Content
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, highly actionable command reference that assumes Claude's competence and stays token-efficient. The one real defect is progressive disclosure: the sole referenced bundle file is missing, leaving the 'load for advanced patterns' path broken.
Suggestions
Create ./references/advanced-workflows.md (git integration, shell functions, power workflows) so the referenced 'Additional Resources' path resolves, or remove the pointer if no such file is intended.
Eliminate the minor duplication between the inline code blocks and the Quick Reference table, e.g. keep the table for recall and trim redundant flag comments in the prose sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and code-first with terse inline comments, assuming Claude's competence and avoiding any explanation of what fd/rg/fzf are; the only minor redundancy is the Quick Reference table re-listing commands already shown. | 3 / 3 |
Actionability | Every example is real, executable shell (e.g. 'fd -e py -x rg "async def" {}', 'fd -e ts | fzf -m | xargs code') with specific flags and pipe combinations, copy-paste ready. | 3 / 3 |
Workflow Clarity | This is a simple single-purpose reference skill whose single action (look up a command, run it) is unambiguous and organized into clear per-tool sections; no destructive or batch operations require validation checkpoints. | 3 / 3 |
Progressive Disclosure | The body is a clean overview with a clearly signaled one-level pointer ('For detailed patterns, load: ./references/advanced-workflows.md'), but that referenced file does not exist in the bundle, so navigation leads to a dead end and undermines the disclosure structure. | 2 / 3 |
Total | 11 / 12 Passed |