Content
80%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is highly actionable and token-efficient, with executable curl examples for every endpoint, but it lacks error-handling/validation feedback loops and keeps the full per-endpoint reference inline rather than progressively disclosing it.
Suggestions
Move the 12 per-endpoint usage blocks into a separate REFERENCE.md and keep SKILL.md as a lean overview with a Capabilities list plus one example, linking out for the rest.
Add a validation step after setup (e.g., a trivial test call to confirm the API key works) and brief error-recovery guidance for common failures like 401/429.
Drop the redundant restatement of the description on line 23 and trim the marketing-style "Use Cases" section to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and functional with no concept-explanation fluff — each endpoint is just parameters plus an executable curl — so nearly every token earns its place despite the repeated header boilerplate being the cost of copy-paste readiness. | 3 / 3 |
Actionability | Every endpoint ships a fully executable curl command with real example values and required-parameter markers, and the setup block provides copy-paste-ready credential extraction, making the guidance directly runnable. | 3 / 3 |
Workflow Clarity | The setup has a clear conditional checkpoint (if credentials are missing, run `npx gooseworks login`), but there is no validation that auth works and no error-handling or feedback loop for API failures such as 401 or rate-limit responses. | 2 / 3 |
Progressive Disclosure | The body is well-sectioned but keeps roughly 200 lines of per-endpoint API reference inline in SKILL.md rather than splitting it into a separate reference file, matching the score-2 anchor of API reference content that could live elsewhere. | 2 / 3 |
Total | 10 / 12 Passed |