Content
56%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.
The body contains genuinely executable ripgrep examples but is weighed down by large amounts of generic boilerplate and two broken/orphaned bundle references. Tightening the template sections and fixing the script link would substantially improve it.
Suggestions
Remove or collapse the generic template sections (Required Inputs, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Quick Validation) and keep only ripgrep-specific guidance to cut padding.
Fix the script reference: replace `python scripts/test_skill.py` with the actual file `python scripts/validate_skill.py --check`, and update the Dependencies section to match.
Link `references/quick-reference.md` from the body (e.g., under Key Features or a Quick Reference section) so the bundled reference file is discoverable rather than orphaned.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Beyond the useful Example Usage, roughly two-thirds of the body (Required Inputs, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Quick Validation, Scope Reminder) is generic template boilerplate that restates what Claude already knows rather than ripgrep specifics. | 2 / 5 |
Actionability | The Example Usage block gives copy-paste ready rg commands covering the common cases, but `python scripts/test_skill.py` references a script that does not exist (the bundle contains `validate_skill.py`), so one example is not executable. | 4 / 5 |
Workflow Clarity | As a simple read-only skill the single search action is unambiguous and the example includes a pre-check (`rg --version`), but the generic 'Recommended Workflow' section adds no search-specific sequencing or checkpoints. | 4 / 5 |
Progressive Disclosure | Section structure is reasonable, but `references/quick-reference.md` is never linked from the body and the only script reference points to the non-existent `test_skill.py` instead of the real `validate_skill.py`, so references are present but not clearly signaled. | 3 / 5 |
Total | 13 / 20 Passed |