Content
50%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 highly actionable with concrete commands and parameter docs, but it is padded with templated boilerplate and duplicated sections, and its workflow lacks an explicit validation checkpoint for batch trimming. Progressive disclosure is undercut by references that do not contain what the body claims.
Suggestions
Remove the 'See ##X above' placeholder lines and merge the duplicated Key Features / Features and Example Usage / Usage sections to reduce padding.
Add an explicit validate-then-proceed step to the Workflow (e.g. run --check-only and confirm key statistics are preserved before returning the trimmed abstract).
Either populate references/guidelines.md with the three documents the body claims (compression strategies, protected elements, journal word limits) or correct the body's reference list to match the actual file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Noticeably verbose: templated 'See ##X above' placeholders, the description repeated verbatim as a trigger, duplicated Key Features vs Features sections, and a stale past 'Next Review Date' not placed in a deprecated section, matching anchor 2. | 2 / 5 |
Actionability | Provides concrete executable commands with real example text, a full parameter table, a strategy table, and output-format examples, leaving only minor gaps such as unsupplied input files, matching anchor 4. | 4 / 5 |
Workflow Clarity | A five-step sequence is present but lacks an explicit output-validation checkpoint, and batch operations are featured, so the batch/destructive guideline caps workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | The bundle is one level deep and signaled (references/guidelines.md, scripts/main.py), but the body over-claims reference contents and inlines material that belongs in references, matching anchor 3. | 3 / 5 |
Total | 12 / 20 Passed |