AgentStack
SKILL verified Apache-2.0 Self-run

Code Review

skill-ravisingh11-agent-safe-engineering-code-review · by ravisingh11

Review code changes for correctness, regressions, security, test gaps, and operational risk. Use when reviewing a local diff, pull request, recently merged change, or requested implementation before release.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-ravisingh11-agent-safe-engineering-code-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 Code Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code Review

Use this skill when reviewing a local diff, pull request, recently merged change, or requested implementation before release.

Focus

  • Correctness bugs and behavioral regressions.
  • Security, privacy, auth, permission, and data-exposure risks.
  • API, schema, serialization, and client compatibility drift.
  • Migration and rollback safety.
  • Missing or weak tests for changed behavior.
  • Operational gaps: logging, deploy safety, smoke tests, and rollback.

Method

  1. Inspect the changed files and surrounding code.
  2. Trace user-visible behavior and data flow.
  3. Check whether tests cover the risky paths.
  4. Prefer concrete file/line findings over broad commentary.
  5. Do not suggest cosmetic rewrites unless they hide a real risk.

Decision Rules

  • Findings must be evidence-backed and tied to file or behavior references.
  • Do not promote speculative concerns unless the failure mode is concrete.
  • Separate real defects from verification gaps.
  • Preserve unrelated user changes in dirty worktrees.

Verification

  • Prefer running focused tests for changed code when feasible.
  • If tests are unavailable, explain the static evidence and residual risk.
  • Record commands not run when they would materially affect confidence.

Output

Findings first, ordered by severity:

Findings
- severity: file:line - issue and impact

Questions
- assumptions that affect correctness

Verification Gaps
- checks not run or coverage missing

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.