Skip to main content
skill CX Codex

shell-review — Claude Code skill: what it does, how to install

shell-review audits shell scripts for masked exit codes, POSIX portability, and unsafe patterns before committing code.

MIT 1 installs ★ 350 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add athola/claude-night-market --skill shell-review -a claude-code
Open on GitHub

What shell-review does

Reviews CI pipelines, Git hooks, and automation scripts matching **/*.sh. The skill checks whether pipelines lose failure statuses, flags Bash-specific syntax inside #!/bin/sh files, and detects unquoted variables or unsafe directory changes.

Execution relies on internal modules imbue:proof-of-work, imbue:review-core, and imbue:structured-output. Each issue gets linked to an exact file location and written to .review/findings.json, while unverified findings get tagged as UNVERIFIED or discarded.

What it helps with

  • Detect masked exit codes inside command pipelines
  • Catch Bash-specific syntax in scripts targeting POSIX #!/bin/sh
  • Spot unquoted variables and risky subshell directory operations
  • Validate Git hooks and CI automation scripts prior to committing changes

Example prompts for the agent

  • /shell-review scripts/deploy.sh
  • Run an audit on scripts/pre-commit.sh for masked errors and Bash-isms
  • /shell-review ci/build.sh

How to install shell-review

1Skills CLI (Vercel)

npx skills add athola/claude-night-market --skill shell-review -a claude-code

2Manually: put the files in place

~/.claude/skills/shell-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/shell-review/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about shell-review

How to install shell-review in Claude Code?

Run npx skills add athola/claude-night-market --skill shell-review -a claude-code.

What does shell-review audit?

It examines *.sh files for masked pipeline errors, POSIX compatibility under #!/bin/sh, unquoted variables, and function layout.

How are review findings validated?

Findings are recorded in .review/findings.json alongside exact code snippets and confirmed via imbue:review-core checks.

Source text

SKILL.md · MIT
---
name: shell-review
description: Audits shell scripts for correctness, portability, and common pitfalls. Use when reviewing shell scripts or before committing shell changes.
globs: "**/*.sh"
alwaysApply: false
  Use when reviewing shell scripts, CI scripts, hook scripts, wrapper scripts. Do
  not use when creating new scripts - use attune:workflow-setup.
category: build
tags:
- shell
- bash
- posix
- scripting
- ci
- hooks
tools: []
complexity: intermediate
model_hint: standard
estimated_tokens: 200
progressive_loading: true
dependencies:
- imbue:proof-of-work
- imbue:review-core
- imbue:structured-output
modules:
- modules/exit-codes.md
- modules/portability.md
- modules/safety-patterns.md
- modules/structure-patterns.md
role: entrypoint
---

# Shell Script Review

Audit shell scripts for correctness, safety, and portability.

## Verification

After review, run `shellcheck <script>` to verify fixes address identified issues.

## Testing

Run `pytest plugins/pensive/tests/skills/test_shell_review.py -v` to validate review patterns.

## Quick Start

```bash
/shell-review path/to/script.sh
```

## When To Use

- CI/CD pipeline scripts
- Git hook scripts
- Wrapper scripts (run-*.sh)
- Build automation scripts
- Pre-commit hook implementations

## When NOT To Use

- Non-shell scripts (Python, JS, etc.)
- One-liner commands that don't need review

## Required Progress Items

1. `shell-review:context-mapped`
2. `shell-review:exit-codes-checked`
3. `shell-review:portability-checked`
4. `shell-review:safety-patterns-verified`
5. `shell-review:structure-checked`
6. `shell-review:evidence-logged`
7. `shell-review:findings-verified`

## Workflow

### Step 1: Map Context (`shell-review:context-mapped`)

Identify shell scripts:
```bash
# Find shell scripts
find . -not -path "*/.venv/*" -not -path "*/__pycache__/*" \
  -not -path "*/node_modules/*" -not -path "*/.git/*" \
  -name "*.sh" -type f | head -20
# Check shebangs
rg -l "^#!/" scripts/ hooks/ 2>/dev/null | head -10
# fallback: grep -l "^#!/" scripts/ hooks/ 2>/dev/null | head -10
```

Document:
- Script purpose and trigger context
- Integration points (make, pre-commit, CI)
- Expected inputs and outputs

### Step 2: Exit Code Audit (`shell-review:exit-codes-checked`)

@include modules/exit-codes.md

### Step 3: Portability Check (`shell-review:portability-checked`)

@include modules/portability.md

### Step 4: Safety Patterns (`shell-review:safety-patterns-verified`)

@include modules/safety-patterns.md

### Step 5: Structure Patterns (`shell-review:structure-checked`)

@include modules/structure-patterns.md

### Step 6: Evidence Log (`shell-review:evidence-logged`)

Use `imbue:proof-of-work` to record findings with file:line references.

Summarize:
- Critical issues (failures masked, security risks)
- Major issues (portability, maintainability)
- Minor issues (style, documentation)

## Output Format

```markdown
## Summary
Shell script review findings

## Scripts Reviewed
- [list with line counts]

## Exit Code Issues
### [E1] Pipeline masks failure
- Location: script.sh:42
- Anchor: `verbatim source text at file:line`
- Pattern: `cmd | grep` loses exit code
- Fix: Use pipefail or capture separately

## Portability Issues
[cross-platform concerns]

## Safety Issues
[unquoted variables, missing set flags]

## Recommendation
Approve / Approve with actions / Block
```

## Verify Findings Are Grounded (`shell-review:findings-verified`)

Write findings to `.review/findings.json`, run the citation verifier
(`Skill(imbue:review-core)` Step 5), and drop or label `UNVERIFIED` any
the verifier rejects.

## Exit Criteria

- [ ] Exit code propagation verified (pipelines checked for pipefail or
  capture-and-check)
- [ ] Portability issues documented (Bash-isms in `#!/bin/sh` scripts flagged)
- [ ] Safety patterns verified (no echo, braced vars, `:?` expansion, cd in
  subshells, no basename/dirname)
- [ ] Structure patterns verified (library/executable distinction, main call,
  preamble, depcheck, shfmt formatting)
- [ ] Evidence logged with file:line references via `imbue:proof-of-work`
- [ ] Every reported finding carries a `Location` + verbatim `Anchor`
  confirmed by `citation_verifier.py` (exit `0`), or unverified findings
  were dropped or labeled `UNVERIFIED`

© athola · MIT · athola/claude-night-market

Similar skills

All skills for Code review and refactoring →

From the same set7

Project sponsors

Companies that keep this analytics open