Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
An excellent, dense SKILL.md body: executable commands, a tight rules table, explicit validation (specificity via BLAST), and error-recovery guidance, with the one external reference appropriately offloaded to a real script. No weaknesses to address.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and dense — executable commands with inline parameter notes, a compact rules table, and targeted callouts — and assumes Claude already knows what PCR, primers, and Tm are, with no padding; the 'Why' column earns its place rather than restating known concepts. | 3 / 3 |
Actionability | It provides copy-paste-ready 'tu run' commands with real parameter objects and points to a real, present QC script (scripts/primer_qc.py), matching the fully-executable anchor. | 3 / 3 |
Workflow Clarity | A clear numbered sequence (design → Tm/Ta → rules → specificity → gotchas) includes an explicit validation checkpoint in Step 4 (BLAST before ordering) and error→fix feedback loops in the constraint-quirk block. | 3 / 3 |
Progressive Disclosure | It is a single-purpose skill with well-organized sections and a single one-level-deep bundle reference (scripts/primer_qc.py, verified to exist at the stated path), with no nested references. | 3 / 3 |
Total | 12 / 12 Passed |