Content
92%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 a concise, well-organized overview with concrete commands and clear example flows; its main gap is the lack of any executable mechanism (scripts or API calls) showing how Claude actually retrieves data from the named platforms.
Suggestions
Add a brief executable example or reference a script showing how to query at least one platform API (e.g., a curl call or a scripts/ helper) so the actionability is fully copy-paste ready.
Clarify how the slash commands map to underlying API calls, or note that the commands are handled by a bundled script.
If per-platform fetching logic differs, link to short per-platform reference notes under references/ rather than leaving the mechanism implicit.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean with terse command listings, compact platform one-liners, and example flows; it assumes Claude's competence and explains no background concepts, so every token earns its place. | 5 / 5 |
Actionability | Commands like "/markets trump 2028", "/price [market-id or slug]", and "/orderbook [market-id]" are concrete and copy-pasteable, but the actual mechanism for fetching data from each platform's API is absent. | 4 / 5 |
Workflow Clarity | This is a simple, read-only skill under 50 lines; the examples give unambiguous input-to-output flows (query -> search platform -> return price), so the simple-skill exception applies and the single action is clear. | 5 / 5 |
Progressive Disclosure | No bundle files exist and the body is well under 50 lines with clean Commands, Supported Platforms, and Examples sections, satisfying the simple-skill exception for well-organized structure. | 5 / 5 |
Total | 19 / 20 Passed |