Content
88%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.
An action-dense, well-routed skill body: every subcommand has an exact command, expected JSON fields, and error handling, with validation checkpoints in the interactive flows. Minor gains available from defining a script-path shorthand and splitting per-subcommand response detail into a reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and operational, but the full script path "python3 $PLUGIN_ROOT/skills/mixpanelyst/scripts/auth_manager.py …" is repeated ~15 times where a defined shorthand would do, and the login branch partially repeats the account-add oauth_browser guidance. | 4 / 5 |
Actionability | Fully executable copy-paste commands for every route, exact flags (--region us|eu|in, --token-env VAR), exact JSON field names (result.ok, error.actionable, bridge.account.name), and prescribed output phrasing cover all common cases. | 5 / 5 |
Workflow Clarity | The account-add wizard is a numbered 1–7 sequence with an explicit validation checkpoint ("After the user confirms they ran it, verify with account test… Report success or failure based on the result.ok field"), and session routing handles all four state outcomes including error recovery. | 5 / 5 |
Progressive Disclosure | Good structure with a routing section and clear per-subcommand headers, but all ~250 lines are inline with no bundle files — the per-subcommand JSON-response detail could be offloaded to a reference file to keep SKILL.md an overview. | 4 / 5 |
Total | 18 / 20 Passed |