Content
35%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is well-organized and reasonably concise, but its instructions are abstract rather than executable, the workflow lacks validation checkpoints, and the single referenced resource file does not exist in the bundle.
Suggestions
Add concrete, executable tooling (e.g., 'npm audit --audit-level=high', 'pip-audit', 'osv-scanner .') instead of abstract directives like 'Run vulnerability and license scans'.
Add explicit validation checkpoints to the workflow (e.g., 'After proposing upgrades, run the test suite; only recommend upgrades that pass').
Either create resources/implementation-playbook.md or remove the reference to it, so the signaled progressive-disclosure path actually resolves.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Sections are short and unpadded, but the opening sentence duplicates the frontmatter description verbatim and '$ARGUMENTS' under Requirements is an empty placeholder, so not every token earns its place. | 2 / 3 |
Actionability | Instructions are abstract directives ('Inventory direct and transitive dependencies', 'Run vulnerability and license scans') with no concrete commands, tool names, or executable examples — it describes rather than instructs. | 1 / 3 |
Workflow Clarity | Steps are sequenced (inventory → scan → prioritize → propose upgrades) and the Safety section mentions verifying upgrades in staging, but the main workflow lacks explicit validation checkpoints or fix→retry feedback loops for these batch/risky operations, which caps the score at 2. | 2 / 3 |
Progressive Disclosure | The body signals a one-level-deep reference ('open resources/implementation-playbook.md') which is good structure, but no resources/ directory or bundle file exists, so the referenced path is a broken pointer and navigation fails. | 2 / 3 |
Total | 7 / 12 Passed |