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 executable commands throughout and a clear, checkpointed connection workflow, supported by clean section organization. Its main weaknesses are minor padding in the introductory prose and slightly inconsistent step numbering that muddies the 'Step 2' references.
Suggestions
Trim the opening company-background paragraph and phrases like 'so you can focus on the integration logic rather than auth plumbing' to tighten token efficiency.
Label the 'Searching for actions' section as 'Step 2' (or remove the 'skip to Step 2' references) so the workflow numbering is internally consistent.
Consider moving the proxy flags table and clientAction state-machine detail into a referenced file to improve progressive disclosure for this 150-line skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient, dominated by copy-paste commands, a flags table, and a tight state-machine breakdown, with only minor over-explanation such as the opening company-background paragraph and phrases like 'so you can focus on the integration logic rather than auth plumbing'. | 4 / 5 |
Actionability | It provides fully executable, copy-paste-ready commands for every common case (install, login, connection ensure, action list/run with JSON input, proxy requests) plus a concrete flags table, matching the anchor for fully executable guidance covering common cases. | 5 / 5 |
Workflow Clarity | The install → login → connect → wait → search → run sequence is clear with explicit state-checking checkpoints and a poll-again feedback loop for CLIENT_ACTION_REQUIRED, but 'skip to Step 2' references point to an unlabeled step and numbering is inconsistent ('1b' with no 'Step 2' heading), leaving minor gaps. | 4 / 5 |
Progressive Disclosure | The single SKILL.md is well-organized into clearly headed sections (install, auth, connecting, searching, actions, proxy, best practices) with no nested references, though some inline material like the proxy flags table and clientAction state machine could justify a separate reference file. | 4 / 5 |
Total | 17 / 20 Passed |