diff --git a/.agents/skills/verification-loop/SKILL.md b/.agents/skills/verification-loop/SKILL.md
deleted file mode 100644
index 1933545d57..0000000000
--- a/.agents/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,126 +0,0 @@
----
-name: verification-loop
-description: "A comprehensive verification system for Claude Code sessions."
-origin: ECC
----
-
-# 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 builds
-npm run build 2>&1 | tail -20
-# OR
-pnpm build 2>&1 | tail -20
-```
-
-If build fails, STOP and fix before continuing.
-
-### Phase 2: Type Check
-```bash
-# TypeScript projects
-npx tsc --noEmit 2>&1 | head -30
-
-# Python projects
-pyright . 2>&1 | head -30
-```
-
-Report all type errors. Fix critical ones before continuing.
-
-### Phase 3: Lint Check
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### Phase 4: Test Suite
-```bash
-# Run tests with coverage
-npm 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 secrets
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# Check for console.log
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### Phase 6: Diff Review
-```bash
-# Show what changed
-git diff --stat
-git 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.
diff --git a/.agents/skills/verification-loop/agents/openai.yaml b/.agents/skills/verification-loop/agents/openai.yaml
deleted file mode 100644
index 644a9ad535..0000000000
--- a/.agents/skills/verification-loop/agents/openai.yaml
+++ /dev/null
@@ -1,7 +0,0 @@
-interface:
-  display_name: "Verification Loop"
-  short_description: "Build, test, lint, typecheck verification"
-  brand_color: "#10B981"
-  default_prompt: "Run verification: build, test, lint, typecheck, security"
-policy:
-  allow_implicit_invocation: true
diff --git a/.codex/AGENTS.md b/.codex/AGENTS.md
index 5230166214..e62fa24042 100644
--- a/.codex/AGENTS.md
+++ b/.codex/AGENTS.md
@@ -33,7 +33,7 @@ Available skills:
 - eval-harness — Eval-driven development
 - strategic-compact — Context management
 - api-design — REST API design patterns
-- verification-loop — Build, test, lint, typecheck, security
+- tdd-workflow — TDD + build, test, lint, typecheck, security verification
 - deep-research — Multi-source research with firecrawl and exa MCPs
 - exa-search — Neural search via Exa MCP for web, code, and companies
 - claude-api — Anthropic Claude API patterns and SDKs
diff --git a/.kiro/README.md b/.kiro/README.md
index 6b105d5b29..0c549243c8 100644
--- a/.kiro/README.md
+++ b/.kiro/README.md
@@ -83,10 +83,9 @@ Skills are on-demand workflows invocable via the `/` menu in chat.
 
 | Skill | Description |
 |-------|-------------|
-| `tdd-workflow` | Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests. Use when writing new features or fixing bugs. |
+| `tdd-workflow` | Enforces TDD with 80%+ coverage (unit, integration, E2E) and includes a pre-PR verification gate (build, type check, lint, tests, security scan, diff review). Use when writing features, fixing bugs, or before creating PRs. |
 | `coding-standards` | Universal coding standards and best practices for TypeScript, JavaScript, React, and Node.js. Use when starting projects, reviewing code, or refactoring. |
 | `security-review` | Comprehensive security checklist and patterns. Use when adding authentication, handling user input, creating API endpoints, or working with secrets. |
-| `verification-loop` | Comprehensive verification system that runs build, type check, lint, tests, security scan, and diff review. Use after completing features or before creating PRs. |
 | `api-design` | RESTful API design patterns and best practices. Use when designing new APIs or refactoring existing endpoints. |
 | `frontend-patterns` | React, Next.js, and frontend architecture patterns. Use when building UI components or optimizing frontend performance. |
 | `backend-patterns` | Node.js, Express, and backend architecture patterns. Use when building APIs, services, or backend infrastructure. |
@@ -272,8 +271,6 @@ Shell scripts used by hooks to perform quality checks and formatting.
 │   │   └── SKILL.md              # Coding standards skill
 │   ├── security-review/
 │   │   └── SKILL.md              # Security review skill
-│   ├── verification-loop/
-│   │   └── SKILL.md              # Verification loop skill
 │   ├── api-design/
 │   │   └── SKILL.md              # API design skill
 │   ├── frontend-patterns/
@@ -361,7 +358,7 @@ All files are yours to modify after installation. The installer never overwrites
 3. **Review your code**: Switch to `code-reviewer` agent after writing code
 4. **Check security**: Use `security-reviewer` agent for auth, API endpoints, or sensitive data handling
 5. **Run quality gate**: Trigger the `quality-gate` hook before committing
-6. **Verify comprehensively**: Use the `verification-loop` skill before creating PRs
+6. **Verify comprehensively**: Use the `tdd-workflow` skill's verification gate before creating PRs
 
 The auto-loaded steering files (coding-style, security, testing) ensure consistent standards throughout your session.
 
@@ -404,10 +401,10 @@ kiro-cli --agent code-reviewer
 # 2. Review specific files or directories
 > "Review the changes in src/api/users.ts"
 
-# 3. Use the verification-loop skill for comprehensive checks
-> /verification-loop
+# 3. Use the tdd-workflow verification gate for comprehensive checks
+> /verify
 
-# 4. The verification loop will:
+# 4. The verification gate will:
 # - Run build and type checks
 # - Run linter
 # - Run all tests
@@ -561,8 +558,8 @@ kiro-cli --agent refactor-cleaner
 # - Suggest consolidation opportunities
 # - Refactor safely without breaking changes
 
-# 3. Use verification-loop after refactoring
-> /verification-loop
+# 3. Use verification gate after refactoring
+> /verify
 # Ensures all tests still pass after refactoring
 ```
 
diff --git a/.kiro/docs/longform-guide.md b/.kiro/docs/longform-guide.md
index 2216a2cf51..1d80fb40ff 100644
--- a/.kiro/docs/longform-guide.md
+++ b/.kiro/docs/longform-guide.md
@@ -107,7 +107,7 @@ Hooks create a safety net and capture knowledge automatically.
    → Agent identifies coupling, cohesion issues
    → Agent suggests refactoring strategy
 
-2. Invoke refactor-cleaner agent with verification-loop skill
+2. Invoke refactor-cleaner agent with tdd-workflow skill
    → Agent refactors incrementally
    → Agent runs tests after each change
    → Agent validates behavior preservation
diff --git a/.kiro/docs/security-guide.md b/.kiro/docs/security-guide.md
index c034bdfb18..e0361def8d 100644
--- a/.kiro/docs/security-guide.md
+++ b/.kiro/docs/security-guide.md
@@ -117,7 +117,7 @@ Plan a user authentication feature with these security requirements:
 **Risk**: May accidentally remove security checks during refactoring.
 
 **Mitigation**:
-- Use verification-loop skill to validate behavior preservation
+- Use tdd-workflow verification gate to validate behavior preservation
 - Include security tests in test suite
 - Review diffs carefully for removed security code
 - Run security-reviewer after refactoring
diff --git a/.kiro/docs/shortform-guide.md b/.kiro/docs/shortform-guide.md
index ace257f314..4b9dc00d10 100644
--- a/.kiro/docs/shortform-guide.md
+++ b/.kiro/docs/shortform-guide.md
@@ -57,9 +57,8 @@ Type `/` in chat and select from the menu, or use:
 
 | Skill | Use For |
 |-------|---------|
-| `tdd-workflow` | Red-green-refactor TDD cycle |
+| `tdd-workflow` | Red-green-refactor TDD cycle + pre-PR verification gate |
 | `security-review` | Comprehensive security audit |
-| `verification-loop` | Continuous validation and improvement |
 | `coding-standards` | Code style and standards enforcement |
 | `api-design` | RESTful API design patterns |
 | `frontend-patterns` | React/Vue/Angular best practices |
@@ -207,7 +206,7 @@ Toggle hooks in the Agent Hooks panel or edit `.kiro/hooks/*.kiro.hook` files.
    "Analyze the user module architecture"
 
 2. /agent swap refactor-cleaner
-   #verification-loop
+   #tdd-workflow
    "Refactor based on the analysis"
 
 3. /agent swap code-reviewer
diff --git a/.kiro/skills/agentic-engineering/SKILL.md b/.kiro/skills/agentic-engineering/SKILL.md
index 72831ba12c..46686d6ff3 100644
--- a/.kiro/skills/agentic-engineering/SKILL.md
+++ b/.kiro/skills/agentic-engineering/SKILL.md
@@ -130,6 +130,6 @@ Outcome: Success
 ## Integration with Other Skills
 
 - **tdd-workflow**: Combine with eval-first loop for test-driven development
-- **verification-loop**: Use for continuous validation during implementation
+- **tdd-workflow**: Also provides a pre-PR verification gate for continuous validation during implementation
 - **search-first**: Apply before implementation to find existing solutions
 - **coding-standards**: Reference during code review phase
diff --git a/.kiro/skills/verification-loop/SKILL.md b/.kiro/skills/verification-loop/SKILL.md
deleted file mode 100644
index f4327b91e1..0000000000
--- a/.kiro/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,128 +0,0 @@
----
-name: verification-loop
-description: >
-  A comprehensive verification system for Kiro sessions.
-metadata:
-  origin: ECC
----
-
-# Verification Loop Skill
-
-A comprehensive verification system for Kiro 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 builds
-npm run build 2>&1 | tail -20
-# OR
-pnpm build 2>&1 | tail -20
-```
-
-If build fails, STOP and fix before continuing.
-
-### Phase 2: Type Check
-```bash
-# TypeScript projects
-npx tsc --noEmit 2>&1 | head -30
-
-# Python projects
-pyright . 2>&1 | head -30
-```
-
-Report all type errors. Fix critical ones before continuing.
-
-### Phase 3: Lint Check
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### Phase 4: Test Suite
-```bash
-# Run tests with coverage
-npm 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 secrets
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# Check for console.log
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### Phase 6: Diff Review
-```bash
-# Show what changed
-git diff --stat
-git 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.
diff --git a/.opencode/README.md b/.opencode/README.md
index 170a8459f7..37f1390f99 100644
--- a/.opencode/README.md
+++ b/.opencode/README.md
@@ -168,7 +168,6 @@ The default OpenCode config loads 11 curated ECC skills via the `instructions` a
 - tdd-workflow
 - strategic-compact
 - eval-harness
-- verification-loop
 - api-design
 - e2e-testing
 
diff --git a/.opencode/opencode.json b/.opencode/opencode.json
index 1038140fdf..44c2526c89 100644
--- a/.opencode/opencode.json
+++ b/.opencode/opencode.json
@@ -14,7 +14,6 @@
     "skills/frontend-slides/SKILL.md",
     "skills/backend-patterns/SKILL.md",
     "skills/e2e-testing/SKILL.md",
-    "skills/verification-loop/SKILL.md",
     "skills/api-design/SKILL.md",
     "skills/strategic-compact/SKILL.md",
     "skills/eval-harness/SKILL.md"
diff --git a/AGENTS.md b/AGENTS.md
index 3abed0a8c2..7b386ce490 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,6 +1,6 @@
 # Everything Claude Code (ECC) — Agent Instructions
 
-This is a **production-ready AI coding plugin** providing 30 specialized agents, 136 skills, 60 commands, and automated hook workflows for software development.
+This is a **production-ready AI coding plugin** providing 30 specialized agents, 135 skills, 60 commands, and automated hook workflows for software development.
 
 **Version:** 1.9.0
 
@@ -142,7 +142,7 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
 
 ```
 agents/          — 30 specialized subagents
-skills/          — 136 workflow skills and domain knowledge
+skills/          — 135 workflow skills and domain knowledge
 commands/        — 60 slash commands
 hooks/           — Trigger-based automations
 rules/           — Always-follow guidelines (common + per-language)
diff --git a/COMMANDS-QUICK-REF.md b/COMMANDS-QUICK-REF.md
index b1bcab691a..f8746ebb6e 100644
--- a/COMMANDS-QUICK-REF.md
+++ b/COMMANDS-QUICK-REF.md
@@ -12,7 +12,7 @@
 | `/tdd` | Enforce test-driven development: scaffold interface → write failing test → implement → verify 80%+ coverage |
 | `/code-review` | Full code quality, security, and maintainability review of changed files |
 | `/build-fix` | Detect and fix build errors — delegates to the right build-resolver agent automatically |
-| `/verify` | Run the full verification loop: build → lint → test → type-check |
+| `/verify` | Run the full verification gate: build → lint → test → type-check (via tdd-workflow) |
 | `/quality-gate` | Quality gate check against project standards |
 
 ---
diff --git a/README.md b/README.md
index 2417f82314..e4d238624f 100644
--- a/README.md
+++ b/README.md
@@ -220,7 +220,7 @@ For manual install instructions see the README in the `rules/` folder. When copy
 /plugin list everything-claude-code@everything-claude-code
 ```
 
-**That's it!** You now have access to 30 agents, 136 skills, and 60 commands.
+**That's it!** You now have access to 30 agents, 135 skills, and 60 commands.
 
 ### Multi-model commands require additional setup
 
@@ -339,10 +339,9 @@ everything-claude-code/
 |   |-- continuous-learning-v2/     # Instinct-based learning with confidence scoring
 |   |-- iterative-retrieval/        # Progressive context refinement for subagents
 |   |-- strategic-compact/          # Manual compaction suggestions (Longform Guide)
-|   |-- tdd-workflow/               # TDD methodology
+|   |-- tdd-workflow/               # TDD methodology + pre-PR verification gate
 |   |-- security-review/            # Security checklist
 |   |-- eval-harness/               # Verification loop evaluation (Longform Guide)
-|   |-- verification-loop/          # Continuous verification (Longform Guide)
 |   |-- videodb/                   # Video and audio: ingest, search, edit, generate, stream (NEW)
 |   |-- golang-patterns/            # Go idioms and best practices
 |   |-- golang-testing/             # Go testing patterns, TDD, benchmarks
@@ -1064,7 +1063,7 @@ Skills at `.agents/skills/` are auto-loaded by Codex:
 | eval-harness | Eval-driven development |
 | strategic-compact | Context management |
 | api-design | REST API design patterns |
-| verification-loop | Build, test, lint, typecheck, security |
+| tdd-workflow | TDD + build, test, lint, typecheck, security verification |
 
 ### Key Limitation
 
@@ -1111,7 +1110,7 @@ The configuration is automatically detected from `.opencode/opencode.json`.
 |---------|-------------|----------|--------|
 | Agents | PASS: 30 agents | PASS: 12 agents | **Claude Code leads** |
 | Commands | PASS: 60 commands | PASS: 31 commands | **Claude Code leads** |
-| Skills | PASS: 136 skills | PASS: 37 skills | **Claude Code leads** |
+| Skills | PASS: 135 skills | PASS: 37 skills | **Claude Code leads** |
 | Hooks | PASS: 8 event types | PASS: 11 events | **OpenCode has more!** |
 | Rules | PASS: 29 rules | PASS: 13 instructions | **Claude Code leads** |
 | MCP Servers | PASS: 14 servers | PASS: Full | **Full parity** |
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 4ccf1cda62..113e8649f1 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -190,10 +190,9 @@ everything-claude-code/
 |   |-- continuous-learning-v2/     # 基于直觉的学习与置信度评分
 |   |-- iterative-retrieval/        # 子代理的渐进式上下文细化
 |   |-- strategic-compact/          # 手动压缩建议（详细指南）
-|   |-- tdd-workflow/               # TDD 方法论
+|   |-- tdd-workflow/               # TDD 方法论 + PR 前验证门控
 |   |-- security-review/            # 安全检查清单
 |   |-- eval-harness/               # 验证循环评估（详细指南）
-|   |-- verification-loop/          # 持续验证（详细指南）
 |   |-- golang-patterns/            # Go 惯用语和最佳实践（新增）
 |   |-- golang-testing/             # Go 测试模式、TDD、基准测试（新增）
 |   |-- cpp-testing/                # C++ 测试模式、GoogleTest、CMake/CTest（新增）
diff --git a/agent.yaml b/agent.yaml
index 881c00cef8..de0f8c5d7b 100644
--- a/agent.yaml
+++ b/agent.yaml
@@ -139,7 +139,6 @@ skills:
   - tdd-workflow
   - team-builder
   - token-budget-advisor
-  - verification-loop
   - video-editing
   - videodb
   - visa-doc-translate
diff --git a/docs/COMMAND-AGENT-MAP.md b/docs/COMMAND-AGENT-MAP.md
index 70bcacfc14..a3e56ec864 100644
--- a/docs/COMMAND-AGENT-MAP.md
+++ b/docs/COMMAND-AGENT-MAP.md
@@ -36,8 +36,8 @@ This document lists each slash command and the primary agent(s) or skills it inv
 | `/promote` | — | continuous-learning-v2 |
 | `/projects` | — | continuous-learning-v2 |
 | `/skill-create` | — | skill-create-output script, git history |
-| `/checkpoint` | — | verification-loop skill |
-| `/verify` | — | verification-loop skill |
+| `/checkpoint` | — | tdd-workflow skill (verification gate) |
+| `/verify` | — | tdd-workflow skill (verification gate) |
 | `/eval` | — | eval-harness skill |
 | `/test-coverage` | — | Coverage analysis |
 | `/sessions` | — | Session history |
@@ -55,7 +55,7 @@ This document lists each slash command and the primary agent(s) or skills it inv
 ## Skills referenced by commands
 
 - **continuous-learning**, **continuous-learning-v2**: `/learn`, `/learn-eval`, `/instinct-*`, `/evolve`, `/promote`, `/projects`
-- **verification-loop**: `/checkpoint`, `/verify`
+- **tdd-workflow** (verification gate): `/checkpoint`, `/verify`
 - **eval-harness**: `/eval`
 - **security-scan**: `/security-scan` (runs AgentShield)
 - **strategic-compact**: suggested at compaction points (hooks)
diff --git a/docs/ja-JP/README.md b/docs/ja-JP/README.md
index 86a802f0ea..c84b672398 100644
--- a/docs/ja-JP/README.md
+++ b/docs/ja-JP/README.md
@@ -215,10 +215,9 @@ everything-claude-code/
 |   |-- continuous-learning-v2/     # 信頼度スコア付き直感ベース学習
 |   |-- iterative-retrieval/        # サブエージェント用の段階的コンテキスト精製
 |   |-- strategic-compact/          # 手動圧縮提案（長文ガイド）
-|   |-- tdd-workflow/               # TDD 方法論
+|   |-- tdd-workflow/               # TDD 方法論 + PR 前検証ゲート
 |   |-- security-review/            # セキュリティチェックリスト
 |   |-- eval-harness/               # 検証ループ評価（長文ガイド）
-|   |-- verification-loop/          # 継続的検証（長文ガイド）
 |   |-- golang-patterns/            # Go イディオムとベストプラクティス
 |   |-- golang-testing/             # Go テストパターン、TDD、ベンチマーク
 |   |-- cpp-testing/                # C++ テスト GoogleTest、CMake/CTest（新規）
diff --git a/docs/ja-JP/skills/configure-ecc/SKILL.md b/docs/ja-JP/skills/configure-ecc/SKILL.md
index 0a9ba790bd..16ef8a222c 100644
--- a/docs/ja-JP/skills/configure-ecc/SKILL.md
+++ b/docs/ja-JP/skills/configure-ecc/SKILL.md
@@ -120,7 +120,7 @@ Options:
 | `security-review` | セキュリティチェックリスト: 認証、入力、シークレット、API、決済機能 |
 | `strategic-compact` | 論理的な間隔で手動コンテキスト圧縮を提案 |
 | `tdd-workflow` | 80%以上のカバレッジで TDD を強制: ユニット、統合、E2E |
-| `verification-loop` | 検証と品質ループのパターン |
+| `tdd-workflow` | TDD 方法論 + PR 前検証ゲート |
 
 **スタンドアロン**
 
diff --git a/docs/ja-JP/skills/verification-loop/SKILL.md b/docs/ja-JP/skills/verification-loop/SKILL.md
deleted file mode 100644
index ee51db997b..0000000000
--- a/docs/ja-JP/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,120 +0,0 @@
-# 検証ループスキル
-
-Claude Codeセッション向けの包括的な検証システム。
-
-## 使用タイミング
-
-このスキルを呼び出す:
-- 機能または重要なコード変更を完了した後
-- PRを作成する前
-- 品質ゲートが通過することを確認したい場合
-- リファクタリング後
-
-## 検証フェーズ
-
-### フェーズ1: ビルド検証
-```bash
-# プロジェクトがビルドできるか確認
-npm run build 2>&1 | tail -20
-# または
-pnpm build 2>&1 | tail -20
-```
-
-ビルドが失敗した場合、停止して続行前に修正。
-
-### フェーズ2: 型チェック
-```bash
-# TypeScriptプロジェクト
-npx tsc --noEmit 2>&1 | head -30
-
-# Pythonプロジェクト
-pyright . 2>&1 | head -30
-```
-
-すべての型エラーを報告。続行前に重要なものを修正。
-
-### フェーズ3: Lintチェック
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### フェーズ4: テストスイート
-```bash
-# カバレッジ付きでテストを実行
-npm run test -- --coverage 2>&1 | tail -50
-
-# カバレッジ閾値を確認
-# 目標: 最低80%
-```
-
-報告:
-- 合計テスト数: X
-- 成功: X
-- 失敗: X
-- カバレッジ: X%
-
-### フェーズ5: セキュリティスキャン
-```bash
-# シークレットを確認
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# console.logを確認
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### フェーズ6: 差分レビュー
-```bash
-# 変更内容を表示
-git diff --stat
-git diff HEAD~1 --name-only
-```
-
-各変更ファイルをレビュー:
-- 意図しない変更
-- 不足しているエラー処理
-- 潜在的なエッジケース
-
-## 出力フォーマット
-
-すべてのフェーズを実行後、検証レポートを作成:
-
-```
-検証レポート
-==================
-
-ビルド:     [成功/失敗]
-型:         [成功/失敗] (Xエラー)
-Lint:       [成功/失敗] (X警告)
-テスト:     [成功/失敗] (X/Y成功、Z%カバレッジ)
-セキュリティ: [成功/失敗] (X問題)
-差分:       [Xファイル変更]
-
-総合:       PRの準備[完了/未完了]
-
-修正すべき問題:
-1. ...
-2. ...
-```
-
-## 継続モード
-
-長いセッションの場合、15分ごとまたは主要な変更後に検証を実行:
-
-```markdown
-メンタルチェックポイントを設定:
-- 各関数を完了した後
-- コンポーネントを完了した後
-- 次のタスクに移る前
-
-実行: /verify
-```
-
-## フックとの統合
-
-このスキルはPostToolUseフックを補完しますが、より深い検証を提供します。
-フックは問題を即座に捕捉; このスキルは包括的なレビューを提供。
diff --git a/docs/ko-KR/skills/verification-loop/SKILL.md b/docs/ko-KR/skills/verification-loop/SKILL.md
deleted file mode 100644
index ca9a5a0a71..0000000000
--- a/docs/ko-KR/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,127 +0,0 @@
----
-name: verification-loop
-description: "Claude Code 세션을 위한 포괄적인 검증 시스템."
-origin: ECC
----
-
-# 검증 루프 스킬
-
-Claude Code 세션을 위한 포괄적인 검증 시스템.
-
-## 사용 시점
-
-다음 상황에서 이 스킬을 호출하세요:
-- 기능 또는 주요 코드 변경을 완료한 후
-- PR을 생성하기 전
-- 품질 게이트가 통과하는지 확인하고 싶을 때
-- 리팩터링 후
-
-## 검증 단계
-
-### 단계 1: 빌드 검증
-```bash
-# Check if project builds
-npm run build 2>&1 | tail -20
-# OR
-pnpm build 2>&1 | tail -20
-```
-
-빌드가 실패하면 계속하기 전에 중단하고 수정합니다.
-
-### 단계 2: 타입 검사
-```bash
-# TypeScript projects
-npx tsc --noEmit 2>&1 | head -30
-
-# Python projects
-pyright . 2>&1 | head -30
-```
-
-모든 타입 에러를 보고합니다. 중요한 것은 계속하기 전에 수정합니다.
-
-### 단계 3: 린트 검사
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### 단계 4: 테스트 스위트
-```bash
-# Run tests with coverage
-npm run test -- --coverage 2>&1 | tail -50
-
-# Check coverage threshold
-# Target: 80% minimum
-```
-
-보고 항목:
-- 전체 테스트: X
-- 통과: X
-- 실패: X
-- 커버리지: X%
-
-### 단계 5: 보안 스캔
-```bash
-# Check for secrets
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# Check for console.log
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### 단계 6: Diff 리뷰
-```bash
-# Show what changed
-git diff --stat
-git diff --name-only
-git diff --cached --name-only
-```
-
-각 변경된 파일에서 다음을 검토합니다:
-- 의도하지 않은 변경
-- 누락된 에러 처리
-- 잠재적 엣지 케이스
-
-## 출력 형식
-
-모든 단계를 실행한 후 검증 보고서를 생성합니다:
-
-```
-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. ...
-```
-
-## 연속 모드
-
-긴 세션에서는 15분마다 또는 주요 변경 후에 검증을 실행합니다:
-
-```markdown
-Set a mental checkpoint:
-- After completing each function
-- After finishing a component
-- Before moving to next task
-
-Run: /verify
-```
-
-## Hook과의 통합
-
-이 스킬은 PostToolUse Hook을 보완하지만 더 깊은 검증을 제공합니다.
-Hook은 즉시 문제를 포착하고, 이 스킬은 포괄적인 검토를 제공합니다.
diff --git a/docs/tr/skills/verification-loop/SKILL.md b/docs/tr/skills/verification-loop/SKILL.md
deleted file mode 100644
index d6936e8012..0000000000
--- a/docs/tr/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,126 +0,0 @@
----
-name: verification-loop
-description: "Claude Code oturumları için kapsamlı doğrulama sistemi."
-origin: ECC
----
-
-# Verification Loop Skill
-
-Claude Code oturumları için kapsamlı doğrulama sistemi.
-
-## Ne Zaman Kullanılır
-
-Bu skill'i şu durumlarda çağır:
-- Bir özellik veya önemli kod değişikliği tamamladıktan sonra
-- PR oluşturmadan önce
-- Kalite kapılarının geçtiğinden emin olmak istediğinde
-- Refactoring sonrasında
-
-## Doğrulama Fazları
-
-### Faz 1: Build Doğrulaması
-```bash
-# Projenin build olup olmadığını kontrol et
-npm run build 2>&1 | tail -20
-# VEYA
-pnpm build 2>&1 | tail -20
-```
-
-Build başarısız olursa, devam etmeden önce DUR ve düzelt.
-
-### Faz 2: Tip Kontrolü
-```bash
-# TypeScript projeleri
-npx tsc --noEmit 2>&1 | head -30
-
-# Python projeleri
-pyright . 2>&1 | head -30
-```
-
-Tüm tip hatalarını raporla. Devam etmeden önce kritik olanları düzelt.
-
-### Faz 3: Lint Kontrolü
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### Faz 4: Test Paketi
-```bash
-# Testleri coverage ile çalıştır
-npm run test -- --coverage 2>&1 | tail -50
-
-# Coverage eşiğini kontrol et
-# Hedef: minimum %80
-```
-
-Rapor:
-- Toplam testler: X
-- Geçti: X
-- Başarısız: X
-- Coverage: %X
-
-### Faz 5: Güvenlik Taraması
-```bash
-# Secret'ları kontrol et
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# console.log kontrol et
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### Faz 6: Diff İncelemesi
-```bash
-# Neyin değiştiğini göster
-git diff --stat
-git diff HEAD~1 --name-only
-```
-
-Her değişen dosyayı şunlar için incele:
-- İstenmeyen değişiklikler
-- Eksik hata işleme
-- Potansiyel edge case'ler
-
-## Çıktı Formatı
-
-Tüm fazları çalıştırdıktan sonra, bir doğrulama raporu üret:
-
-```
-DOĞRULAMA RAPORU
-==================
-
-Build:     [PASS/FAIL]
-Tipler:    [PASS/FAIL] (X hata)
-Lint:      [PASS/FAIL] (X uyarı)
-Testler:   [PASS/FAIL] (X/Y geçti, %Z coverage)
-Güvenlik:  [PASS/FAIL] (X sorun)
-Diff:      [X dosya değişti]
-
-Genel:     PR için [HAZIR/HAZIR DEĞİL]
-
-Düzeltilmesi Gereken Sorunlar:
-1. ...
-2. ...
-```
-
-## Sürekli Mod
-
-Uzun oturumlar için, her 15 dakikada bir veya major değişikliklerden sonra doğrulama çalıştır:
-
-```markdown
-Mental kontrol noktası belirle:
-- Her fonksiyonu tamamladıktan sonra
-- Bir component'i bitirdikten sonra
-- Sonraki göreve geçmeden önce
-
-Çalıştır: /verify
-```
-
-## Hook'larla Entegrasyon
-
-Bu skill PostToolUse hook'larını tamamlar ancak daha derin doğrulama sağlar.
-Hook'lar sorunları anında yakalar; bu skill kapsamlı inceleme sağlar.
diff --git a/docs/zh-CN/README.md b/docs/zh-CN/README.md
index e363001e0b..e7c6f0a58c 100644
--- a/docs/zh-CN/README.md
+++ b/docs/zh-CN/README.md
@@ -314,10 +314,9 @@ everything-claude-code/
 |   |-- continuous-learning-v2/     # 基于直觉的学习与置信度评分
 |   |-- iterative-retrieval/        # 子代理渐进式上下文优化
 |   |-- strategic-compact/          # 手动压缩建议（长文指南）
-|   |-- tdd-workflow/               # TDD 方法论
+|   |-- tdd-workflow/               # TDD 方法论 + PR 前验证门控
 |   |-- security-review/            # 安全检查清单
 |   |-- eval-harness/               # 验证循环评估（长文指南）
-|   |-- verification-loop/          # 持续验证（长文指南）
 |   |-- videodb/                   # 视频与音频：导入、搜索、编辑、生成与流式处理（新增）
 |   |-- golang-patterns/            # Go 习惯用法与最佳实践
 |   |-- golang-testing/             # Go 测试模式、TDD 与基准测试
@@ -1049,7 +1048,7 @@ Codex macOS 应用：
 | eval-harness | 评估驱动的开发 |
 | strategic-compact | 上下文管理 |
 | api-design | REST API 设计模式 |
-| verification-loop | 构建、测试、代码检查、类型检查、安全 |
+| tdd-workflow | TDD + 构建、测试、代码检查、类型检查、安全验证 |
 
 ### 关键限制
 
diff --git a/docs/zh-CN/skills/autonomous-loops/SKILL.md b/docs/zh-CN/skills/autonomous-loops/SKILL.md
index 15807f6524..81acf2541f 100644
--- a/docs/zh-CN/skills/autonomous-loops/SKILL.md
+++ b/docs/zh-CN/skills/autonomous-loops/SKILL.md
@@ -579,7 +579,7 @@ evictionContext ─────────────────────
 
 2. **连续 Claude + 去草率化** — 为每次迭代添加带有去草率化指令的 `--review-prompt`。
 
-3. **任何循环 + 验证** — 在提交前，使用 ECC 的 `/verify` 命令或 `verification-loop` 技能作为关卡。
+3. **任何循环 + 验证** — 在提交前，使用 ECC 的 `/verify` 命令或 `tdd-workflow` 技能中的验证门控作为关卡。
 
 4. **Ralphinho 在简单循环中的分层方法** — 即使在顺序流水线中，你也可以将简单任务路由到 Haiku，复杂任务路由到 Opus：
    ```bash
@@ -618,4 +618,4 @@ evictionContext ─────────────────────
 | Infinite Agentic Loop | disler | credit: @disler |
 | Continuous Claude | AnandChowdhary | credit: @AnandChowdhary |
 | NanoClaw | ECC | 此仓库中的 `/claw` 命令 |
-| Verification Loop | ECC | 此仓库中的 `skills/verification-loop/` |
+| Verification Gate | ECC | `skills/tdd-workflow/` 中的 PR 前验证 |
diff --git a/docs/zh-CN/skills/configure-ecc/SKILL.md b/docs/zh-CN/skills/configure-ecc/SKILL.md
index fad024c313..2197b1c65c 100644
--- a/docs/zh-CN/skills/configure-ecc/SKILL.md
+++ b/docs/zh-CN/skills/configure-ecc/SKILL.md
@@ -150,7 +150,7 @@ mkdir -p $TARGET/skills $TARGET/rules
 | `security-review` | 安全检查清单：身份验证、输入、密钥、API、支付功能 |
 | `strategic-compact` | 在逻辑间隔处建议手动上下文压缩 |
 | `tdd-workflow` | 强制要求 TDD，覆盖率 80% 以上：单元测试、集成测试、端到端测试 |
-| `verification-loop` | 验证和质量循环模式 |
+| `tdd-workflow` | TDD 方法论 + PR 前验证门控 |
 
 **类别：业务与内容（5 项技能）**
 
diff --git a/docs/zh-CN/skills/plankton-code-quality/SKILL.md b/docs/zh-CN/skills/plankton-code-quality/SKILL.md
index f5c888c411..05264674df 100644
--- a/docs/zh-CN/skills/plankton-code-quality/SKILL.md
+++ b/docs/zh-CN/skills/plankton-code-quality/SKILL.md
@@ -131,7 +131,7 @@ claude
 1. 将 ECC 安装为你的插件（代理、技能、命令、规则）
 2. 添加 Plankton 钩子以实现编写时质量强制执行
 3. 使用 AgentShield 进行安全审计
-4. 在 PR 之前使用 ECC 的 verification-loop 作为最后一道关卡
+4. 在 PR 之前使用 ECC 的 tdd-workflow 验证门控作为最后一道关卡
 
 ### 避免钩子冲突
 
diff --git a/docs/zh-CN/skills/prompt-optimizer/SKILL.md b/docs/zh-CN/skills/prompt-optimizer/SKILL.md
index 73a3fbf0b2..453e5f9ad4 100644
--- a/docs/zh-CN/skills/prompt-optimizer/SKILL.md
+++ b/docs/zh-CN/skills/prompt-optimizer/SKILL.md
@@ -99,9 +99,9 @@ metadata:
 
 | 意图 | 命令 | 技能 | 代理 |
 |--------|----------|--------|--------|
-| 新功能 | /plan, /tdd, /code-review, /verify | tdd-workflow, verification-loop | planner, tdd-guide, code-reviewer |
+| 新功能 | /plan, /tdd, /code-review, /verify | tdd-workflow | planner, tdd-guide, code-reviewer |
 | 错误修复 | /tdd, /build-fix, /verify | tdd-workflow | tdd-guide, build-error-resolver |
-| 重构 | /refactor-clean, /code-review, /verify | verification-loop | refactor-cleaner, code-reviewer |
+| 重构 | /refactor-clean, /code-review, /verify | tdd-workflow | refactor-cleaner, code-reviewer |
 | 研究 | /plan | search-first, iterative-retrieval | — |
 | 测试 | /tdd, /e2e, /test-coverage | tdd-workflow, e2e-testing | tdd-guide, e2e-runner |
 | 审查 | /code-review | security-review | code-reviewer, security-reviewer |
diff --git a/docs/zh-CN/skills/verification-loop/SKILL.md b/docs/zh-CN/skills/verification-loop/SKILL.md
deleted file mode 100644
index 6607fe8bf0..0000000000
--- a/docs/zh-CN/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,136 +0,0 @@
----
-name: verification-loop
-description: "Claude Code 会话的全面验证系统。"
-origin: ECC
----
-
-# 验证循环技能
-
-一个全面的 Claude Code 会话验证系统。
-
-## 何时使用
-
-在以下情况下调用此技能：
-
-* 完成功能或重大代码变更后
-* 创建 PR 之前
-* 当您希望确保质量门通过时
-* 重构之后
-
-## 验证阶段
-
-### 阶段 1：构建验证
-
-```bash
-# Check if project builds
-npm run build 2>&1 | tail -20
-# OR
-pnpm build 2>&1 | tail -20
-```
-
-如果构建失败，请停止并在继续之前修复。
-
-### 阶段 2：类型检查
-
-```bash
-# TypeScript projects
-npx tsc --noEmit 2>&1 | head -30
-
-# Python projects
-pyright . 2>&1 | head -30
-```
-
-报告所有类型错误。在继续之前修复关键错误。
-
-### 阶段 3：代码规范检查
-
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### 阶段 4：测试套件
-
-```bash
-# Run tests with coverage
-npm run test -- --coverage 2>&1 | tail -50
-
-# Check coverage threshold
-# Target: 80% minimum
-```
-
-报告：
-
-* 总测试数：X
-* 通过：X
-* 失败：X
-* 覆盖率：X%
-
-### 阶段 5：安全扫描
-
-```bash
-# Check for secrets
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# Check for console.log
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### 阶段 6：差异审查
-
-```bash
-# Show what changed
-git diff --stat
-git diff HEAD~1 --name-only
-```
-
-审查每个更改的文件，检查：
-
-* 意外更改
-* 缺失的错误处理
-* 潜在的边界情况
-
-## 输出格式
-
-运行所有阶段后，生成验证报告：
-
-```
-验证报告
-==================
-
-构建:     [通过/失败]
-类型:     [通过/失败] (X 处错误)
-代码检查:  [通过/失败] (X 条警告)
-测试:     [通过/失败] (X/Y 通过，覆盖率 Z%)
-安全:     [通过/失败] (X 个问题)
-差异:      [X 个文件被修改]
-
-总体:     [就绪/未就绪] 提交 PR
-
-待修复问题:
-1. ...
-2. ...
-```
-
-## 持续模式
-
-对于长时间会话，每 15 分钟或在重大更改后运行验证：
-
-```markdown
-设置一个心理检查点：
-- 完成每个函数后
-- 完成一个组件后
-- 在移动到下一个任务之前
-
-运行: /verify
-
-```
-
-## 与钩子的集成
-
-此技能补充 PostToolUse 钩子，但提供更深入的验证。
-钩子会立即捕获问题；此技能提供全面的审查。
diff --git a/docs/zh-TW/README.md b/docs/zh-TW/README.md
index 5185e9c636..14469fefa8 100644
--- a/docs/zh-TW/README.md
+++ b/docs/zh-TW/README.md
@@ -168,10 +168,9 @@ everything-claude-code/
 |   |-- continuous-learning-v2/     # 基於本能的學習與信心評分
 |   |-- iterative-retrieval/        # 子代理程式的漸進式上下文精煉
 |   |-- strategic-compact/          # 手動壓縮建議（完整指南）
-|   |-- tdd-workflow/               # TDD 方法論
+|   |-- tdd-workflow/               # TDD 方法論 + PR 前驗證門控
 |   |-- security-review/            # 安全性檢查清單
 |   |-- eval-harness/               # 驗證迴圈評估（完整指南）
-|   |-- verification-loop/          # 持續驗證（完整指南）
 |   |-- golang-patterns/            # Go 慣用語法和最佳實務（新增）
 |   |-- golang-testing/             # Go 測試模式、TDD、基準測試（新增）
 |
diff --git a/docs/zh-TW/skills/verification-loop/SKILL.md b/docs/zh-TW/skills/verification-loop/SKILL.md
deleted file mode 100644
index 07efbf8c25..0000000000
--- a/docs/zh-TW/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,120 +0,0 @@
-# 驗證循環技能
-
-Claude Code 工作階段的完整驗證系統。
-
-## 何時使用
-
-在以下情況呼叫此技能：
-- 完成功能或重大程式碼變更後
-- 建立 PR 前
-- 想確保品質門檻通過時
-- 重構後
-
-## 驗證階段
-
-### 階段 1：建置驗證
-```bash
-# 檢查專案是否建置
-npm run build 2>&1 | tail -20
-# 或
-pnpm build 2>&1 | tail -20
-```
-
-如果建置失敗，停止並在繼續前修復。
-
-### 階段 2：型別檢查
-```bash
-# TypeScript 專案
-npx tsc --noEmit 2>&1 | head -30
-
-# Python 專案
-pyright . 2>&1 | head -30
-```
-
-報告所有型別錯誤。繼續前修復關鍵錯誤。
-
-### 階段 3：Lint 檢查
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### 階段 4：測試套件
-```bash
-# 執行帶覆蓋率的測試
-npm run test -- --coverage 2>&1 | tail -50
-
-# 檢查覆蓋率門檻
-# 目標：最低 80%
-```
-
-報告：
-- 總測試數：X
-- 通過：X
-- 失敗：X
-- 覆蓋率：X%
-
-### 階段 5：安全掃描
-```bash
-# 檢查密鑰
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# 檢查 console.log
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### 階段 6：差異審查
-```bash
-# 顯示變更內容
-git diff --stat
-git diff HEAD~1 --name-only
-```
-
-審查每個變更的檔案：
-- 非預期變更
-- 缺少錯誤處理
-- 潛在邊界案例
-
-## 輸出格式
-
-執行所有階段後，產生驗證報告：
-
-```
-驗證報告
-==================
-
-建置：     [PASS/FAIL]
-型別：     [PASS/FAIL]（X 個錯誤）
-Lint：     [PASS/FAIL]（X 個警告）
-測試：     [PASS/FAIL]（X/Y 通過，Z% 覆蓋率）
-安全性：   [PASS/FAIL]（X 個問題）
-差異：     [X 個檔案變更]
-
-整體：     [READY/NOT READY] for PR
-
-待修復問題：
-1. ...
-2. ...
-```
-
-## 持續模式
-
-對於長時間工作階段，每 15 分鐘或重大變更後執行驗證：
-
-```markdown
-設定心理檢查點：
-- 完成每個函式後
-- 完成元件後
-- 移至下一個任務前
-
-執行：/verify
-```
-
-## 與 Hooks 整合
-
-此技能補充 PostToolUse hooks 但提供更深入的驗證。
-Hooks 立即捕捉問題；此技能提供全面審查。
diff --git a/manifests/install-components.json b/manifests/install-components.json
index 8f3d73064c..16098fb0b6 100644
--- a/manifests/install-components.json
+++ b/manifests/install-components.json
@@ -355,14 +355,6 @@
         "workflow-quality"
       ]
     },
-    {
-      "id": "skill:verification-loop",
-      "family": "skill",
-      "description": "Verification loop for code quality assurance.",
-      "modules": [
-        "workflow-quality"
-      ]
-    },
     {
       "id": "skill:strategic-compact",
       "family": "skill",
diff --git a/manifests/install-modules.json b/manifests/install-modules.json
index 619d39483b..3e3f40f65a 100644
--- a/manifests/install-modules.json
+++ b/manifests/install-modules.json
@@ -197,8 +197,7 @@
         "skills/project-guidelines-example",
         "skills/skill-stocktake",
         "skills/strategic-compact",
-        "skills/tdd-workflow",
-        "skills/verification-loop"
+        "skills/tdd-workflow"
       ],
       "targets": [
         "claude",
diff --git a/skills/autonomous-loops/SKILL.md b/skills/autonomous-loops/SKILL.md
index d6f455723a..0bbb4919f6 100644
--- a/skills/autonomous-loops/SKILL.md
+++ b/skills/autonomous-loops/SKILL.md
@@ -568,7 +568,7 @@ These patterns compose well:
 
 2. **Continuous Claude + De-Sloppify** — Add `--review-prompt` with a de-sloppify directive to each iteration.
 
-3. **Any loop + Verification** — Use ECC's `/verify` command or `verification-loop` skill as a gate before commits.
+3. **Any loop + Verification** — Use ECC's `/verify` command or the verification gate in the `tdd-workflow` skill as a gate before commits.
 
 4. **Ralphinho's tiered approach in simpler loops** — Even in a sequential pipeline, you can route simple tasks to Haiku and complex tasks to Opus:
    ```bash
@@ -607,4 +607,4 @@ These patterns compose well:
 | Infinite Agentic Loop | disler | credit: @disler |
 | Continuous Claude | AnandChowdhary | credit: @AnandChowdhary |
 | NanoClaw | ECC | `/claw` command in this repo |
-| Verification Loop | ECC | `skills/verification-loop/` in this repo |
+| Verification Gate | ECC | Pre-PR verification in `skills/tdd-workflow/` |
diff --git a/skills/configure-ecc/SKILL.md b/skills/configure-ecc/SKILL.md
index 07109a30e0..8e1779c9b5 100644
--- a/skills/configure-ecc/SKILL.md
+++ b/skills/configure-ecc/SKILL.md
@@ -146,7 +146,7 @@ For each selected category, print the full list of skills below and ask the user
 | `security-review` | Security checklist: auth, input, secrets, API, payment features |
 | `strategic-compact` | Suggests manual context compaction at logical intervals |
 | `tdd-workflow` | Enforces TDD with 80%+ coverage: unit, integration, E2E |
-| `verification-loop` | Verification and quality loop patterns |
+| `tdd-workflow` | TDD methodology with pre-PR verification gate |
 
 **Category: Business & Content (5 skills)**
 
diff --git a/skills/plankton-code-quality/SKILL.md b/skills/plankton-code-quality/SKILL.md
index 16513c2573..f1ba3bed66 100644
--- a/skills/plankton-code-quality/SKILL.md
+++ b/skills/plankton-code-quality/SKILL.md
@@ -127,7 +127,7 @@ To use Plankton hooks in your own project:
 1. Install ECC as your plugin (agents, skills, commands, rules)
 2. Add Plankton hooks for write-time quality enforcement
 3. Use AgentShield for security audits
-4. Use ECC's verification-loop as a final gate before PRs
+4. Use ECC's tdd-workflow verification gate as a final gate before PRs
 
 ### Avoiding Hook Conflicts
 
diff --git a/skills/prompt-optimizer/SKILL.md b/skills/prompt-optimizer/SKILL.md
index 3241968c0b..93aba2f0ca 100644
--- a/skills/prompt-optimizer/SKILL.md
+++ b/skills/prompt-optimizer/SKILL.md
@@ -117,9 +117,9 @@ Map intent + scope + tech stack (from Phase 0) to specific ECC components.
 
 | Intent | Commands | Skills | Agents |
 |--------|----------|--------|--------|
-| New Feature | /plan, /tdd, /code-review, /verify | tdd-workflow, verification-loop | planner, tdd-guide, code-reviewer |
+| New Feature | /plan, /tdd, /code-review, /verify | tdd-workflow | planner, tdd-guide, code-reviewer |
 | Bug Fix | /tdd, /build-fix, /verify | tdd-workflow | tdd-guide, build-error-resolver |
-| Refactor | /refactor-clean, /code-review, /verify | verification-loop | refactor-cleaner, code-reviewer |
+| Refactor | /refactor-clean, /code-review, /verify | tdd-workflow | refactor-cleaner, code-reviewer |
 | Research | /plan | search-first, iterative-retrieval | — |
 | Testing | /tdd, /e2e, /test-coverage | tdd-workflow, e2e-testing | tdd-guide, e2e-runner |
 | Review | /code-review | security-review | code-reviewer, security-reviewer |
diff --git a/skills/santa-method/SKILL.md b/skills/santa-method/SKILL.md
index 77a9ac8711..27f72bbb1e 100644
--- a/skills/santa-method/SKILL.md
+++ b/skills/santa-method/SKILL.md
@@ -279,7 +279,7 @@ def santa_batch(items, rubric, sample_rate=0.15):
 
 | Skill | Relationship |
 |-------|-------------|
-| Verification Loop | Use for deterministic checks (build, lint, test). Santa for semantic checks (accuracy, hallucinations). Run verification-loop first, Santa second. |
+| TDD Workflow (Verification Gate) | Use for deterministic checks (build, lint, test). Santa for semantic checks (accuracy, hallucinations). Run the tdd-workflow verification gate first, Santa second. |
 | Eval Harness | Santa Method results feed eval metrics. Track pass@k across Santa runs to measure generator quality over time. |
 | Continuous Learning v2 | Santa findings become instincts. Repeated failures on the same criterion → learned behavior to avoid the pattern. |
 | Strategic Compact | Run Santa BEFORE compacting. Don't lose review context mid-verification. |
diff --git a/skills/tdd-workflow/SKILL.md b/skills/tdd-workflow/SKILL.md
index 76aaaa1ac7..e9f55728d7 100644
--- a/skills/tdd-workflow/SKILL.md
+++ b/skills/tdd-workflow/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: tdd-workflow
-description: Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
+description: Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests. Includes pre-PR verification gates (build, type-check, lint, security, diff review).
 origin: ECC
 ---
 
@@ -15,6 +15,9 @@ This skill ensures all code development follows TDD principles with comprehensiv
 - Refactoring existing code
 - Adding API endpoints
 - Creating new components
+- After completing a feature or significant code change (verification gate)
+- Before creating a PR (pre-PR verification)
+- When you want to ensure quality gates pass
 
 ## Core Principles
 
@@ -230,57 +233,10 @@ describe('GET /api/markets', () => {
 ```
 
 ### E2E Test Pattern (Playwright)
-```typescript
-import { test, expect } from '@playwright/test'
-
-test('user can search and filter markets', async ({ page }) => {
-  // Navigate to markets page
-  await page.goto('/')
-  await page.click('a[href="/markets"]')
-
-  // Verify page loaded
-  await expect(page.locator('h1')).toContainText('Markets')
-
-  // Search for markets
-  await page.fill('input[placeholder="Search markets"]', 'election')
 
-  // Wait for debounce and results
-  await page.waitForTimeout(600)
-
-  // Verify search results displayed
-  const results = page.locator('[data-testid="market-card"]')
-  await expect(results).toHaveCount(5, { timeout: 5000 })
-
-  // Verify results contain search term
-  const firstResult = results.first()
-  await expect(firstResult).toContainText('election', { ignoreCase: true })
-
-  // Filter by status
-  await page.click('button:has-text("Active")')
-
-  // Verify filtered results
-  await expect(results).toHaveCount(3)
-})
-
-test('user can create a new market', async ({ page }) => {
-  // Login first
-  await page.goto('/creator-dashboard')
-
-  // Fill market creation form
-  await page.fill('input[name="name"]', 'Test Market')
-  await page.fill('textarea[name="description"]', 'Test description')
-  await page.fill('input[name="endDate"]', '2025-12-31')
-
-  // Submit form
-  await page.click('button[type="submit"]')
-
-  // Verify success message
-  await expect(page.locator('text=Market created successfully')).toBeVisible()
-
-  // Verify redirect to market page
-  await expect(page).toHaveURL(/\/markets\/test-market/)
-})
-```
+For comprehensive Playwright patterns including Page Object Model, configuration,
+flaky test strategies, artifact management, and CI/CD integration, see the
+[e2e-testing skill](../e2e-testing/SKILL.md).
 
 ## Test File Organization
 
@@ -458,6 +414,116 @@ npm test && npm run lint
 - E2E tests cover critical user flows
 - Tests catch bugs before production
 
+## Pre-PR Verification Gate
+
+After completing the TDD cycle, run a full verification gate before creating a PR.
+This replaces the former `verification-loop` skill.
+
+### Phase 1: Build Verification
+```bash
+# Check if project builds
+npm run build 2>&1 | tail -20
+# OR
+pnpm build 2>&1 | tail -20
+```
+
+If build fails, STOP and fix before continuing.
+
+### Phase 2: Type Check
+```bash
+# TypeScript projects
+npx tsc --noEmit 2>&1 | head -30
+
+# Python projects
+pyright . 2>&1 | head -30
+```
+
+Report all type errors. Fix critical ones before continuing.
+
+### Phase 3: Lint Check
+```bash
+# JavaScript/TypeScript
+npm run lint 2>&1 | head -30
+
+# Python
+ruff check . 2>&1 | head -30
+```
+
+### Phase 4: Test Suite
+```bash
+# Run tests with coverage
+npm 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 secrets
+grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
+grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
+
+# Check for console.log
+grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
+```
+
+### Phase 6: Diff Review
+```bash
+# Show what changed
+git diff --stat
+git diff HEAD~1 --name-only
+```
+
+Review each changed file for:
+- Unintended changes
+- Missing error handling
+- Potential edge cases
+
+### Verification Report 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 Verification
+
+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
+```
+
+This verification gate complements PostToolUse hooks but provides deeper,
+comprehensive review.
+
 ---
 
 **Remember**: Tests are not optional. They are the safety net that enables confident refactoring, rapid development, and production reliability.
diff --git a/skills/verification-loop/SKILL.md b/skills/verification-loop/SKILL.md
deleted file mode 100644
index 1933545d57..0000000000
--- a/skills/verification-loop/SKILL.md
+++ /dev/null
@@ -1,126 +0,0 @@
----
-name: verification-loop
-description: "A comprehensive verification system for Claude Code sessions."
-origin: ECC
----
-
-# 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 builds
-npm run build 2>&1 | tail -20
-# OR
-pnpm build 2>&1 | tail -20
-```
-
-If build fails, STOP and fix before continuing.
-
-### Phase 2: Type Check
-```bash
-# TypeScript projects
-npx tsc --noEmit 2>&1 | head -30
-
-# Python projects
-pyright . 2>&1 | head -30
-```
-
-Report all type errors. Fix critical ones before continuing.
-
-### Phase 3: Lint Check
-```bash
-# JavaScript/TypeScript
-npm run lint 2>&1 | head -30
-
-# Python
-ruff check . 2>&1 | head -30
-```
-
-### Phase 4: Test Suite
-```bash
-# Run tests with coverage
-npm 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 secrets
-grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
-
-# Check for console.log
-grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
-```
-
-### Phase 6: Diff Review
-```bash
-# Show what changed
-git diff --stat
-git 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.