Content
86%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.
A well-organized, token-efficient body that uses progressive disclosure effectively and includes a mandatory validation gate. Adding one or two inline worked command examples and an error-recovery loop would push it to full marks.
Suggestions
Add 1-2 concrete worked command examples for the most common operations (e.g. a 'map' and a 'interactions' call with real flags) so the body is copy-paste ready without opening a reference file.
Include a brief error-recovery feedback loop (e.g. what to do on API errors, rate limits, or empty result sets) to strengthen workflow validation for batch/remote operations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and directive throughout, assumes Claude's competence, and never pads with explanations of what STRING/PPIs/libraries are; every section earns its place. | 5 / 5 |
Actionability | Provides a concrete runnable invocation ('uv run scripts/string_cli.py <command> [options] --output /tmp/out.tsv'), but only a generic template rather than specific copy-paste worked examples for common commands, which live in the reference files. | 4 / 5 |
Workflow Clarity | Clear ordered workflow with an explicit validation checkpoint (MANDATORY species confirmation before proceeding) and a map-identifiers-first step, but no error-recovery feedback loops for API failures or retries. | 4 / 5 |
Progressive Disclosure | A concise overview with four well-signaled, one-level-deep reference links, each annotated with a clear one-line purpose; all referenced files exist in references/ and content is appropriately split by feature domain. | 5 / 5 |
Total | 18 / 20 Passed |