Overview
The business diagnostic assistant is used to answer "how should this be done," PRD, SaaS, and product review. It is suitable for technical, managers, software, and PRD to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as PRD drafts, pasted requirement background, target users, user stories, feature scope, processes, and acceptance criteria to organize key context and output summaries, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, retrospective 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 executable results
- technical, managers, software, and PRD need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the business diagnostic assistant
- Users have already prepared PRD drafts (paste requirement background, target users, user stories, feature scope, processes, and acceptance criteria.), review priorities (select the direction that the SaaS PRD review assistant most needs to prioritize this time.), and uploaded PRD documents (upload PRDs, prototype descriptions, requirement pools, review records, or competitive product materials.), and want to organize them into executable analysis or optimization results
- Users need to turn business diagnostic assistant-related materials into clear conclusions, priorities, and next actions
How to invoke
Call the AI Skills API directly through the exported Python runner:
Command examples
Basic call
python3 scripts/run.py --params '{}'
Call with common parameters
python3 scripts/run.py --params '{"prdDraftText":"PRD草稿"}'
Parameter description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prdDraftText |
string | No | - | Paste requirement background, target users, user stories, feature scope, processes, and acceptance criteria |
prdReviewFocus |
string | No | 需求清晰度 |
Select the direction that the SaaS PRD review assistant most needs to prioritize this time; optional values:需求清晰度、边界范围、验收标准、风险依赖 |
prdDocumentFile |
string | No | - | Upload PRDs, prototype descriptions, requirement pools, review records, or competitive product materials |
prdReferenceLink |
string | No | - | Fill in publicly accessible links to prototypes, requirement documents, competitor pages, or help documents; a complete accessible URL is required |
userScenarioContext |
string | No | - | Describe target users, core scenarios, business metrics, launch cadence, and dependent teams |
metricConstraintNotes |
string | No | - | Supplement success metrics, out-of-scope items, technical constraints, compliance requirements, and pending decisions |
See the complete machine-readable parameter structure at references/form-schema.json。
Parameter value reference
Currently, this skill has no categorical parameters that require an additional lookup table.
Supported input formats
Currently, this skill directly accepts JSON parameters; if the parameters contain link fields, pass complete, accessible URLs.
Example request
The example parameters below can be passed directly to scripts/run.py; the runner will send them to the AI Skills API.
python3 scripts/run.py --params '{"prdDraftText":"PRD草稿"}'
Equivalent --params JSON:
{
"prdDraftText": "PRD草稿"
}
Return result example
{
"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 that can be directly read, reviewed, or delivered around the user's goals.
- Interpretation of input materials: combine the PRD draft (paste the requirement background, target users, user stories, feature scope, process, and acceptance criteria.), review focus (select the direction that this SaaS PRD review assistant most needs to prioritize.), and uploaded PRD documents (upload PRDs, prototype descriptions, requirement pools, review records, or competitor materials.) to extract key context and the 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 clear next steps are provided.
- If there is little input material, it is recommended to ask the user to supplement the goals, audience, constraints, or original materials before running.
Preparation before running
AISKILLS_BASE_URL: defaulthttps://ai-skills.aiAISKILLS_API_KEY: required, used for authenticated callsAISKILLS_TENANT_ID: defaultdefault