AgentStack
SKILL verified MIT Self-run

Review

skill-smartwhale8-claude-playbook-review · by smartwhale8

Review all uncommitted changes against project standards before committing

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-smartwhale8-claude-playbook-review

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Review all uncommitted changes in this project. $ARGUMENTS

Process

  1. Gather changes: Run git diff --staged for staged changes, or git diff if nothing is staged. Also check git status for new untracked files.
  1. Check each changed file against the project rules (.claude/rules/*.md):

### Code Quality

  • Is there dead code, unused imports, or commented-out code?
  • Are there bandaid fixes or workarounds instead of root-cause solutions?
  • Is anything over-engineered for what it needs to do?

### Architecture

  • Does this follow existing patterns in the codebase?
  • Is there duplicate logic that should use an existing shared component or utility?
  • Are dependencies pointing in the right direction (inward, not outward)?

### Consistency

  • Does the code match the style and structure of similar files in the project?
  • For frontend: are spacing, colors, and component usage consistent with the rest of the UI?
  • For backend: are error handling, response format, and validation patterns consistent?

### Reuse

  • Could any new component, function, or pattern already exist in the codebase? Search before approving.
  • If something similar exists, flag it — it should be reused or extracted into a shared utility.

### Security

  • Any hardcoded secrets, credentials, or API keys?
  • Is user input validated at the boundary?
  • Are there SQL injection, XSS, or other OWASP risks?

### Performance

  • Any N+1 query patterns (database calls inside loops)?
  • Any unbounded queries missing LIMIT/pagination?
  • Frontend: unnecessary re-renders, missing debounce on inputs?
  1. Verdict: Provide one of:
  • Ready to commit — no issues found
  • Minor issues — list them, but committing is acceptable after acknowledging
  • Needs changes — list specific issues that must be fixed before committing

For each issue, provide: the file, the line(s), what's wrong, and what the fix should be.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.