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 concrete, executable CLI commands and a clear connection-state workflow, and it stays mostly concise. The main weaknesses are an incomplete 'Popular actions' list relative to the promised overview entities and a stray 'Step 2' reference with no Step 1.
Suggestions
Reconcile the overview (Post/Reply/User/Feed/Notification) with the 'Popular actions' table by documenting actions for each entity or moving the full list to a referenced file.
Fix the orphaned 'Step 2' / '1b' numbering in the connection-ready section so the sequence is coherent.
Consider moving the proxy flag table and action-schema details into a separate reference file to keep SKILL.md a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely efficient with concrete CLI commands and minimal concept explanation, though a few phrasings like 'so you can focus on the integration logic rather than auth plumbing' add light padding. | 4 / 5 |
Actionability | It provides copy-paste-ready membrane CLI commands for install, login, connection setup, action search/run, and proxy requests, covering the common cases with executable flag tables. | 5 / 5 |
Workflow Clarity | The connection setup flow has a clear READY/BUILDING/CLIENT_ACTION_REQUIRED sequence with polling checkpoints, but it is labeled 'Step 2' with no preceding Step 1 and the overview promises five entities while only three actions are documented, leaving minor gaps. | 4 / 5 |
Progressive Disclosure | Content is well sectioned with clear headers and no bundle files to reference, though all reference-style detail (action schemas, proxy options) is inlined rather than split into separate files, keeping it just below the ideal split. | 4 / 5 |
Total | 17 / 20 Passed |