技能文件类型电子表格
- 作者仓库星标 435
- 作者仓库 nvim
- 领域
- 数据
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @benbrastmckie · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- 未检出明确要求
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 命令执行
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
# Spreadsheet Skill
Thin wrapper that routes spreadsheet-to-table operations to the `filetypes-spreadsheet-agent`.
## Context Pointers
Reference (do not load eagerly):
- Path: `.claude/context/formats/subagent-return.md`
- Purpose: Return validation
- Load at: Subagent execution only
Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.
## Trigger Conditions
This skill activates when:
### Direct Invocation
- User explicitly runs `/table` command
- User requests spreadsheet to table conversion in conversation
### Implicit Invocation (during task implementation)
When an implementing agent encounters any of these patterns:
**Plan step language patterns**:
- "Convert spreadsheet to table"
- "Create LaTeX table from Excel"
- "Import data from XLSX"
- "Generate Typst table from CSV"
- "Extract table data from spreadsheet"
**File extension detection**:
- Source file has extension: `.xlsx`, `.xls`, `.csv`, `.ods`
- Target mentions: "LaTeX table", ".tex", "Typst table", ".typ"
**Task description keywords**:
- "spreadsheet conversion"
- "Excel to table"
- "data table"
- "tabular data"
### When NOT to trigger
Do not invoke for:
- Document conversions (use skill-filetypes)
- Presentation conversions (use skill-presentation)
- Reading spreadsheets without table generation
- Spreadsheets already in LaTeX/Typst format
---
## Execution
### 1. Input Validation
Validate required inputs:
- `source_path` - Must be provided and file must exist
- `output_path` - Optional, defaults to source dir with .tex extension
- `output_format` - Optional, defaults to "latex"
```bash
# Validate source exists
if [ ! -f "$source_path" ]; then
return error "Source file not found: $source_path"
fi
# Validate source is spreadsheet format
source_ext="${source_path##*.}"
case "$source_ext" in
xlsx|xls|csv|ods) ;; # Valid
*) return error "Not a spreadsheet format: .$source_ext" ;;
esac
# Determine output path if not provided
if [ -z "$output_path" ]; then
source_dir=$(dirname "$source_path")
source_base=$(basename "$source_path" | sed 's/\.[^.]*$//')
case "$output_format" in
latex|tex) output_path="${source_dir}/${source_base}.tex" ;;
typst|typ) output_path="${source_dir}/${source_base}.typ" ;;
*) output_path="${source_dir}/${source_base}.tex" ;;
esac
fi
```
### 2. Context Preparation
Prepare delegation context:
```json
{
"source_path": "/absolute/path/to/data.xlsx",
"output_path": "/absolute/path/to/data.tex",
"output_format": "latex",
"sheet_name": null,
"metadata": {
"session_id": "sess_{timestamp}_{random}",
"delegation_depth": 1,
"delegation_path": ["orchestrator", "table", "skill-filetypes-spreadsheet"]
}
}
```
### 3. Invoke Agent
**CRITICAL**: You MUST use the **Agent** tool to spawn the agent.
**Required Tool Invocation**:
```
Tool: Agent (NOT Skill, NOT Plan)
Parameters:
- subagent_type: "filetypes-spreadsheet-agent"
- prompt: [Include source_path, output_path, output_format, sheet_name, metadata]
- description: "Convert {source_path} to {output_format} table"
```
The agent will:
- Detect available tools (pandas, openpyxl, xlsx2csv)
- Read spreadsheet data
- Generate formatted table output
- Return standardized JSON result
### 4. Return Validation
Validate return matches `subagent-return.md` schema:
- Status is one of: converted, partial, failed
- Summary is non-empty and <100 tokens
- Artifacts array present with output file path
- Metadata contains row/column counts
### 5. Return Propagation
Return validated result to caller without modification.
---
## Return Format
Expected successful return:
```json
{
"status": "converted",
"summary": "Successfully converted data.xlsx to LaTeX table using pandas",
"artifacts": [
{
"type": "implementation",
"path": "/absolute/path/to/data.tex",
"summary": "LaTeX table with 5 columns, 100 rows"
}
],
"metadata": {
"session_id": "sess_...",
"agent_type": "filetypes-spreadsheet-agent",
"delegation_depth": 2,
"tool_used": "pandas+openpyxl",
"rows": 100,
"columns": 5
},
"next_steps": "Include table in document"
}
```
---
## Error Handling
### Input Validation Errors
Return immediately with failed status if source file not found or not a spreadsheet.
### Unsupported Format
Return failed status with clear message about supported formats.
### Agent Errors
Pass through the agent's error return verbatim.
### Tool Not Available
Return failed status with installation instructions.
章节与文件索引
按说明文件中的顺序排列。
上下文指针
直接调用
隐式调用(任务执行期间)
何时不触发
1. 输入验证
文件/命令 -> filetypes-spreadsheet-agent · .claude/context/formats/subagent-return.md · /table · .xlsx · .xls · .csv · .ods · source_path
内容校验值 -> 45d92eb86875
当前原文的自动摘译,尚未人工审校。
上下文指针
参考(不要急于加载): 路径:
.claude/context/formats/subagent-return.md目的:返回验证 加载于:仅子代理执行 注意:此技能是一个薄包装。上下文由委托代理加载,而不是由该技能加载。直接调用
用户显式运行
/table命令 用户在对话中请求电子表格到表格的转换隐式调用(任务执行期间)
当实施代理遇到以下任何模式时: 规划步骤语言模式:“将电子表格转换为表格”“从 Excel 创建 LaTeX 表”“从 XLSX 导入数据”
何时不触发
请勿调用: 文档转换(使用技能文件类型) 演示文稿转换(使用技能演示文稿) 读取电子表格而不生成表格 已采用 LaTeX/Typst 格式的电子表格
1. 输入验证
验证所需的输入:
source_path- 必须提供且文件必须存在output_path- 可选,默认为扩展名为 .tex 的源目录output_format- 可选,默认为“latex”