text-to-excel
Skill302 starsChanged 7 months agoMITView on GitHub
将结构化文本内容生成为Excel表格(.xlsx)的工具。支持解析用户提供的各种结构化文本(表格、列表、键值对、CSV、Markdown表格、JSON等),自动识别表头和数据行,生成格式规整的Excel文件。支持多sheet、合并单元格、样式设置、冻结窗格、自动筛选、条件格式、数据验证、图表生成等全部功能。当用户提到以下场景时触发:(1) 需要将文本/数据/内容转换为Excel/表格/xlsx文件 (2) 需要生成Excel表格 (3) 需要创建电子表格 (4) 提供了结构化数据并要求输出为Excel (5) 要求整理数据到表格中 (6) 需要把信息做成表格导出。关键词:Excel、表格、xlsx、电子表格、导出表格、生成表格、做成表格、转成表格、整理成表格。
In this repository35 other files it gives its agents.
- analytic-memoSkill
- argument-auditorSkill
- cjournal-analyzerSkill
- cnki-advanced-searchSkill
- concept-clarifierSkill
- conceptual-framework-builderSkill
- counterfactual-reasoningSkill
- design-coherence-checkSkill
- feishu-paper-reviewerSkill
- foreign-literature-searchSkill
- grounded-codingSkill
- introduction-writerSkill
- literature-review-writerSkill
- literature-verifierSkill
- memo-coachSkill
- negative-case-finderSkill
- paper-analyzerSkill
- paper-formatterSkill
- paper-reviewerSkill
- paper-title-abstract-keywordsSkill
- pdf-bib-importSkill
- phd-literature-reviewSkill
- problematizationSkill
- skill-installerSkill
- strategy-makerSkill
- ta-discussion-writerSkill
- ta-findings-writerSkill
- ta-framework-builderSkill
- ta-framework-writerSkill
- ta-methods-writerSkill
- ta-research-AFP-autoSkill
- ta-research-AFPSkill
- thematic-analysisSkill
- theory-fit-assessmentSkill
- top-journals-methods-scoutSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
Ask the user for the save path.
- Distinctive: line 80
Write the JSON config to a temp file
- Distinctive: line 82
Verify the file was created
- Very specific: line 97
Multi-sheet: Add multiple objects to the sheets array
- Very specific: line 98
Merge cells: Use merge_cells with range strings or row/col objects
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Text-to-Excel
将结构化文本转换为格式规整的Excel文件。
Workflow
Step 1: Parse User Input
Analyze user-provided structured text. Supported input formats:
- Markdown tables (
| col1 | col2 |) - Plaintext tables (tab/space-separated)
- CSV/TSV data
- Lists (bulleted, numbered)
- Key-value pairs
- JSON/dict-like structures
- Free-form text with identifiable tabular structure
- Descriptions of desired table content
Identify: headers, data rows, data types per column, and any special formatting requests.
Step 2: Ask for Output Path
Ask the user for the save path. Suggest a reasonable default filename based on the content (e.g. ~/Desktop/sales_data.xlsx).
Step 3: Build JSON Config
Construct a JSON config object following the schema in references/config_schema.md.
Minimal example:
{
"sheets": [{
"name": "Sheet1",
"headers": ["Name", "Age", "City"],
"data": [
["Alice", 30, "Beijing"],
["Bob", 25, "Shanghai"]
]
}]
}Full-featured example with styles, charts, and validation:
{
"sheets": [{
"name": "Sales",
"title_row": {"text": "Q1 Sales Report", "style": {"font": {"bold": true, "size": 16}}},
"headers": ["Month", "Revenue", "Growth"],
"data": [
["January", 50000, 0.12],
["February", 62000, 0.24],
["March", 58000, 0.16]
],
"column_types": ["text", "currency_cny", "percent"],
"freeze_pane": "A2",
"auto_filter": true,
"charts": [{
"type": "bar",
"title": "Monthly Revenue",
"x_column": 1,
"y_columns": [2],
"position": "E2"
}],
"conditional_formats": [{
"type": "color_scale",
"range": "B2:B4"
}]
}]
}Step 4: Generate Excel
- Write the JSON config to a temp file
- Run:
python3 scripts/generate_excel.py <config.json> <output_path> - Verify the file was created
- Report success with the file path
Style Defaults
The script applies professional defaults automatically:
- Headers: Blue background (#4472C4), white bold text, centered
- Data rows: Alternating gray/white bands, thin borders
- Column widths: Auto-calculated based on content length
- Title row (optional): Large bold text, merged across all columns
Override any default by specifying header_style, data_style, or per-cell styles in the config.
Advanced Features
- Multi-sheet: Add multiple objects to the
sheetsarray - Merge cells: Use
merge_cellswith range strings or row/col objects - Freeze pane: Set
freeze_paneto e.g."A2"to freeze header row - Auto-filter: Set
auto_filter: trueto enable dropdown filters - Charts: Bar, line, pie, area, scatter charts — see references/config_schema.md
- Data validation: Dropdown lists, numeric ranges, date ranges, text length limits
- Conditional formatting: Cell-based rules, color scales, data bars
- Number formats: Predefined (
percent,currency_cny,currency_usd,date) or custom Excel format strings - Print settings: Orientation, paper size, fit-to-page
See full schema: references/config_schema.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

