hivemq/hivemq-edge/pre-review
Claude Code and agent skill by hivemq/hivemq-edge
- community
- ext:[{"type":"hook","description":"Pre/post lifecycle hooks"}]
Checking that the SKILL.md file is still in the repository.
Automated code review against established patterns before PR creation. Analyzes git diff for critical issues, pattern violations, test coverage, and generates a comprehensive report.
Install
npx vskill@latest install hivemq/hivemq-edge/pre-reviewSemi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard
SKILL.md
Pre-Review Skill
Analyzes code changes in the current branch against established patterns, catching common issues early before PR submission.
Generates a comprehensive report covering:
- Critical issues (must fix before PR)
- Pattern violations (should fix)
- Missing test coverage & quality gates
- Suggestions (nice to have)
Usage
Arguments are parsed as follows:
--base <branch>: Base branch to compare against (default: master)--focus <areas>: Comma-separated focus areas (e.g., "state-management,testing")--skip <sections>: Skip report sections (e.g., "suggestions")
Examples:
Skill Workflow
Phase 1: Change Analysis (Gather)
- Identify changed files
``bash git diff master...HEAD --name-status ``
- Categorize changes
- Source files (
.ts,.tsx) - non-test - Test files (
.spec.ts,.cy.tsx) - Generated files (
__generated__/) - Config files
- Extract metrics
- Line count changes
- Number of files modified
- Test coverage ratio
Phase 2: Critical Issues Check (Must Fix)
Run these checks and flag any violations:
1. Type Safety Issues
Pattern: All type suppressions must have:
- Justification comment
- TODO with ticket reference
- Expected fix timeline
Example:
2. Linter Suppressions
Pattern: All eslint-disable must have:
- Inline comment explaining why
- Specific rule name (not
eslint-disable-linewithout rule) - Considered alternative solutions
Example:
3. Console Statements in Production
Pattern: No console.* in production code
- Use proper logging library
- Or remove debug statements
4. TODO/FIXME Without Owner
Pattern: All TODO comments must include:
- Ticket reference:
TODO[TICKET-123] - Or owner:
TODO[YourName] - Brief explanation
Example:
5. Missing Test Coverage for New Public Functions
Check: For each new exported function, ensure test exists
Pattern:
6. Hardcoded Strings (i18n)
Pattern: All user-facing text must use t() translation
Phase 3: Pattern Violations (Should Fix)
1. Inline Types vs Interfaces
Pattern: Use explicit interfaces, not inline object types
2. Emoji in Production Code
Pattern: No emojis in code comments (markdown docs are fine)
3. Magic Strings/Numbers
Pattern: Extract constants
4. Large File Size
Pattern: Files > 300 lines should be considered for splitting
5. Inconsistent Naming
Pattern: Follow project conventions
- Components: PascalCase (
UserProfile.tsx) - Hooks: camelCase starting with
use(useUserData.ts) - Utils: camelCase (
formatDate.ts) - Constants: UPPER_SNAKE_CASE (
MAX_RETRY_COUNT)
Phase 4: Test Coverage & Quality Gates
1. Test Files for Changed Components
Rule: Every new/changed component needs test file
2. Accessibility Tests
Pattern: Every component test must include:
3. Test Selectors
Pattern: Must use in priority order:
data-testid(best)- ARIA roles/labels
- Text content
- Never CSS classes
4. Backward Compatibility Tests
Rule: When deprecating or migrating, add compat tests
5. Edge Case Coverage
Check: For each new function, verify edge cases tested:
- Null/undefined inputs
- Empty arrays
- Missing optional fields
- Error conditions
Phase 5: Suggestions (Nice to Have)
1. JSDoc for Public APIs
2. Performance Considerations
Check: For loops/iterations over large arrays:
- Use
.reduce()efficiently - Avoid nested loops
- Consider memoization for expensive calculations
3. Code Organization
Suggest:
- Extract complex logic to separate functions
- Group related functions
- Consider custom hooks for stateful logic
4. Storybook Stories
Suggest: For new visual components, add Storybook story
Output Format
Generate a markdown report with structure:
Expandable Checklist
The checklist is stored in .claude/skills/pre-review/checklist.yaml and can be extended:
Add new checks by editing the YAML file.
Integration with Tasks
The skill automatically:
- Checks for related task documentation in
.tasks/{task-id}/ - References analysis documents if found
- Links to relevant pattern guides
- Generates PR template with task context
Example Invocation
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinghivemq-edge-frontend/.claude/skills/pre-review/SKILL.md
Popularity
- Repository stars
- 165
- Repository forks
- 44
- 7-day trend score
- 26
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 4 Sep 2026, 2 months ago.
Extension points
hookPre/post lifecycle hooks
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/hivemq/hivemq-edge/pre-review)