Skip to content
Skills Library
Programming · Review & audit

code-review

/code-review

Use to review diffs without editing code. Focus on bugs, regressions, security risks, data loss, missing validation, missing tests, and performance risks.

Licence
MIT
Last repository change
05.10.2026

Assessment and security

91/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content26 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 05.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use to review diffs without editing code. Focus on bugs, regressions, security risks, data loss, missing validation, missing tests, and performance risks.

Arguments

/code-review [files or diff scope (optional — defaults to recent changes)]
Original author description

Use to review diffs without editing code. Focus on bugs, regressions, security risks, data loss, missing validation, missing tests, and performance risks.

How it works

SKILL.md has no level-two headings · 19 lines, 254 words

SKILL.md preview
---
name: code-review
description: Use to review diffs without editing code. Focus on bugs, regressions, security risks, data loss, missing validation, missing tests, and performance risks.
allowed-tools: Read, Grep, Glob, Bash
disallowed-tools: Edit, Write, NotebookEdit
when_to_use: Use automatically after meaningful changes or when the user asks for review.
argument-hint: "[files or diff scope (optional — defaults to recent changes)]"
context: fork
background: false
effort: high
---

# code-review

Review for actionable risks only. Skip subjective style. Read changed files + directly imported deps only. Auto-fires after meaningful changes; also invocable directly via `/code-review` for a deliberate pre-merge pass. If the diff touches a guarded domain (auth/payment/DB/CI), raise effort and escalate per the last line.

Do not use for: a dedicated, exhaustive security audit (`security-review`) — items (5) and (7) below are an inline sanity check on the diff, not a substitute for one; dependency CVE checks (`security-scan`); pre-release gating (`release-gate`); or a deep performance investigation (`performance-check`) — item (10) below is a quick flag, not a profiling pass.

Review order: (1) correctness bugs — logic errors, off-by-one, wrong condition, unhandled null/undefined. (2) regressions — breaks behavior callers depend on? (3) breaking changes — endpoint removed/renamed, required field added → grep for callers. (4) missing validation — unvalidated input reaching DB or executing code. (5) auth gaps — unauthenticated access, missing ownership check, role bypass.
(6) data loss — overwriting without backup, missing transaction, destructive op. (7) injection — SQL/NoSQL/XSS/command via unsanitized input. (8) race conditions — non-atomic check-then-act, missing lock. (9) missing tests — behavior changed with no test update. (10) performance — N+1, expensive loop, unnecessary full-table scan.

Severity: `critical (ship blocker) | high (fix before merge) | medium | low` — format: `SEVERITY | file:line | issue | fix`

```text
Critical:[N] High:[N] Medium:[N] Low:[N]
BREAKING CHANGES: [N — list | none]
VERDICT: ship ✓ | fix critical first | needs work
ESCALATE: [security-guard | db-guard | none]
```

Versions

RepositoryScoreLicence
This page · mtvrkan/senior-dev-kit91MIT
microsoft/aspire100MIT
kdlbs/kandev100AGPL-3.0
dotnet/runtime100MIT
drosam/agents100MIT
ggml-org/llama.cpp100MIT
ShamelesAbyss/Nyx100Apache-2.0
dzhng/jevgrep100MIT
iuliandita/skills100MIT

Database snapshot: 13.11.2026 · package version dd9ba62dcfe9 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 80Code review
    Review a diff or module for correctness, security, regressions, and missing tests. Use when the user asks for a review or before shipping a change.
  • 90doompi-review
    Review a code change for concrete defects, regressions, missing tests, and contract violations. Use when the user asks for code review, diff review, or risk assessment, not as a general implementation workflow.
  • 90ce-code-review
    Review a named diff or PR for bugs, regressions, tests, and standards. Use when asked to review code or when a shipping skill needs a review receipt. Use when asked to apply this review's findings locally. Use ce-resolve-pr-feedback for feedback already left on a PR.
  • 100review
    Review a diff, PR, or changed files for bugs, security holes, performance, missing tests, and over-engineering. Use when asked to review or critique code. Read-only. Merge prep goes to ship; accessibility-only audits go to uiux.
  • 90superior-code-review
    Review a code change, diff, commit, branch, or pull request for actionable defects, regressions, security risks, compatibility breaks, and missing verification. Use when code review is the primary requested outcome. Keep the review read-only unless the user explicitly asks to…
  • 100pr-review
    Review a pull request or the current branch for real bugs, security holes, risky data changes and missing tests, ranked blocking / should-fix / nit, with every finding checked against the code. Use when the user asks to review a PR, check their changes before pushing, or look for bugs in a diff.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.