Skip to main content
idapt
AccueilModèles IATarifs
Sign inStart free
All templates

Skills

Code review standards skill

What blocker means here: severity definitions and review order the whole team shares.

Last reviewed July 17, 2026

A single-file skill template defining code review standards: the review order, severity definitions with examples, and comment etiquette.

SKILL.md
# Code review standards

Apply when reviewing code or responding to review comments.

## Review order

Correctness, security, data safety, tests, then style. Never open with style.

## Severity definitions

- Blocker: would corrupt data, break users, or open a security hole. Merge stops.
- Should-fix: a real defect with a workaround, or missing tests on changed behavior. Fix before merge unless explicitly deferred with a task.
- Nit: taste or convention. Never blocks; batch at the end, prefix "nit:".

## Comment etiquette

- Quote the exact lines you judge. Findings without line references get ignored.
- Every finding proposes a concrete fix or asks a specific question.
- Praise real things briefly; skip ceremony.
- Disagreements cite the convention or the failure mode, not seniority.

## Verdicts

End with: approve, approve with nits, or request changes, plus the single most important item.

Set it up

  1. 1

    Copy the skill body

    Align the severity definitions with what your team actually enforces; aspirational strictness erodes fast.

  2. 2

    Create the skill

    Add it in the workspace Skills page; the code reviewer agent and any review request follow it.

Frequently asked

Related templates

Code reviewer agentCommit style skillQA test runner agent

Built on these features

Skills

Installable instruction bundles agents load on demand: curated, forkable, shareable.

Agents

Skills, scoped permissions, persistent memory: any model you pick.

Code Execution

Sandboxed Python, Node, and shell: agents and you, side-by-side.

Ready to get to work?

Free to start. No credit card. Never trained on your data.

Start free
  • Accueil
  • Tarifs
  • Modèles IA
  • Modèles d'image
  • Modèles de voix
  • Modèles vidéo
  • Classements
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Cas d'usage
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Centre d'aide
  • FAQ
  • Confidentialité
  • Comparer tous les modèles
  • Support
  • Développeurs
  • Quickstarts
  • Référence API
  • Tarifs API
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]ConditionsPolitique de confidentialitéMentions légalesSignaler un contenu
X (Twitter)