feat: support direct slash command trigger (Claude Code 2.1.0+)

- Add user-invocable: true to all SKILL.md files (10 files)
- Update README with new command format (/research:deep)
- Keep backward compatibility notes for older versions

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

README.md

@@ -31,15 +31,17 @@ pip install pyyaml
 
 ## Commands
 
-> **Note**: Use `run /research` instead of `/research` directly, as slash commands conflict with built-in commands.
+> **Claude Code 2.1.0+**: Direct `/research` trigger is now supported!
+>
+> **Older versions**: Use `run /research` format instead.
 
-| Command | Description |
+| Command (2.1.0+) | Command (older) | Description |
-|---------|-------------|
+|------------------|-----------------|-------------|
-| `run /research` | Generate research outline with items and fields |
+| `/research` | `run /research` | Generate research outline with items and fields |
-| `run /research/add-items` | Add more items to existing outline |
+| `/research:add-items` | `run /research/add-items` | Add more items to existing outline |
-| `run /research/add-fields` | Add more fields to existing outline |
+| `/research:add-fields` | `run /research/add-fields` | Add more fields to existing outline |
-| `run /research/deep` | Deep research each item with parallel agents |
+| `/research:deep` | `run /research/deep` | Deep research each item with parallel agents |
-| `run /research/report` | Generate markdown report from JSON results |
+| `/research:report` | `run /research/report` | Generate markdown report from JSON results |
 
 ## Workflow & Example
 
@@ -47,24 +49,27 @@ pip install pyyaml
 
 ### Phase 1: Generate Outline
 ```
-run /research AI Agent Demo 2025
+/research AI Agent Demo 2025
 ```
+> *Older versions: `run /research AI Agent Demo 2025`*
 💡 **What happens**: Tell it your topic → It creates a research list for you
 
 **You get**: A list of 17 AI Agents to research (ChatGPT Agent, Claude Computer Use, Cursor, etc.) + what info to collect for each
 
 ### Phase 2: Deep Research
 ```
-run /research/deep
+/research:deep
 ```
+> *Older versions: `run /research/deep`*
 💡 **What happens**: AI automatically searches the web for each item, one by one
 
 **You get**: Detailed info for each Agent (company, release date, pricing, tech specs, reviews...)
 
 ### Phase 3: Generate Report
 ```
-run /research/report
+/research:report
 ```
+> *Older versions: `run /research/report`*
 💡 **What happens**: All data → One organized report
 
 **You get**: `report.md` - A complete markdown report with table of contents, ready to read or share

README.zh.md

@@ -31,15 +31,17 @@ pip install pyyaml
 
 ## 命令
 
-> **注意**：使用 `run /research` 而非直接 `/research`，因为斜杠命令与内置命令冲突。
+> **Claude Code 2.1.0+**：现已支持直接 `/research` 触发！
+>
+> **旧版本**：请使用 `run /research` 格式。
 
-| 命令 | 描述 |
+| 命令 (2.1.0+) | 命令 (旧版本) | 描述 |
-|------|------|
+|---------------|---------------|------|
-| `run /research` | 生成包含items和fields的调研outline |
+| `/research` | `run /research` | 生成包含items和fields的调研outline |
-| `run /research/add-items` | 向现有outline添加更多items |
+| `/research:add-items` | `run /research/add-items` | 向现有outline添加更多items |
-| `run /research/add-fields` | 向现有outline添加更多fields |
+| `/research:add-fields` | `run /research/add-fields` | 向现有outline添加更多fields |
-| `run /research/deep` | 使用并行agents对每个item进行深度调研 |
+| `/research:deep` | `run /research/deep` | 使用并行agents对每个item进行深度调研 |
-| `run /research/report` | 从JSON结果生成markdown报告 |
+| `/research:report` | `run /research/report` | 从JSON结果生成markdown报告 |
 
 ## 工作流 & 示例
 
@@ -47,24 +49,27 @@ pip install pyyaml
 
 ### 阶段1：生成Outline
 ```
-run /research AI Agent Demo 2025
+/research AI Agent Demo 2025
 ```
+> *旧版本: `run /research AI Agent Demo 2025`*
 💡 **发生了什么**：告诉它你要研究什么 → 它帮你列出调研清单
 
 **你会得到**：17个待调研的AI Agent清单（ChatGPT Agent、Claude Computer Use、Cursor等）+ 每个要收集哪些信息
 
 ### 阶段2：深度调研
 ```
-run /research/deep
+/research:deep
 ```
+> *旧版本: `run /research/deep`*
 💡 **发生了什么**：AI自动上网搜索每个item的详细信息，逐个完成
 
 **你会得到**：每个Agent的详细资料（公司、发布日期、定价、技术规格、用户评价...）
 
 ### 阶段3：生成报告
 ```
-run /research/report
+/research:report
 ```
+> *旧版本: `run /research/report`*
 💡 **发生了什么**：所有数据 → 一份整理好的报告
 
 **你会得到**：`report.md` - 带目录的完整Markdown报告，可直接阅读或分享

skills/research-en/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 allowed-tools: Read, Write, Glob, WebSearch, Task, AskUserQuestion
 description: Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
 ---

skills/research-en/add-fields/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 description: Add field definitions to existing research outline.
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion
 ---

skills/research-en/add-items/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 description: Add items (research objects) to existing research outline.
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion
 ---

skills/research-en/deep/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 description: Read research outline, launch independent agent for each item for deep research. Disable task output.
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task
 ---

skills/research-en/report/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 description: Summarize deep research results into markdown report, cover all fields, skip uncertain values.
 allowed-tools: Read, Write, Glob, Bash, AskUserQuestion
 ---

skills/research-zh/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 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。
 ---

skills/research-zh/add-fields/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 description: 向现有调研outline补充字段定义。
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion
 ---

skills/research-zh/add-items/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 description: 向现有调研outline补充items（调研对象）。
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task, AskUserQuestion
 ---

skills/research-zh/deep/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 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。
 allowed-tools: Bash, Read, Write, Glob, WebSearch, Task
 ---

skills/research-zh/report/SKILL.md

@@ -1,4 +1,5 @@
 ---
+user-invocable: true
 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。
 allowed-tools: Read, Write, Glob, Bash, AskUserQuestion
 ---