lark-sheets

lark-sheets Business Diagnosis Assistant

Quick Start

More Skills

Overview

The Business Diagnosis Assistant is used to answer "how should this be done," office collaboration, meeting minutes, and task breakdown. It is suitable for operations, product, technical, and sales to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as Lark Sheets data, pastable Lark Sheets, CSV, field descriptions, formula snippets, metric definitions, or exported text content... to organize key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables, making it easy to continue execution, review, or delivery.

When to Use

Applicable Scenarios

• The user raises questions like "how should this be done," needs to quickly break down goals, determine priorities, and form actionable results
• Operations, product, technical, and sales need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Business Diagnosis Assistant
• The user has already prepared the processing goal (for example, data health check, progress summary, metric explanation, anomaly investigation, list cleaning, or external sync.), report audience (explain who this spreadsheet brief is for, for example, project team, operations, finance, sales, management, data team, or client.), Lark Sheets link (fill in a Lark Sheets link that the user can publicly share; it serves only as a manual link clue and does not mean workspace data can be read.), and hopes to organize it into actionable analysis or optimization results
• The user needs to turn materials related to the Business Diagnosis Assistant into clear conclusions, priorities, and next-step actions

How to Invoke

Directly call the AI Skills API through the exported Python runner:

Command Example

Basic Invocation

python3 scripts/run.py --params '{}'

Invocation with Common Parameters

python3 scripts/run.py --params '{"goal":"处理目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	For example, data health check, progress summary, metric explanation, anomaly investigation, list cleaning, or external sync
audience	string	No	-	Explain who this spreadsheet brief is for, for example, project team, operations, finance, sales, management, data team, or client
materialUrl	string	No	-	Fill in a Lark Sheets link that the user can publicly share; it serves only as a manual link clue and does not mean workspace data can be read; a complete accessible URL must be provided
materialFile	string	No	-	Upload xlsx/csv/tsv/pdf files manually exported from Lark or other parseable spreadsheets
materialText	string	No	-	Pastable Lark Sheets, CSV, field descriptions, formula snippets, metric definitions, or exported text content
brandRequirements	string	No	-	Supplementary metric definitions, field naming, display format, confidentiality boundaries, columns that must be retained, and external narrative restrictions

See the complete machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

The current skill has no categorical parameters that require additional lookup.

Supported Input Formats

The current skill directly accepts JSON parameters; if the parameters contain link fields, please provide a complete, accessible URL.

Example request

The following example parameters can be passed directly to scripts/run.py, and the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"goal":"处理目标"}'

Equivalent --params JSON：

{
  "goal": "处理目标"
}

Example return result

{
  "success": true,
  "data": {
    "message": "示例结果请以技能真实返回结构为准。"
  },
  "meta": {
    "executionTime": 842,
    "cached": false
  }
}

Deliverables

• Summary, diagnostic conclusions, action recommendations, and reusable deliverables: organize the core results around the user's goals that can be directly read, reviewed, or delivered.
• Interpretation of input materials: combine the processing goal (for example, data health check, progress summary, metric explanation, anomaly troubleshooting, list cleaning, or external synchronization.), report audience (explain who this spreadsheet briefing is for, for example, project team, operations, finance, sales, management, data team, or client.), Feishu spreadsheet link (fill in a Feishu spreadsheet link that the user can publicly share; this is only a manual link clue and does not mean the workspace data can be read.) to extract key context and basis for judgment.
• Next steps: provide priorities, execution recommendations, or a content framework that can be further processed.

Suggestions for using the results

• First determine whether the output answers the user's core questions about the "Business Diagnostic Assistant".
• Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether they provide clear next steps.
• If there is little input material, it is recommended to ask the user to supplement the goals, audience, constraints, or raw materials before running.

Preparation before running

• AISKILLS_BASE_URL: default https://ai-skills.ai
• AISKILLS_API_KEY: required, used for authenticated calls
• AISKILLS_TENANT_ID: default default