diff --git a/skills/research/SKILL.md b/skills/research/SKILL.md
index 37ed79d..bcb0431 100644
--- a/skills/research/SKILL.md
+++ b/skills/research/SKILL.md
@@ -1,55 +1,140 @@
 ---
 allowed-tools: Read, Write, Glob, WebSearch, Task, AskUserQuestion
-description: 对目标话题进行初步调研，生成调研outline。用于学术调研、benchmark调研、技术选型等场景。
+description: Conduct preliminary research on a topic and generate a research outline. Use for academic research, benchmark research, technology selection, etc.
 ---
 
-# Research Skill - 初步调研
+# Research Skill - Preliminary Research
 
-## 触发方式
+## Trigger
 `/research <topic>`
 
-## 执行流程
+## Workflow
 
-### Step 1: 模型内部知识生成初步框架
-基于topic，利用模型已有知识生成：
-- 该领域的主要研究对象/items列表
-- 建议的调研字段框架
+### Step 1: Generate Initial Framework from Model Knowledge
+Based on the topic, use model's existing knowledge to generate:
+- Main research objects/items list in this domain
+- Suggested research field framework
 
-### Step 2: Web Search补充
-启动1个web-search-agent（后台），传入topic和当前日期备注，agent自行设计搜索策略补充最新items和字段建议。等待完成后获取搜集知识。
+Output {step1_output}.
 
-### Step 3: 询问用户已有字段
-使用AskUserQuestion询问用户是否有已定义的字段文件，如有则读取并合并。
+### Step 2: Web Search Supplement
+Use AskUserQuestion to ask for time range (e.g., last 6 months, since 2024, unlimited).
 
-### Step 4: 生成Outline（分离文件）
-合并所有信息，生成两个文件：
+**Parameter Retrieval**:
+- `{topic}`: User input research topic
+- `{YYYY-MM-DD}`: Current date
+- `{step1_output}`: Complete output from Step 1
+- `{time_range}`: User specified time range
 
-**outline.yaml**（items + 配置）：
-- topic: 调研主题
-- items: 调研对象列表
+**Hard Constraint**: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.
+
+Launch 1 web-search-agent (background), **Prompt Template**:
+```python
+prompt = f"""## Task
+Research topic: {topic}
+Current date: {YYYY-MM-DD}
+
+Based on the following initial framework, supplement latest items and recommended research fields.
+
+## Existing Framework
+{step1_output}
+
+## Goals
+1. Verify if existing items are missing important objects
+2. Supplement items based on missing objects
+3. Continue searching for {topic} related items within {time_range} and supplement
+4. Supplement new fields
+
+## Output Requirements
+Return structured results directly (do not write files):
+
+### Supplementary Items
+- item_name: Brief explanation (why it should be added)
+...
+
+### Recommended Supplementary Fields
+- field_name: Field description (why this dimension is needed)
+...
+
+### Sources
+- [Source1](url1)
+- [Source2](url2)
+"""
+```
+
+**One-shot Example** (assuming researching AI Coding History):
+```
+## Task
+Research topic: AI Coding History
+Current date: 2025-12-30
+
+Based on the following initial framework, supplement latest items and recommended research fields.
+
+## Existing Framework
+### Items List
+1. GitHub Copilot: Developed by Microsoft/GitHub, first mainstream AI coding assistant
+2. Cursor: AI-first IDE, based on VSCode
+...
+
+### Field Framework
+- Basic Info: name, release_date, company
+- Technical Features: underlying_model, context_window
+...
+
+## Goals
+1. Verify if existing items are missing important objects
+2. Supplement items based on missing objects
+3. Continue searching for AI Coding History related items within since 2024 and supplement
+4. Supplement new fields
+
+## Output Requirements
+Return structured results directly (do not write files):
+
+### Supplementary Items
+- item_name: Brief explanation (why it should be added)
+...
+
+### Recommended Supplementary Fields
+- field_name: Field description (why this dimension is needed)
+...
+
+### Sources
+- [Source1](url1)
+- [Source2](url2)
+```
+
+### Step 3: Ask User for Existing Fields
+Use AskUserQuestion to ask if user has existing field definition file, if so read and merge.
+
+### Step 4: Generate Outline (Separate Files)
+Merge {step1_output}, {step2_output} and user's existing fields, generate two files:
+
+**outline.yaml** (items + config):
+- topic: Research topic
+- items: Research objects list
 - execution:
-  - batch_size: 并行agent数量（默认5）
-  - items_per_agent: 每个agent调研项目数（默认1，需AskUserQuestion确认）
-  - output_dir: 结果输出目录（默认./results）
+  - batch_size: Number of parallel agents (confirm with AskUserQuestion)
+  - items_per_agent: Items per agent (confirm with AskUserQuestion)
+  - output_dir: Results output directory (default: ./results)
 
-**fields.yaml**（字段定义）：
-- 字段分类和定义
-- 每个字段的name、description、detail_level
-- uncertain: 不确定字段列表（保留字段，deep阶段自动填充）
+**fields.yaml** (field definitions):
+- Field categories and definitions
+- Each field's name, description, detail_level
+- uncertain: Uncertain fields list (reserved field, auto-filled in deep phase)
 
-### Step 5: 输出并确认
-- 创建目录: `./{topic_slug}/`
-- 保存: `outline.yaml` 和 `fields.yaml`
-- 展示给用户确认
+### Step 5: Output and Confirm
+- Create directory: `./{topic_slug}/`
+- Save: `outline.yaml` and `fields.yaml`
+- Show to user for confirmation
 
-## 输出路径
+## Output Path
 ```
-{当前工作目录}/{topic_slug}/
-  ├── outline.yaml    # items列表 + execution配置
-  └── fields.yaml     # 字段定义
+{current_working_directory}/{topic_slug}/
+  ├── outline.yaml    # items list + execution config
+  └── fields.yaml     # field definitions
 ```
 
-## 后续命令
-- `/research-add-items` - 补充items
-- `/research-add-fields` - 补充字段
-- `/research-deep` - 开始深度调研
+## Follow-up Commands
+- `/research-add-items` - Supplement items
+- `/research-add-fields` - Supplement fields
+- `/research-deep` - Start deep research
diff --git a/skills/research/add-fields/SKILL.md b/skills/research/add-fields/SKILL.md
index 639c5bf..c77d7d1 100644
--- a/skills/research/add-fields/SKILL.md
+++ b/skills/research/add-fields/SKILL.md
@@ -1,30 +1,30 @@
 ---
-description: 向现有调研outline补充字段定义。
+description: Add field definitions to existing research outline.
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion
 ---
 
-# Research Add Fields - 补充调研字段
+# Research Add Fields - Supplement Research Fields
 
-## 触发方式
+## Trigger
 `/research-add-fields`
 
-## 执行流程
+## Workflow
 
-### Step 1: 自动定位Fields文件
-在当前工作目录查找 `*/fields.yaml` 文件，自动读取现有fields定义。
+### Step 1: Auto-locate Fields File
+Find `*/fields.yaml` file in current working directory, auto-read existing fields definitions.
 
-### Step 2: 获取补充来源
-询问用户选择：
-- **A. 用户直接输入**：用户提供字段名称和描述
-- **B. Web Search搜索**：启动agent搜索该领域常用字段
+### Step 2: Get Supplement Source
+Ask user to choose:
+- **A. User direct input**: User provides field names and descriptions
+- **B. Web Search**: Launch agent to search common fields in this domain
 
-### Step 3: 展示并确认
-- 展示建议的新字段列表
-- 用户确认哪些字段需要添加
-- 用户指定字段分类和detail_level
+### Step 3: Display and Confirm
+- Display suggested new fields list
+- User confirms which fields to add
+- User specifies field category and detail_level
 
-### Step 4: 保存更新
-将确认的字段追加到fields.yaml，保存文件。
+### Step 4: Save Update
+Append confirmed fields to fields.yaml, save file.
 
-## 输出
-更新后的 `{topic}/fields.yaml` 文件（原地修改，需用户确认）
+## Output
+Updated `{topic}/fields.yaml` file (in-place modification, requires user confirmation)
diff --git a/skills/research/add-items/SKILL.md b/skills/research/add-items/SKILL.md
index aa74eb0..c902004 100644
--- a/skills/research/add-items/SKILL.md
+++ b/skills/research/add-items/SKILL.md
@@ -1,28 +1,28 @@
 ---
-description: 向现有调研outline补充items（调研对象）。
+description: Add items (research objects) to existing research outline.
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion
 ---
 
-# Research Add Items - 补充调研对象
+# Research Add Items - Supplement Research Objects
 
-## 触发方式
+## Trigger
 `/research-add-items`
 
-## 执行流程
+## Workflow
 
-### Step 1: 自动定位Outline
-在当前工作目录查找 `*/outline.yaml` 文件，自动读取。
+### Step 1: Auto-locate Outline
+Find `*/outline.yaml` file in current working directory, auto-read.
 
-### Step 2: 并行获取补充来源
-同时进行：
-- **A. 询问用户**：需要补充哪些items？有具体名称吗？
-- **B. 询问是否需要Web Search**：是否启动agent搜索更多items？
+### Step 2: Get Supplement Sources in Parallel
+Simultaneously:
+- **A. Ask user**: What items to supplement? Any specific names?
+- **B. Ask if Web Search needed**: Launch agent to search for more items?
 
-### Step 3: 合并更新
-- 将新items追加到outline.yaml
-- 展示给用户确认
-- 避免重复
-- 保存更新后的outline
+### Step 3: Merge and Update
+- Append new items to outline.yaml
+- Display to user for confirmation
+- Avoid duplicates
+- Save updated outline
 
-## 输出
-更新后的 `{topic}/outline.yaml` 文件（原地修改）
+## Output
+Updated `{topic}/outline.yaml` file (in-place modification)
diff --git a/skills/research/deep/SKILL.md b/skills/research/deep/SKILL.md
index a5fa8f4..b8f7372 100644
--- a/skills/research/deep/SKILL.md
+++ b/skills/research/deep/SKILL.md
@@ -1,55 +1,96 @@
 ---
-description: 读取调研outline，为每个item启动独立agent进行深度调研。禁用task output。
+description: Read research outline, launch independent agent for each item for deep research. Disable task output.
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task
 ---
 
-# Research Deep - 深度调研
+# Research Deep - Deep Research
 
-## 触发方式
+## Trigger
 `/research-deep`
 
-## 执行流程
+## Workflow
 
-### Step 1: 自动定位Outline
-在当前工作目录查找 `*/outline.yaml` 文件，读取items列表、execution配置（含items_per_agent）。
+### Step 1: Auto-locate Outline
+Find `*/outline.yaml` file in current working directory, read items list, execution config (including items_per_agent).
 
-### Step 2: 断点续传检查
-- 检查output_dir下已完成的JSON文件
-- 跳过已完成的items
+### Step 2: Resume Check
+- Check completed JSON files in output_dir
+- Skip completed items
 
-### Step 3: 分批执行
-- 按batch_size分批（完成一批需要得到用户同意才可进行下一批）
-- 每个agent负责items_per_agent个项目
-- 启动web-search-agent（后台并行，禁用task output），使用以下prompt模板：
+### Step 3: Batch Execution
+- Batch by batch_size (need user approval before next batch)
+- Each agent handles items_per_agent items
+- Launch web-search-agent (background parallel, disable task output)
 
-```
-## 任务
-调研 {item_related_info}，输出结构化JSON到 {output_path}
+**Parameter Retrieval**:
+- `{topic}`: topic field from outline.yaml
+- `{item_name}`: item's name field
+- `{item_related_info}`: item's complete yaml content (name + category + description etc.)
+- `{output_dir}`: execution.output_dir from outline.yaml (default: ./results)
+- `{fields_path}`: absolute path to {topic}/fields.yaml
+- `{output_path}`: absolute path to {output_dir}/{item_name}.json
 
-## 字段定义
-读取 {topic}/fields.yaml 获取所有字段定义
+**Hard Constraint**: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.
 
-## 输出要求
-1. 按fields.yaml定义的字段输出JSON
-2. 不确定的字段值标注[不确定]
-3. JSON末尾添加uncertain数组，列出所有不确定的字段名
+**Prompt Template**:
+```python
+prompt = f"""## Task
+Research {item_related_info}, output structured JSON to {output_path}
 
-## 输出路径
-{output_dir}/{item_name}.json
+## Field Definitions
+Read {fields_path} to get all field definitions
+
+## Output Requirements
+1. Output JSON according to fields defined in fields.yaml
+2. Mark uncertain field values with [uncertain]
+3. Add uncertain array at the end of JSON, listing all uncertain field names
+
+## Output Path
+{output_path}
+
+## Validation
+After completing JSON output, run validation script to ensure complete field coverage:
+python ~/.claude/commands/research/validate_json.py -f {fields_path} -j {output_path}
+Task is complete only after validation passes.
+"""
 ```
 
-### Step 4: 等待与监控
-- 等待当前批次完成
-- 启动下一批
-- 显示进度
+**One-shot Example** (assuming researching GitHub Copilot):
+```
+## Task
+Research name: GitHub Copilot
+category: International Product
+description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json
 
-### Step 5: 汇总报告
-全部完成后输出：
-- 完成数量
-- 失败/不确定标记的items
-- 输出目录
+## Field Definitions
+Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field definitions
 
-## Agent配置
-- 后台执行: 是
-- Task Output: 禁用（agent完成时有明确输出文件）
-- 断点续传: 是
+## Output Requirements
+1. Output JSON according to fields defined in fields.yaml
+2. Mark uncertain field values with [uncertain]
+3. Add uncertain array at the end of JSON, listing all uncertain field names
+
+## Output Path
+/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json
+
+## Validation
+After completing JSON output, run validation script to ensure complete field coverage:
+python ~/.claude/commands/research/validate_json.py -f /home/weizhena/AIcoding/aicoding-history/fields.yaml -j /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json
+Task is complete only after validation passes.
+```
+
+### Step 4: Wait and Monitor
+- Wait for current batch to complete
+- Launch next batch
+- Display progress
+
+### Step 5: Summary Report
+After all complete, output:
+- Completion count
+- Failed/uncertain marked items
+- Output directory
+
+## Agent Config
+- Background execution: Yes
+- Task Output: Disabled (agent has explicit output file when complete)
+- Resume support: Yes
diff --git a/skills/research/report/SKILL.md b/skills/research/report/SKILL.md
index 0afb7ad..5c235a4 100644
--- a/skills/research/report/SKILL.md
+++ b/skills/research/report/SKILL.md
@@ -1,31 +1,71 @@
 ---
-description: 将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。
+description: Summarize deep research results into markdown report, cover all fields, skip uncertain values.
 allowed-tools: Read, Write, Glob, Bash
 ---
 
-# Research Report - 汇总报告
+# Research Report - Summary Report
 
-## 触发方式
+## Trigger
 `/research-report`
 
-## 执行流程
+## Workflow
 
-### Step 1: 定位结果目录
-在当前工作目录查找 `*/outline.yaml`，读取topic和output_dir配置。
+### Step 1: Locate Results Directory
+Find `*/outline.yaml` in current working directory, read topic and output_dir config.
 
-### Step 2: 生成Python转换脚本
-在 `{topic}/` 目录下生成 `generate_report.py`，脚本要求：
-- 读取output_dir下所有JSON
-- 读取fields.yaml获取字段结构
-- 覆盖每个JSON的所有字段值
-- 跳过值包含[不确定]的字段
-- 跳过uncertain字段
-- 生成markdown报告格式：目录（带锚点跳转）+ 详细内容（按字段分类）
-- 保存到 `{topic}/report.md`
+### Step 2: Generate Python Conversion Script
+Generate `generate_report.py` in `{topic}/` directory, script requirements:
+- Read all JSON from output_dir
+- Read fields.yaml to get field structure
+- Cover all field values from each JSON
+- Skip fields with values containing [uncertain]
+- Skip fields listed in uncertain array
+- Generate markdown report format: Table of contents (with anchor links) + Detailed content (by field category)
+- Save to `{topic}/report.md`
 
-### Step 3: 执行脚本
-运行 `python {topic}/generate_report.py`
+#### Script Technical Requirements (Must Follow)
 
-## 输出
-- `{topic}/generate_report.py` - 转换脚本
-- `{topic}/report.md` - 汇总报告
+**1. JSON Structure Compatibility**
+Support two JSON structures:
+- Flat structure: Fields directly at top level `{"name": "xxx", "release_date": "xxx"}`
+- Nested structure: Fields in category sub-dict `{"basic_info": {"name": "xxx"}, "technical_features": {...}}`
+
+Field lookup order: Top level -> category mapping key -> Traverse all nested dicts
+
+**2. Category Multi-language Mapping**
+fields.yaml category names and JSON keys can be any combination (CN-CN, CN-EN, EN-CN, EN-EN). Must establish bidirectional mapping:
+```python
+CATEGORY_MAPPING = {
+    "Basic Info": ["basic_info", "Basic Info"],
+    "Technical Features": ["technical_features", "technical_characteristics", "Technical Features"],
+    "Performance Metrics": ["performance_metrics", "performance", "Performance Metrics"],
+    "Milestone Significance": ["milestone_significance", "milestones", "Milestone Significance"],
+    "Business Info": ["business_info", "commercial_info", "Business Info"],
+    "Competition & Ecosystem": ["competition_ecosystem", "competition", "Competition & Ecosystem"],
+    "History": ["history", "History"],
+    "Market Positioning": ["market_positioning", "market", "Market Positioning"],
+}
+```
+
+**3. Complex Value Formatting**
+- list of dicts (e.g., key_events, funding_history): Format each dict as one line, separate kv with ` | `
+- Normal list: Short lists joined with comma, long lists displayed with line breaks
+- Nested dict: Recursive formatting, display with semicolon or line breaks
+
+**4. Extra Fields Collection**
+Collect fields that exist in JSON but not defined in fields.yaml, put in "Other Info" category. Note to filter:
+- Internal fields: `_source_file`, `uncertain`
+- Nested structure top-level keys: `basic_info`, `technical_features` etc.
+
+**5. Uncertain Value Skipping**
+Skip conditions:
+- Field value contains `[uncertain]` string
+- Field name is in `uncertain` array
+- Field value is None or empty string
+
+### Step 3: Execute Script
+Run `python {topic}/generate_report.py`
+
+## Output
+- `{topic}/generate_report.py` - Conversion script
+- `{topic}/report.md` - Summary report
diff --git a/skills/research/validate_json.py b/skills/research/validate_json.py
new file mode 100644
index 0000000..9513d9d
--- /dev/null
+++ b/skills/research/validate_json.py
@@ -0,0 +1,219 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+JSON Field Validation Script
+Validate if JSON files completely cover all fields defined in fields.yaml
+"""
+
+import json
+import yaml
+import sys
+from pathlib import Path
+from typing import Dict, List, Set, Any, Tuple
+
+# Category mapping (supports both Chinese and English)
+CATEGORY_MAPPING = {
+    "Basic Info": ["basic_info", "Basic Info"],
+    "Technical Features": ["technical_features", "technical_characteristics", "Technical Features"],
+    "Performance Metrics": ["performance_metrics", "performance", "Performance Metrics"],
+    "Milestone Significance": ["milestone_significance", "milestones", "Milestone Significance"],
+    "Business Info": ["business_info", "commercial_info", "Business Info"],
+    "Competition & Ecosystem": ["competition_ecosystem", "competition", "Competition & Ecosystem"],
+    "History": ["history", "History"],
+    "Market Positioning": ["market_positioning", "market", "Market Positioning"],
+}
+
+
+def load_fields_yaml(fields_path: Path) -> Tuple[Set[str], Set[str], Dict[str, str]]:
+    """
+    Load fields.yaml, returns:
+    - all_fields: Set of all field names
+    - required_fields: Set of field names where required=true
+    - field_categories: Mapping from field name to category
+    """
+    with open(fields_path, 'r', encoding='utf-8') as f:
+        data = yaml.safe_load(f)
+
+    all_fields = set()
+    required_fields = set()
+    field_categories = {}
+
+    for category_info in data.get("field_categories", []):
+        category_name = category_info["category"]
+        for field in category_info.get("fields", []):
+            field_name = field["name"]
+            all_fields.add(field_name)
+            field_categories[field_name] = category_name
+            if field.get("required", False):
+                required_fields.add(field_name)
+
+    return all_fields, required_fields, field_categories
+
+
+def extract_json_fields(data: Dict, category_mapping: Dict = None) -> Set[str]:
+    """
+    Extract all field names from JSON (supports flat and nested structures)
+    """
+    if category_mapping is None:
+        category_mapping = CATEGORY_MAPPING
+
+    # Get all possible nested keys
+    nested_keys = set()
+    for keys in category_mapping.values():
+        nested_keys.update(keys)
+
+    fields = set()
+
+    def collect_fields(d: Dict, is_top_level: bool = True):
+        for k, v in d.items():
+            # Skip internal fields
+            if k in {"_source_file", "uncertain"}:
+                continue
+            # If it's a nested structure top-level key, recurse into it
+            if is_top_level and k in nested_keys:
+                if isinstance(v, dict):
+                    collect_fields(v, is_top_level=False)
+            else:
+                fields.add(k)
+                if isinstance(v, dict):
+                    collect_fields(v, is_top_level=False)
+
+    collect_fields(data)
+    return fields
+
+
+def validate_json(json_path: Path, all_fields: Set[str], required_fields: Set[str],
+                  field_categories: Dict[str, str]) -> Dict:
+    """
+    Validate a single JSON file
+    Returns validation result dictionary
+    """
+    with open(json_path, 'r', encoding='utf-8') as f:
+        data = json.load(f)
+
+    json_fields = extract_json_fields(data)
+
+    # Calculate coverage
+    covered = all_fields & json_fields
+    missing = all_fields - json_fields
+    extra = json_fields - all_fields
+
+    # Categorize missing fields
+    missing_required = missing & required_fields
+    missing_optional = missing - required_fields
+
+    # Group missing fields by category
+    missing_by_category = {}
+    for field in missing:
+        cat = field_categories.get(field, "Unknown")
+        if cat not in missing_by_category:
+            missing_by_category[cat] = []
+        missing_by_category[cat].append(field)
+
+    return {
+        "file": json_path.name,
+        "total_defined": len(all_fields),
+        "covered": len(covered),
+        "missing": len(missing),
+        "extra": len(extra),
+        "coverage_rate": len(covered) / len(all_fields) * 100 if all_fields else 100,
+        "missing_required": list(missing_required),
+        "missing_optional": list(missing_optional),
+        "missing_by_category": missing_by_category,
+        "extra_fields": list(extra),
+        "valid": len(missing_required) == 0,  # Valid if all required fields are covered
+    }
+
+
+def print_result(result: Dict, verbose: bool = True):
+    """Print validation result"""
+    status = "PASS" if result["valid"] else "FAIL"
+    print(f"\n{'='*60}")
+    print(f"[{status}] {result['file']}")
+    print(f"{'='*60}")
+    print(f"Coverage: {result['coverage_rate']:.1f}% ({result['covered']}/{result['total_defined']})")
+
+    if result["missing_required"]:
+        print(f"\n[ERROR] Missing required fields ({len(result['missing_required'])}):")
+        for field in result["missing_required"]:
+            print(f"  - {field}")
+
+    if verbose and result["missing_optional"]:
+        print(f"\n[WARN] Missing optional fields ({len(result['missing_optional'])}):")
+        for cat, fields in result["missing_by_category"].items():
+            optional_fields = [f for f in fields if f not in result["missing_required"]]
+            if optional_fields:
+                print(f"  [{cat}]: {', '.join(optional_fields)}")
+
+    if verbose and result["extra_fields"]:
+        print(f"\n[INFO] Extra fields ({len(result['extra_fields'])}):")
+        print(f"  {', '.join(result['extra_fields'][:10])}")
+        if len(result["extra_fields"]) > 10:
+            print(f"  ... and {len(result['extra_fields']) - 10} more fields")
+
+
+def main():
+    """Main function"""
+    import argparse
+    parser = argparse.ArgumentParser(description="Validate if JSON files cover all fields defined in fields.yaml")
+    parser.add_argument("--fields", "-f", type=str, help="Path to fields.yaml", default="fields.yaml")
+    parser.add_argument("--json", "-j", type=str, nargs="*", help="JSON file paths to validate")
+    parser.add_argument("--dir", "-d", type=str, help="JSON files directory", default="results")
+    parser.add_argument("--quiet", "-q", action="store_true", help="Show summary only")
+    args = parser.parse_args()
+
+    # Locate fields.yaml
+    fields_path = Path(args.fields)
+    if not fields_path.exists():
+        # Try to find in current and parent directory
+        for p in [Path.cwd() / "fields.yaml", Path.cwd().parent / "fields.yaml"]:
+            if p.exists():
+                fields_path = p
+                break
+
+    if not fields_path.exists():
+        print(f"[ERROR] fields.yaml not found: {fields_path}")
+        sys.exit(1)
+
+    print(f"Field definitions file: {fields_path}")
+    all_fields, required_fields, field_categories = load_fields_yaml(fields_path)
+    print(f"Total fields: {len(all_fields)} (required: {len(required_fields)}, optional: {len(all_fields) - len(required_fields)})")
+
+    # Collect JSON files
+    json_files = []
+    if args.json:
+        json_files = [Path(p) for p in args.json]
+    else:
+        json_dir = Path(args.dir)
+        if json_dir.exists():
+            json_files = sorted(json_dir.glob("*.json"))
+
+    if not json_files:
+        print(f"[WARN] No JSON files found")
+        sys.exit(0)
+
+    # Validate each file
+    results = []
+    for json_path in json_files:
+        if not json_path.exists():
+            print(f"[WARN] File not found: {json_path}")
+            continue
+        result = validate_json(json_path, all_fields, required_fields, field_categories)
+        results.append(result)
+        print_result(result, verbose=not args.quiet)
+
+    # Summary
+    print(f"\n{'='*60}")
+    print("Summary")
+    print(f"{'='*60}")
+    passed = sum(1 for r in results if r["valid"])
+    avg_coverage = sum(r["coverage_rate"] for r in results) / len(results) if results else 0
+    print(f"Validation passed: {passed}/{len(results)}")
+    print(f"Average coverage: {avg_coverage:.1f}%")
+
+    if passed < len(results):
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()