Verification Loop

作者 affaan-mef648e01899bMIT275K 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫3 天前更新

A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.

AI 產生的概覽

引導代理在宣告編碼工作完成前,對工作階段執行六個階段的驗證檢查。

功能
這個技能為編碼工作階段定義一套驗證迴圈,涵蓋建置、型別檢查、程式碼檢查、測試套件、安全掃描與差異審查六個階段。它列出每個階段要執行的指令,以及遇到問題時應停下來修正的條件。最後提供固定的驗證報告範本,逐項顯示各階段通過或失敗、整體是否可提交,以及待修正的問題。
適用情境
適用於完成某項功能或較大程式碼變更之後、建立提取要求之前、重構之後,或需要確保品質關卡通過時。也建議在長時間工作階段中定期或在大幅變更後執行。
執行需求
僅為說明性指示,未附帶指令碼。需要代理能在專案中執行 shell 指令,並依技術堆疊提供 npm、pnpm、tsc、pyright、ruff、git、grep 等工具。

Verification Loop Skill

A comprehensive verification system for Claude Code sessions.

When to Use

Invoke this skill:

  • After completing a feature or significant code change
  • Before creating a PR
  • When you want to ensure quality gates pass
  • After refactoring

Verification Phases

Phase 1: Build Verification

bash
# Check if project buildsnpm run build 2>&1 | tail -20# ORpnpm build 2>&1 | tail -20

If build fails, STOP and fix before continuing.

Phase 2: Type Check

bash
# TypeScript projectsnpx tsc --noEmit 2>&1 | head -30
# Python projectspyright . 2>&1 | head -30

Report all type errors. Fix critical ones before continuing.

Phase 3: Lint Check

bash
# JavaScript/TypeScriptnpm run lint 2>&1 | head -30
# Pythonruff check . 2>&1 | head -30

Phase 4: Test Suite

bash
# Run tests with coveragenpm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold# Target: 80% minimum

Report:

  • Total tests: X
  • Passed: X
  • Failed: X
  • Coverage: X%

Phase 5: Security Scan

bash
# Check for secretsgrep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.loggrep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

Phase 6: Diff Review

bash
# Show what changedgit diff --statgit diff HEAD~1 --name-only

Review each changed file for:

  • Unintended changes
  • Missing error handling
  • Potential edge cases

Output Format

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]
Overall:   [READY/NOT READY] for PR
Issues to Fix:1. ...2. ...

Continuous Mode

For long sessions, run verification every 15 minutes or after major changes:

markdown
Set a mental checkpoint:- After completing each function- After finishing a component- Before moving to next task
Run: /verify

Integration with Hooks

This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.

來源與署名

來源:affaan-m/ecc位於.agents/skills/verification-loop提交ef648e0

授權條款: MIT

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架