lark-approval

lark-approval Business Diagnostic Assistant

Quick Start

More Skills

Overview

The Business Diagnostic 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 Lark approval records, pasted approval titles, form fields, approval reasons, amounts, applicants, approval comments, routing records… and other inputs, organizes key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables for further execution, review, or delivery.

When to Use

Applicable Scenarios

• Users raise questions like "how should this be done," needing 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 Diagnostic Assistant
• Users have already prepared approval review goals (for example, checking material completeness, identifying approval risks, preparing supplementary explanations, or forming review opinions.), review targets (for example, applicant, direct supervisor, finance, legal, procurement, HR, or manager.), and approval link descriptions (fill in the Lark approval or process description link, and add a summary of visible content; the system will not automatically open links.), and hope to organize them into actionable analysis or optimization results
• Users need to convert Business Diagnostic Assistant-related materials into clear conclusions, priorities, and next-step actions

How to Invoke

Call the AI Skills API directly through the exported Python runner:

Command Example

Basic Call

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

Call with Common Parameters

python3 scripts/run.py --params '{"goal":"审批审阅目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	For example, checking material completeness, identifying approval risks, preparing supplementary explanations, or forming review opinions
audience	string	No	-	For example, applicant, direct supervisor, finance, legal, procurement, HR, or manager
materialUrl	string	No	-	Fill in the Lark approval or process description link, and add a summary of visible content; the system will not automatically open links; a complete accessible URL must be provided
reviewDepth	string	No	标准诊断	Choose quick self-check, standard review, or deep risk re-review; optional values:快速体检、标准诊断、深度改稿
materialFile	string	No	-	Upload approval screenshot OCR text, approval export, attachment summary, policy documents, or supplementary explanations
materialText	string	No	-	Paste approval titles, form fields, approval reasons, amounts, applicants, approval comments, routing records, or policy clauses
targetPlatform	string	No	-	Specify whether it is used for pre-submission self-check of Lark approvals, supervisor review, finance review, legal review, or process retrospective
brandRequirements	string	No	-	Supplement enterprise policy standards, approval templates, compliance requirements, confidentiality requirements, or internal wording standards

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 a link field, please pass a complete, accessible URL.

Example request

The example parameters below 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":"审批审阅目标"}'

Equivalent --params JSON：

{
  "goal": "审批审阅目标"
}

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: combined with the approval review goals (for example, checking material completeness, identifying approval risks, preparing supplementary explanations, or forming review opinions.), the review targets (for example, the applicant, direct supervisor, finance, legal, procurement, HR, or managers.), and the approval link description (fill in the Feishu approval or process description link, and add a summary of the visible content; the system will not automatically open the link.) to extract key context and bases 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 question about the "Business Diagnostic Assistant".
• Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are provided.
• If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or original 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