Content
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that clearly defines research standards and output expectations. Its main weakness is the lack of concrete examples—a sample executive summary, a TAM calculation walkthrough, or a competitor analysis snippet would significantly improve actionability. The quality gate is a good validation mechanism but the research modes lack workflow sequencing for handling ambiguity or conflicting data.
Suggestions
Add a concrete example of at least one research mode output (e.g., a brief sample competitive analysis or TAM estimate with sources) to make the skill more actionable and copy-paste ready.
Include guidance on what to do when data is conflicting, unavailable, or stale—a feedback loop for research iteration would improve workflow clarity.
Consider adding a brief example of the output format filled in for a specific scenario to show the expected level of detail and source attribution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section earns its place—no unnecessary explanations of what market research is or how Claude should think about it. Bullet points are tight and directive. | 3 / 3 |
Actionability | The skill provides clear checklists of what to collect and what to include, but lacks concrete examples—no sample output, no example TAM calculation, no template showing what a completed deliverable looks like. It describes what to do rather than showing it. | 2 / 3 |
Workflow Clarity | The output format section provides a clear sequence, and the quality gate serves as a validation checkpoint. However, the research modes are presented as independent collection lists without sequencing or feedback loops—there's no guidance on how to iterate when sources conflict or data is insufficient. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but everything is inline in a single file. The four research modes could benefit from being split into separate reference files, especially if they were fleshed out with examples. For the current length (~80 lines) it's borderline acceptable but the research modes add bulk that could be externalized. | 2 / 3 |
Total | 9 / 12 Passed |