Content
100%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 an efficient, executable guide: complete commands, a rules checklist, a working QC script, an explicit specificity validation step, and error-recovery guidance for the tool's constraint quirks. Structure is clean with a single well-signaled bundle reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and dense with non-obvious, task-specific knowledge (constraint quirks, Tm-method caveats, specificity warning) and never pads with concepts Claude already knows; tables and callouts carry information efficiently. | 5 / 5 |
Actionability | Provides fully executable, copy-paste-ready `tu run` commands with complete JSON arguments for both primer design and Tm calculation, plus a runnable QC script with documented usage covering the common cases. | 5 / 5 |
Workflow Clarity | A clear five-step sequence (design → Tm/Ta → rules → specificity → gotchas) with an explicit validation step (QC script in Step 3, genome-specificity check in Step 4) and a feedback loop mapping concrete error messages to fixes in the constraint-quirk callout. | 5 / 5 |
Progressive Disclosure | Well-organized overview with clearly signaled, one-level-deep reference to the real bundle file `scripts/primer_qc.py` (verified present); detailed QC logic is offloaded to the script rather than inlined, and there are no nested references. | 5 / 5 |
Total | 20 / 20 Passed |