Content
60%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 skill delivers executable CLI guidance and a clear connection workflow, but it is dragged down by a massive inline entity catalog that violates progressive disclosure and adds token bloat.
Suggestions
Move the full entity-type list into a references/entities.md file and keep only a short representative sample in SKILL.md with a pointer.
Add an explicit error-recovery checkpoint for the connection flow (e.g. on CONFIGURATION_ERROR: read the error field, remediate, re-run ensure).
Replace CONNECTION_ID placeholders with a note on where the value comes from so commands are fully runnable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The prose instructions are reasonably tight, but the ~170-line bulleted enumeration of every Workamajig entity type (Project through Zip Code) is padding that Claude does not need pre-loaded. | 3 / 5 |
Actionability | It provides concrete, copy-paste-ready commands for install, login, connection ensure, action list/run, and proxy requests with a flags table, with only minor placeholders like CONNECTION_ID. | 4 / 5 |
Workflow Clarity | The connection flow is clearly sequenced with state-based branching (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and an explicit polling loop with --wait, though it lacks a formal validate-fix-retry feedback loop. | 4 / 5 |
Progressive Disclosure | No bundle files exist and all content is inlined; the large entity-type catalog clearly belongs in a separate reference file but is dumped directly into SKILL.md, burying the actionable content. | 2 / 5 |
Total | 13 / 20 Passed |