Frontend change quality review
Skill SHIHAOZOU/ai-frontend-engineering-skills/skills/frontend-change-quality-review
Review frontend changes for correctness, types, architecture, accessibility, performance, security, naming, tests, and maintainability. Use for pull requests, diffs, patches, or pre-merge quality audits.From its SKILL.md
npx -y skills add SHIHAOZOU/ai-frontend-engineering-skills --skill frontend-change-quality-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.8 KB, 550 tokens by cl100k_base, as published. Nobody here has run it
Frontend Code Review Skill
For the Simplified Chinese reference, read references/zh-CN.md when the user communicates primarily in Chinese or requests Chinese output.
Purpose
Find actionable defects and risks in changed code while separating blocking issues from optional improvements.
When to Use
Use for pull request review, local diff review, release readiness, or acceptance-criteria verification.
Inputs
- Diff or changed files
- Requirement and acceptance criteria
- Repository rules and validation output
- Runtime evidence when available
Outputs
- Findings ordered by severity
- File and line references
- Evidence, impact, and focused remediation
- Validation gaps and residual risk
Workflow
- Read the requirement and repository instructions.
- Inspect the full diff and affected call paths.
- Verify behavior against acceptance criteria.
- Check types, architecture, state, errors, accessibility, performance, security, naming, and tests.
- Reproduce high-risk findings where practical.
- Report only actionable findings with evidence.
- Summarize validation gaps after findings.
Decision Tree
flowchart TD
A[Potential issue] --> B{Caused by this change?}
B -->|No| C[Do not report as a finding]
B -->|Yes| D{Observable impact or concrete risk?}
D -->|No| E[Optional note only]
D -->|Yes| F{Blocks correctness, safety, or release?}
F -->|Yes| G[High severity]
F -->|No| H[Medium or low severity]
Checklist
- Findings are caused by the reviewed change.
- Severity matches impact and likelihood.
- Each finding includes a precise location.
- Suggested remediation is smaller than a rewrite.
- Missing tests are tied to concrete risk.
- Summary does not hide important findings.
Constraints
- MUST lead with findings, ordered by severity.
- MUST NOT report style preference as a defect when conventions are met.
- MUST NOT claim a bug without a plausible failing scenario.
- SHOULD distinguish verified facts from uncertainty.
Examples
Finding: “High — src/cart/save.ts:42 retries a non-idempotent purchase request after timeout, which can create duplicate orders. Add an idempotency key or disable automatic retry.”
Anti-patterns
- Summarizing the diff without reviewing it
- Producing many low-value style comments
- Missing security or accessibility regressions
- Giving vague feedback without location or impact
What ships with it: 2 files
4.1 KB alongside SKILL.md
evals/
- evals.json2.0 KB
references/
- zh-CN.md2.1 KB