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.
A well-structured skill body that is lean, executable, and rich in validation checkpoints, with detail correctly deferred to four real reference files and helper scripts. It is a strong example of progressive disclosure for a non-trivial multi-task domain.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean body that assumes Claude's genomics knowledge, avoids explaining what BED/VCF are, and lets every section earn its place; no padded introductory prose. | 5 / 5 |
Actionability | Copy-paste-ready bash commands with concrete arguments and example output tables for convert_coords.py, normalize_variant.py, check_contigs.py, and audit_intervals.py cover the common cases. | 5 / 5 |
Workflow Clarity | Explicit validation checkpoints throughout - REF checked against FASTA first, MISMATCH halts and routes to check_contigs.py, --split before normalising, exit code 1 as a CI gate - with clear error-recovery feedback loops for batch/destructive operations. | 5 / 5 |
Progressive Disclosure | Clear overview body with four well-signaled one-level-deep references (format-conventions, variant-representation, reference-builds, transcript-coordinates), all of which exist as real files, with detailed content appropriately split out of the main file. | 5 / 5 |
Total | 20 / 20 Passed |