- Home
- Skills
- Smallnest
- Langgraphgo
- Code Review
code-review_skill
- Go
162
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill smallnest/langgraphgo --skill code-review- SKILL.md6.3 KB
Overview
This skill is a professional code review assistant that delivers a structured review process, a detailed checklist, and constructive feedback guidelines. It supports reviewing pull requests, commits, or any code needing quality assessment across functionality, security, performance, tests, documentation, and architecture. The goal is actionable, prioritized recommendations that improve safety and maintainability. It is language-agnostic but tuned for practical, reviewer-friendly output.
How this skill works
The skill first gathers context: purpose, scope of changes, business background, and tech stack. It runs a prioritized, multi-dimension checklist covering correctness, security, performance, tests, error handling, architecture, quality, and documentation. It formats findings into a clear report with severity levels, impact explanations, suggested fixes, and example code when helpful. It also recommends tooling and next steps to close feedback loops efficiently.
When to use it
- When requesting a review of a pull request or specific commit
- When evaluating code quality before merging into main branches
- When auditing security-sensitive or performance-critical code
- When mentoring junior developers or reviewing onboarding PRs
- When preparing a large PR for staged review or refactor
Best practices
- Start by understanding the change purpose, scope, and relevant tests
- Prioritize fixes: block issues (correctness/security) before style
- Provide severity + impact + concrete remediation for every finding
- Use automated tools for style/format to focus human review on logic
- Keep PRs small, describe intent clearly, and respond promptly to feedback
Example use cases
- Quick review of a small feature PR (<200 lines) focusing on correctness and tests
- High-level review of a large PR (>400 lines) recommending split and core-path checks
- Security audit of input validation, auth/authorization, and secret handling
- Performance review to identify algorithmic or DB-query bottlenecks
- Guided feedback for junior devs with examples and learning resources
FAQ
Issues are grouped by severity: must-fix (critical correctness/security), recommended (performance/tests/architecture), and optional (style/docs). Each entry explains impact and remediation.
Can it suggest code examples?
Yes. For many findings the skill provides concrete code snippets or patterns to illustrate fixes and best practices.