Skip to content
Agentmart
Submit a tool

code-review

Use when the user requests code review, review feedback must be evaluated, or a high-risk change warrants an independent technical pass

Skill by tenecsson

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tenecsson-code-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when the user requests code review, review feedback must be evaluated, or a high-risk change warrants an independent technical pass

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/code-review

What's inside

Skill name
code-review
Description
Use when the user requests code review, review feedback must be evaluated, or a high-risk change warrants an independent technical pass
License
MIT
Instructions
17 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Review the actual change against its requirements and risks. Do not add a review round merely because implementation occurred.

Requesting or performing review:
- Use an independent reviewer only when explicitly requested or justified by novelty, uncertainty, blast radius, security, compatibility, or merge risk.
- Inspect the diff and surrounding code; do not trust implementation summaries.
- Prioritize correctness, missing requirements, data loss, races, security, compatibility, and operational failure. Distinguish blocking findings from optional polish.
- Review tests for value: each new test should protect a plausible regression or durable contract. Flag tautological, source-text, private-structure, impossible-state, redundant, and overly mocked tests.
- Cite concrete locations and explain impact and the smallest appropriate correction.

Receiving review:
- Read the complete feedback and verify claims against the codebase and constraints.
- Implement valid findings, consolidate related fixes and verification, and push back with evidence when feedback is wrong or out of scope.
- Ask the user only when ambiguity would materially change the result. Do not serialize every comment into a separate approval or test cycle.

Stop when material requirements and risks are addressed with proportionate evidence. Do not manufacture further rounds for speculative improvements or exact stylistic conformity.

From tenecsson/playbooks, MIT.

More from tenecsson/playbooks

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 28, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tenecsson

Cite this page

code-review skill. Agent Mart. https://agentmart.dev/skills/tenecsson-code-review (last updated 2026-10-24)