Content
92%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.
An exceptionally well-structured body: executable code, an explicit safety contract with validation checkpoints, and clean one-level-deep navigation to real reference files. Only minor conciseness tightening of the version-pin section would improve it.
Suggestions
Condense the 'Verified Baseline' section's version/date detail into a compact pinned-versions table or move it to references/sources.md to reduce token weight on the overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes Claude's competence (no explainers on what OMERO/microscopy is), but the version/date-heavy 'Verified Baseline' section could be trimmed slightly despite being justified as a reproducibility pin. | 4 / 5 |
Actionability | Provides copy-paste-ready uv install commands, a complete exception-safe BlitzGateway snippet with try/finally, and runnable helper invocations covering the common read path. | 5 / 5 |
Workflow Clarity | A destructive/remote skill with explicit validation gates — dry-run-first operating contract, per-write reviewed-target rules, dry-run-by-default helpers gated by --execute, and a final pre-remote review checklist with error-recovery feedback. | 5 / 5 |
Progressive Disclosure | SKILL.md is a clear overview; the Capability Guide maps each topic to a real, one-level-deep reference file (all 9 verified present) with relative-path links, and scripts are listed with concise descriptions. | 5 / 5 |
Total | 19 / 20 Passed |