Content
81%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, highly actionable skill body with genuine expert content (version-migration caveats, normalization selection, validation-first workflows) and clean one-level-deep references that all exist. Its main weakness is verbosity in the second half — response-style sections and reminder lists that restate earlier guidance and inflate the SKILL.md beyond overview size.
Suggestions
Cut or collapse 'Handling User Requests', 'Example Interactions', and 'Key Reminders' — they restate Best Practices or instruct Claude on behavior it can infer.
Replace the per-file 'Reference Documentation' section with the inline 'Use this reference when' pointers already present, removing the duplicated navigation.
De-duplicate the normalization quick-selection guide (currently listed twice within the same section) and keep only the inline genome-size table or the reference-file table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The bulk of the body is dense, non-obvious domain guidance (4.0 migration flags, normalization selection, effective genome sizes, SAM-flag filtering) that earns its tokens. However, sections like 'Handling User Requests', 'Example Interactions', and 'Key Reminders' largely restate Best Practices or instruct Claude on response styles it can infer, and 'Reference Documentation' re-describes files already pointed to inline — noticeable padding that could be trimmed. | 3 / 5 |
Actionability | Guidance is fully executable throughout: copy-paste bash for installation, validate_files.py and workflow_generator.py invocations with real flags, troubleshooting commands (samtools index, --region chr1), and exact --effectiveGenomeSize values. Concrete examples cover the common cases (ChIP-seq QC, BAM conversion, heatmap creation, sample comparison). | 5 / 5 |
Workflow Clarity | Sequences are explicit and validation-first: Quick Start mandates validate_files.py before any analysis, workflow generation includes a 'Review the generated script before running' checkpoint, and the Validation Errors + Troubleshooting sections provide feedback loops for error recovery. Validation is present for the batch operations, so no cap applies. | 5 / 5 |
Progressive Disclosure | All referenced bundle paths (references/core_workflows.md, workflows.md, tools_reference.md, normalization_methods.md, effective_genome_sizes.md, review.md; assets/quick_reference.md; both scripts) exist and are signaled one level deep with 'Use this reference when' guidance — strong navigation. The score stops short of 5 because the body itself runs ~420 lines with some content duplicated between inline summaries and references (e.g., the genome-size table, normalization quick guide listed twice), and the 'Reference Documentation' section repeats pointers already made in context. | 4 / 5 |
Total | 17 / 20 Passed |