reviewing-code SKILL.md skillA
reviewing-code from qte77/claude-code-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qte77/claude-code-plugins/reviewing-code@git:20260322.75aadc6Pins git:20260322.75aadc6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- qte77/claude-code-plugins
- Path
plugins/python-dev/skills/reviewing-code/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260322.75aadc6, committed Mar 22, 2026
- First version recorded
- Feb 22, 2026
- Size
- 2,597 bytes
- Repository stars
- 3
- License
- Apache-2.0
Provides concise, focused code reviews matching exact task complexity requirements. Use when reviewing code quality, security, or when the user asks for code review.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Review Context - Changed files: !`git diff --name-only HEAD~1 2>/dev/null || echo "No recent commits"` - Staged files: !`git diff --staged --name-only` ## Code Review **Scope**: $ARGUMENTS Delivers **focused, streamlined** code reviews matching stated task requirements exactly. No over-analysis. ## Python Standards See `references/python-best-practices.md` for comprehensive Python guidelines. ## Workflow 1. **Read task requirements** to understand expected scope 2. **Check `make validate`** passes before detailed review 3. **Match review depth** to task complexity (simple vs complex) 4. **Validate requirements** - does implementation match task scope exactly? 5. **Issue focused feedback** with specific file paths and line numbers ## Review Strategy **Simple Tasks (100-200 lines)**: Security, compliance, requirements match, basic quality **Complex Tasks (500+ lines)**: Above plus architecture, performance, comprehensive testing **Always**: Use existing project patterns, immediate use after implementation ## Review Checklist **Security & Compliance**: - [ ] No security vulnerabilities (injection, XSS, etc.) - [ ] Follows @AGENTS.md mandatory requirements …
Read the whole file at its exact version.
How to install
mdr add qte77/claude-code-plugins/reviewing-code@sha256:51d3924402b7887dThe line at the top of this page pins the label git:20260322.75aadc6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_iecqqp5tnag2ammc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Feb 22, 2026 and Mar 22, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260322.75aadc6 latest | 2026-03-22 | 75aadc6 | 2,597 B | A | view · diff |
| git:20260301.2e7e6b3 | 2026-03-01 | 2e7e6b3 | 2,454 B | A | view · diff |
| git:20260301.26f7262 | 2026-03-01 | 26f7262 | 2,448 B | A | view · diff |
| git:20260222.2b61bad | 2026-02-22 | 2b61bad | 2,457 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2597 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
qte77/claude-code-plugins · 3 stars · license Apache-2.0 · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_iecqqp5tnag2ammc GET https://markdownregistry.com/api/v1/resolve?ref=qte77/claude-code-plugins/reviewing-code GET https://markdownregistry.com/api/v1/blob/51d3924402b7887dd8f75c6cdd0ddde999696d2387f134b75127865f44bf533c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from qte77/claude-code-plugins
Every file in qte77/claude-code-plugins