From example-skills
Comprehensive quality verification system for code changes with build, type, lint, test, and security checks
npx claudepluginhub organvm-iv-taxis/a-i--skills --plugin document-skillsThis skill uses the workspace's default tool permissions.
A comprehensive verification system for ensuring code quality across multiple dimensions.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
A comprehensive verification system for ensuring code quality across multiple dimensions.
Invoke this skill:
# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20
# OR for other build systems
make build 2>&1 | tail -20
cargo build 2>&1 | tail -20
Critical: If build fails, STOP and fix before continuing.
# TypeScript projects
npx tsc --noEmit 2>&1 | head -30
# Python projects
pyright . 2>&1 | head -30
mypy . 2>&1 | head -30
# Go projects
go vet ./... 2>&1 | head -30
Report all type errors. Fix critical ones before continuing.
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
eslint . 2>&1 | head -30
# Python
ruff check . 2>&1 | head-30
flake8 . 2>&1 | head -30
# Go
golint ./... 2>&1 | head -30
# Rust
cargo clippy 2>&1 | head -30
# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50
pytest --cov=. 2>&1 | tail -50
go test -cover ./... 2>&1 | tail -50
# Check coverage threshold
# Target: 80% minimum for new code
Report:
# Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" --include="*.py" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" --include="*.py" . 2>/dev/null | head -10
grep -rn "password.*=" --include="*.ts" --include="*.js" --include="*.py" . 2>/dev/null | head -10
# Check for debug statements
grep -rn "console.log" --include="*.ts" --include="*.tsx" --include="*.js" src/ 2>/dev/null | head -10
grep -rn "print(" --include="*.py" . 2>/dev/null | head -10
grep -rn "println!" --include="*.rs" src/ 2>/dev/null | head -10
# Show what changed
git diff --stat
git diff HEAD~1 --name-only
git diff --shortstat
Review each changed file for:
After running all phases, produce a verification report:
VERIFICATION REPORT
==================
Build: [✓ PASS / ✗ FAIL]
Types: [✓ PASS / ✗ FAIL] (X errors)
Lint: [✓ PASS / ✗ FAIL] (X warnings)
Tests: [✓ PASS / ✗ FAIL] (X/Y passed, Z% coverage)
Security: [✓ PASS / ✗ FAIL] (X issues)
Diff: [X files changed, +Y lines, -Z lines]
Overall: [✓ READY / ✗ NOT READY] for PR
Issues to Fix:
1. [Priority] Description
2. [Optional] Description
...
Recommendations:
- Suggestion 1
- Suggestion 2
For long sessions, run verification every 15 minutes or after major changes:
Checkpoints:
This skill complements:
For rapid checks during development:
# Minimal verification (30 seconds)
npm run build && npm run lint && npm test
Use full verification before commits.