Content
35%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable structural framework for Bash script review but critically lacks actionable, executable content. There are no code examples, no shellcheck command invocations, no strict-mode boilerplate (`set -euo pipefail`), and no concrete quoting fix demonstrations. The skill reads more like a process outline than a teaching document that would help Claude perform Bash hygiene tasks effectively.
Suggestions
Add concrete, executable examples: a strict-mode boilerplate snippet, a before/after quoting fix, and an exact shellcheck invocation command (e.g., `shellcheck -x -s bash script.sh`).
Replace the abstract workflow bullets with specific steps showing what to check and how, e.g., 'Verify shebang matches target shell: `head -1 script.sh` should show `#!/usr/bin/env bash`'.
Add at least one complete worked example showing input (buggy script snippet) and output (fixed script with explanation of the fix).
Consolidate the 'Avoid' and 'Anti-Patterns' sections to reduce redundancy and free tokens for actionable content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some meta-commentary and philosophical framing ('Philosophy', 'Anti-Patterns') that Claude doesn't need. Sections like 'Avoid' and 'Anti-Patterns' overlap conceptually. The 'Inputs' and 'Outputs' sections are terse but read more like a schema stub than actionable guidance. | 2 / 3 |
Actionability | The skill lacks any concrete code, commands, or executable examples. The workflow is described abstractly ('Check strict mode, quoting, arrays, traps, paths, and temporary files') without showing what to check or how. The examples section lists user prompts but provides no corresponding outputs or code patterns. There are no shellcheck invocation examples, no strict-mode boilerplate, no quoting fix demonstrations. | 1 / 3 |
Workflow Clarity | The workflow section provides a reasonable sequence (identify shell, check issues, run shellcheck, report fixes) and the validation section includes a fail-fast gate. However, the steps are vague and lack explicit validation checkpoints between them. For a skill involving potentially destructive shell operations, the absence of concrete validation commands and feedback loops is a gap. | 2 / 3 |
Progressive Disclosure | The skill references multiple external files (contract.yaml, evals.yaml, task-profile.json, deferred context directory) with clear paths, which is good structure. However, no bundle files were provided to verify these references exist, and the main content itself is thin enough that the references feel like they're compensating for missing substance rather than appropriately splitting detailed content. | 2 / 3 |
Total | 7 / 12 Passed |