mazdac/Szpitale-graph
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: translate all SKILL.md files to English

Browse Source 
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
jilinchen
2025-12-31 11:48:37 +08:00
co-authored by Claude Opus 4.5
parent 11a51a8d79
commit 92b47e006e
3 changed files with 216 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/research/SKILL.md
+92 -92
View File
@@ -1,143 +1,143 @@
---
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 research outline. 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 topic, use model's existing knowledge to generate:
- Main research objects/items list in this domain
- Suggested research field framework
输出{step1_output}，使用AskUserQuestion确认：
- items列表是否需要增减？
- 字段框架是否满足需求？
Output {step1_output}, use AskUserQuestion to confirm:
- Need to add/remove items?
- Does field framework meet requirements?
### Step 2: Web Search补充
使用AskUserQuestion询问时间范围（如：最近6个月、2024年至今、不限）。
### Step 2: Web Search Supplement
Use AskUserQuestion to ask for time range (e.g., last 6 months, since 2024, unlimited).
**参数获取**：
- `{topic}`: 用户输入的调研话题
- `{YYYY-MM-DD}`: 当前日期
- `{step1_output}`: Step 1生成的完整输出内容
- `{time_range}`: 用户指定的时间范围
**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
**硬约束**：以下prompt必须严格复述，仅替换{xxx}中的变量，禁止改写结构或措辞。
**Hard Constraint**: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.
启动1个web-search-agent（后台），**Prompt模板**：
Launch 1 web-search-agent (background), **Prompt Template**:
```python
prompt = f"""## 任务
调研话题: {topic}
当前日期: {YYYY-MM-DD}
prompt = f"""## Task
Research topic: {topic}
Current date: {YYYY-MM-DD}
基于以下初步框架，补充最新items和推荐调研字段。
Based on the following initial framework, supplement latest items and recommended research fields.
## 已有框架
## Existing Framework
{step1_output}
## 目标
1. 验证已有items是否遗漏重要对象
2. 根据遗漏对象进行补充items
3. 继续搜索{topic}相关且{time_range}内的items并补充
4. 补充新fields
## 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
## 输出要求
直接返回结构化结果（不写文件）：
## Output Requirements
Return structured results directly (do not write files):
### 补充Items
- item_name: 简要说明（为什么应该加入）
### Supplementary Items
- item_name: Brief explanation (why it should be added)
...
### 推荐补充字段
- field_name: 字段描述（为什么需要这个维度）
### Recommended Supplementary Fields
- field_name: Field description (why this dimension is needed)
...
### 信息来源
- [来源1](url1)
- [来源2](url2)
### Sources
- [Source1](url1)
- [Source2](url2)
"""
```
**One-shot示例**（假设调研AI Coding发展史）：
**One-shot Example** (assuming researching AI Coding History):
```
## 任务
调研话题: AI Coding 发展史
当前日期: 2025-12-30
## Task
Research topic: AI Coding History
Current date: 2025-12-30
基于以下初步框架，补充最新items和推荐调研字段。
Based on the following initial framework, supplement latest items and recommended research fields.
## 已有框架
### Items列表
1. GitHub Copilot: Microsoft/GitHub开发，首个主流AI编程助手
2. Cursor: AI-first IDE，基于VSCode
## Existing Framework
### Items List
1. GitHub Copilot: Developed by Microsoft/GitHub, first mainstream AI coding assistant
2. Cursor: AI-first IDE, based on VSCode
...
### 字段框架
- 基本信息: name, release_date, company
- 技术特性: underlying_model, context_window
### Field Framework
- Basic Info: name, release_date, company
- Technical Features: underlying_model, context_window
...
## 目标
1. 验证已有items是否遗漏重要对象
2. 根据遗漏对象进行补充items
3. 继续搜索AI Coding 发展史相关且2024年至今内的items并补充
4. 补充新fields
## 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
## 输出要求
直接返回结构化结果（不写文件）：
## Output Requirements
Return structured results directly (do not write files):
### 补充Items
- item_name: 简要说明（为什么应该加入）
### Supplementary Items
- item_name: Brief explanation (why it should be added)
...
### 推荐补充字段
- field_name: 字段描述（为什么需要这个维度）
### Recommended Supplementary Fields
- field_name: Field description (why this dimension is needed)
...
### 信息来源
- [来源1](url1)
- [来源2](url2)
### Sources
- [Source1](url1)
- [Source2](url2)
```
### 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 3: Ask User for Existing Fields
Use AskUserQuestion to ask if user has existing field definition file, if so read and merge.
### Step 4: 生成Outline（分离文件）
合并{step1_output}、{step2_output}和用户已有字段，生成两个文件：
### Step 4: Generate Outline (Separate Files)
Merge {step1_output}, {step2_output} and user's existing fields, generate two files:
**outline.yaml**（items + 配置）：
- topic: 调研主题
- items: 调研对象列表
**outline.yaml** (items + config):
- topic: Research topic
- items: Research objects list
- execution:
- batch_size: 并行agent数量（需AskUserQuestion确认）
- items_per_agent: 每个agent调研项目数（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
- detail_level分层：极简 → 简要 → 详细
- 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
- detail_level hierarchy: brief -> moderate -> detailed
- 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
skills/research/deep/SKILL.md
+64 -64
View File
@@ -1,98 +1,98 @@
---
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）
### 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)
**参数获取**：
- `{topic}`: outline.yaml中的topic字段
- `{item_name}`: item的name字段
- `{item_related_info}`: item的完整yaml内容（name + category + description等）
- `{output_dir}`: outline.yaml中execution.output_dir（默认./results）
- `{fields_path}`: {topic}/fields.yaml的绝对路径
- `{output_path}`: {output_dir}/{item_name}.json的绝对路径
**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
**硬约束**：以下prompt必须严格复述，仅替换{xxx}中的变量，禁止改写结构或措辞。
**Hard Constraint**: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.
**Prompt模板**：
**Prompt Template**:
```python
prompt = f"""## 任务
调研 {item_related_info}，输出结构化JSON到 {output_path}
prompt = f"""## Task
Research {item_related_info}, output structured JSON to {output_path}
## 字段定义
读取 {fields_path} 获取所有字段定义
## Field Definitions
Read {fields_path} to get all field definitions
## 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
4. 所有字段值必须使用中文输出（调研过程可用英文，但最终JSON值为中文）
## 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
4. All field values must be in Chinese (research can be in English, but final JSON values in Chinese)
## 输出路径
## Output Path
{output_path}
## 验证
完成JSON输出后，运行验证脚本确保字段完整覆盖：
## 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}
验证通过后才算完成任务。
Task is complete only after validation passes.
"""
```
**One-shot示例**（假设调研GitHub Copilot）：
**One-shot Example** (assuming researching GitHub Copilot):
```
## 任务
调研 name: GitHub Copilot
category: 国际产品
description: Microsoft/GitHub开发，首个主流AI编程助手，市场份额约40%，输出结构化JSON到 /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json
## 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
## 字段定义
读取 /home/weizhena/AIcoding/aicoding-history/fields.yaml 获取所有字段定义
## Field Definitions
Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field definitions
## 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
4. 所有字段值必须使用中文输出（调研过程可用英文，但最终JSON值为中文）
## 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
4. All field values must be in Chinese (research can be in English, but final JSON values in Chinese)
## 输出路径
## Output Path
/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json
## 验证
完成JSON输出后，运行验证脚本确保字段完整覆盖：
## 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
验证通过后才算完成任务。
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
### Step 4: Wait and Monitor
- Wait for current batch to complete
- Launch next batch
- Display progress
### 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
### Step 5: Summary Report
After all complete, output:
- Completion count
- Failed/uncertain marked items
- Output directory
## 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
## Agent Config
- Background execution: Yes
- Task Output: Disabled (agent has explicit output file when complete)
- Resume support: Yes
skills/research/report/SKILL.md
+60 -60
View File
@@ -1,20 +1,20 @@
---
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: 扫描可选摘要字段
读取所有JSON结果，提取适合在目录中显示的字段（数值型、简短指标），例如：
### Step 2: Scan Optional Summary Fields
Read all JSON results, extract fields suitable for TOC display (numeric, short metrics), e.g.:
- github_stars
- google_scholar_cites
- swe_bench_score
@@ -22,70 +22,70 @@ allowed-tools: Read, Write, Glob, Bash
- valuation
- release_date
使用AskUserQuestion询问用户：
- 目录中除了item名称外，还需要显示哪些字段？
- 提供动态选项列表（基于实际JSON中存在的字段）
Use AskUserQuestion to ask user:
- Which fields to display in TOC besides item name?
- Provide dynamic options list (based on actual fields in JSON)
### Step 3: 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数组中列出的字段
- 生成markdown报告格式：目录（带锚点跳转+用户选择的摘要字段）+ 详细内容（按字段分类）
- 保存到 `{topic}/report.md`
### Step 3: 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 + user-selected summary fields) + Detailed content (by field category)
- Save to `{topic}/report.md`
**目录格式要求**：
- 必须包含每一个item
- 每个item显示：序号、名称（锚点链接）、用户选择的摘要字段
- 示例：`1. [GitHub Copilot](#github-copilot) - Stars: 10k | Score: 85%`
**TOC Format Requirements**:
- Must include every item
- Each item displays: number, name (anchor link), user-selected summary fields
- Example: `1. [GitHub Copilot](#github-copilot) - Stars: 10k | Score: 85%`
#### 脚本技术要点（必须遵循）
#### Script Technical Requirements (Must Follow)
**1. JSON结构兼容**
支持两种JSON结构：
- 扁平结构：字段直接在顶层 `{"name": "xxx", "release_date": "xxx"}`
- 嵌套结构：字段在category子dict中 `{"basic_info": {"name": "xxx"}, "technical_features": {...}}`
**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": {...}}`
字段查找顺序：顶层 -> category映射key -> 遍历所有嵌套dict
Field lookup order: Top level -> category mapping key -> Traverse all nested dicts
**2. Category多语言映射**
fields.yaml的category名与JSON的key可能是任意组合（中中、中英、英中、英英）。必须建立双向映射：
**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 = {
"基本信息": ["basic_info", "基本信息"],
"技术特性": ["technical_features", "technical_characteristics", "技术特性"],
"性能指标": ["performance_metrics", "performance", "性能指标"],
"里程碑意义": ["milestone_significance", "milestones", "里程碑意义"],
"商业信息": ["business_info", "commercial_info", "商业信息"],
"竞争与生态": ["competition_ecosystem", "competition", "竞争与生态"],
"历史沿革": ["history", "历史沿革"],
"市场定位": ["market_positioning", "market", "市场定位"],
"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. 复杂值格式化**
- list of dicts（如key_events, funding_history）：每个dict格式化为一行，用` | `分隔kv
- 普通list：短列表用逗号连接，长列表换行显示
- 嵌套dict：递归格式化，用分号或换行显示
- 长文本字符串（超过100字符）：添加换行符`<br>`或使用blockquote格式，提高可读性
**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
- Long text strings (over 100 chars): Add line breaks `<br>` or use blockquote format for readability
**4. 额外字段收集**
收集JSON中有但fields.yaml中没定义的字段，放入"其他信息"分类。注意过滤：
- 内部字段：`_source_file`, `uncertain`
- 嵌套结构顶级key：`basic_info`, `technical_features`等
- `uncertain_fields`列表：需要逐行显示每个字段名，不要压缩成一行
**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.
- `uncertain_fields` list: Display each field name on separate line, don't compress into one line
**5. 不确定值跳过**
跳过条件：
- 字段值包含`[不确定]`字符串
- 字段名在`uncertain`数组中
- 字段值为None或空字符串
**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 4: 执行脚本
运行 `python {topic}/generate_report.py`
### Step 4: Execute Script
Run `python {topic}/generate_report.py`
## 输出
- `{topic}/generate_report.py` - 转换脚本
- `{topic}/report.md` - 汇总报告
## Output
- `{topic}/generate_report.py` - Conversion script
- `{topic}/report.md` - Summary report