Content
61%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 concise and well-structured with useful command and output templates, but it stops at illustrative patterns rather than executable retrieval guidance and lacks a sequenced workflow with validation. Providing real data-source access and a stepped research process would lift actionability and workflow clarity.
Suggestions
Add concrete, executable data-retrieval steps or scripts for base-rate lookups (e.g., specific datasets, APIs, or commands to fetch FEC/Cook data) rather than only command-syntax templates.
Define a sequenced research workflow with explicit checkpoints (gather sources → compute base rate → cross-check resolution rules → cite sources) instead of a flat reference layout.
Move the worked Output Format example into a references/ file or trim it to a compact schema so the main body stays a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean, well-organized content with no over-explanation of concepts Claude already knows; only minor padding in the worked output-format example keeps it just below anchor 5. | 4 / 5 |
Actionability | Provides command-syntax templates and an output template, but no executable code, real data-retrieval steps, or concrete source access — guidance is pattern-level rather than copy-paste ready, matching anchor 3. | 3 / 5 |
Workflow Clarity | Content is a sectioned reference (Commands, Research Areas, Examples, Output Format) rather than a sequenced workflow, with no validation checkpoints; anchor 3 fits the present-but-checkpoints-missing case. | 3 / 5 |
Progressive Disclosure | Single self-contained file with no bundle files present and clear section headers; slightly over 50 lines and with examples inlined that could be split out, fitting anchor 4 rather than 5. | 4 / 5 |
Total | 14 / 20 Passed |