Content
85%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-architected skill body: executable quick-start code, a decision table, a sequenced multi-step workflow with embedded correctness checks, and clean progressive disclosure to three real reference files. Slightly verbose in the pitfalls/integration sections but genuinely actionable throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Efficient and assumes competence — no padding about what enrichment or a p-value is — but the Common Pitfalls and Integration sections and repeated library lists add some length that could be trimmed without loss. | 4 / 5 |
Actionability | Provides copy-paste-ready, executable code for ORA and preranked GSEA, a decision table mapping situation to tool, and a runnable helper script with concrete CLI invocations covering the common cases. | 5 / 5 |
Workflow Clarity | An explicit 8-step Core Workflow is clearly sequenced with validation built into steps (ID check, background, adjusted-p filtering), but checkpoints are advisory rather than gated 'stop and verify' feedback loops as in the anchor-5 example. | 4 / 5 |
Progressive Disclosure | SKILL.md is a lean overview with a Reference Files section signaling three real one-level-deep files (gseapy.md, databases-and-gene-sets.md, interpretation.md) and a bundled script; all referenced paths exist and navigation is clear. | 5 / 5 |
Total | 18 / 20 Passed |