Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable and well-organized, with concrete commands for each operation. Its main gaps are mild redundancy and the lack of explicit validation checkpoints around destructive operations.
Suggestions
Add an explicit confirmation/verification step to destructive operations (e.g., a guard that checks the path exists and prompts before `rm -rf`).
Consolidate the duplicated per-tool listing: either the `ls` block or the `echo` count block, not both, to tighten token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean tables and commands, but repeats content: per-tool `ls` lines followed by per-tool `echo` count lines, and a 'Skill File Format' example that restates the path tables; it could be tightened, ruling out 3. | 2 / 3 |
Actionability | It provides concrete, copy-paste-ready bash commands for every operation (mkdir, cp, mv, rm -rf, find, grep), fully executable and specific, matching the 'fully executable code/commands' anchor. | 3 / 3 |
Workflow Clarity | Operations are clearly grouped, but destructive operations like `rm -rf ~/.cursor/skills/my-skill` have only an out-of-band guideline ('Always confirm before deleting') with no in-flow validation checkpoint, capping workflow clarity at 2 per the rubric. | 2 / 3 |
Progressive Disclosure | No bundle files exist and the skill is a self-contained, well-sectioned reference (Supported Tools, File Format, Operations, Guidelines) with no nested references, so the well-organized-sections allowance applies. | 3 / 3 |
Total | 10 / 12 Passed |