Content
87%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, highly actionable skill with copy-paste commands and a well-organized section structure. The only notable gap is the lack of an explicit validation/retry feedback loop for the batch pipeline, which caps workflow clarity.
Suggestions
Add a validate→fix→retry loop, e.g. after the QC Gates list: "If a sample fails a gate, rerun with adjusted parameters (e.g. --min-mapping-quality) and re-review before proceeding."
Number the route steps (preflight → run → QC Gates review → outputs) to make the sequence explicit rather than leaving it implied by section order.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean imperative/bulleted body with no explanation of concepts Claude already knows (no "ATAC-seq is a technique that..." preamble); every section earns its place, matching the lean-and-efficient anchor. | 3 / 3 |
Actionability | Provides three fully executable, copy-paste-ready bash commands with concrete flags and paths (ngs_preflight.py, run_fastq_assay_package.py, run_atacseq_peaks_qc.py) plus the nf-core invocation, not pseudocode. | 3 / 3 |
Workflow Clarity | Has a sequenced route and a QC Gates checklist with a "Do not proceed to differential accessibility if..." gate, but no validate→fix→retry feedback loop, which the scoring notes say should cap batch-operation workflows at 2. | 2 / 3 |
Progressive Disclosure | No bundle files exist and the body is organized into clear single-purpose sections (Essential Inputs, Route, QC Gates, Outputs) with no nested references or monolithic wall of text. | 3 / 3 |
Total | 11 / 12 Passed |