Content
93%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 exemplary SKILL.md body: lean, executable, and well-organized, with appropriate offloading of secondary stacks to a clearly signaled reference file. The only gap is that verification (checklist, scanning tools) is presented as a list rather than an ordered workflow with a fix-and-rescan loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a lean table, two copy-paste config blocks, a tool list, and a checklist; it explains nothing Claude already knows and every section earns its place, matching anchor 5. | 5 / 5 |
Actionability | Fully executable code for the two most common servers (helmet() Express config and Nginx add_header directives) plus named verification tools — copy-paste ready and covering the common cases, matching anchor 5. | 5 / 5 |
Workflow Clarity | A security-headers checklist and verification tools are present, but there is no explicit implement → verify → fix sequence tying them together; this sits between anchor 4 (most checkpoints, minor gaps) and anchor 5 (explicit feedback loop). | 4 / 5 |
Progressive Disclosure | Common cases (Express, Nginx) stay inline while Python/Apache move to a well-signaled, one-level-deep references/python-apache.md with a bulleted preview of its contents — exactly the anchor-5 pattern. | 5 / 5 |
Total | 19 / 20 Passed |