughout (npm install, membrane login, connection ensure, action run with --input JSON, proxy flags table), matching the mostly-executable anchor; minor gaps are the unsubstituted placeholders (CONNECTION_ID, QUERY) and the duplicated search command in "Popular actions". | 4 / 5 |
Workflow Clarity | The connection flow has a clear poll/feedback loop (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with re-poll), but running actions and proxy requests (which support destructive DELETE/PUT methods) lack validation or verification checkpoints, so per the destructive-operations cap workflow clarity cannot exceed 3. | 3 / 5 |
Progressive Disclosure | It is a single, well-organized file with clear section headers (Install, Auth, Connecting, Searching, Running, Proxy, Best practices) and no nested references, fitting the good-structure anchor; it scores below 5 only because no content is split into reference files and some inline detail (e.g. clientAction sub-fields, proxy flag table) could live separately. | 4 / 5 |
Total | 14 / 20 Passed |