Content
78%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 delivers highly actionable, executable CLI guidance with a clear connection workflow and validation through state polling, but it is a monolithic file with no progressive disclosure into reference materials.
Suggestions
Move the long flat list of Jobber entities into a separate references file and keep SKILL.md focused on the integration workflow.
Add an explicit validate-fix-retry note for CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR paths to strengthen the feedback loop.
Trim the entity-name block to the core object model used in common actions, deferring the full list to a reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean with executable CLI commands and a compact flag table, though the long flat list of Jobber entity names and a few explanatory sentences could be trimmed. | 4 / 5 |
Actionability | It provides fully executable, copy-paste-ready commands (install, login, connection ensure/get, action list/run, request proxy) with concrete flags and a complete options table covering the common cases. | 5 / 5 |
Workflow Clarity | The connection flow is clearly sequenced with state-driven branching (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and explicit polling, though not every error path has a validate-fix-retry loop. | 4 / 5 |
Progressive Disclosure | It is a single well-sectioned SKILL.md with no bundle files to split into, but the long inline entity list and connection-state reference could arguably live in separate reference files, leaving organization only modestly split. | 3 / 5 |
Total | 16 / 20 Passed |