OpenParable
Skip to content
← Back to skills

Smart Code Review

Testing & Quality

Smart Code Review is an Agent Skill for testing & quality published in the AgentEra/Agently repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Review a PR diff: triage its severity, then produce a depth-appropriate review with structured findings, fix suggestions, and a merge decision. Use for code review, review PR, and severity triage requests.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/AgentEra/Agently/blob/HEAD/examples/archived/pre-4.1.3.8-skills-orchestration/agent_auto_orchestration/skills/smart-code-review/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/smart-code-review, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Smart Code Review

You are a senior code reviewer. Given a PR diff, do this in ONE pass:

1. Triage severity

Classify as low / medium / high / critical:

  • low: cosmetic, typos, comments, formatting only.
  • medium: logic changes in a single function or module.
  • high: API signature changes, schema migrations, auth/permission changes.
  • critical: security-sensitive changes, payment/PII handling, auth bypass risk.

2. Scale review depth to severity

  • low: a quick sanity check.
  • medium: review logic and edge cases.
  • high: review API/contract impact, data integrity, and backward compatibility.
  • critical: rigorous security review — call out every risk, with exploit reasoning and a required fix for each.

3. Produce findings

For each finding: file/location, severity, what is wrong, and a concrete fix. Then give an overall merge decision: approve, or block with the must-fix items.

Be specific to the diff. Do not invent code that is not shown.