Overview
The risk review assistant is used to answer "what risks are here," API documentation, integration, and developer experience. It is suitable for technical, managers, software, and API documentation after clarifying business goals, content materials, or analysis objects. It will combine interface documentation content, pasted interface descriptions, authentication methods, request and response fields, error codes, and call limits. and other inputs, organize key context, and output summaries, diagnostic conclusions, action recommendations, and reusable deliverables, making it easy to continue execution, review, or delivery.
When to Use
Applicable Scenarios
- Users ask questions such as "what risks are here," and need to quickly break down goals, determine priorities, and form executable results
- technical, managers, software, and API documentation need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the risk review assistant
- Users have already prepared uploaded interface materials (uploaded interface documentation, field tables, integration records, error code tables, or change descriptions.), interface documentation links (fill in publicly accessible API documentation, SDK documentation, or developer guide links.), interface documentation content (paste interface descriptions, authentication methods, request and response fields, error codes, and call limits.), and hope to organize them into executable analysis or optimization results
- Users need to turn risk review assistant-related materials into clear conclusions, priorities, and next-step actions
How to Call
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 '{"apiGuideFile":"上传接口资料"}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
apiGuideFile |
string | No | - | Upload interface documentation, field tables, integration records, error code tables, or change descriptions |
apiGuideLink |
string | No | - | Fill in publicly accessible API documentation, SDK documentation, or developer guide links; a complete accessible URL must be provided |
apiGuideText |
string | No | - | Paste interface descriptions, authentication methods, request and response fields, error codes, and call limits |
integrationRiskFocus |
string | No | 字段完整性 |
Select the direction that needs the highest priority in this API documentation integration risk review; optional values:字段完整性、错误处理、鉴权限流、联调风险 |
dependencyConstraintNotes |
string | No | - | Supplement authentication methods, rate limiting, callbacks, idempotency, compatibility, and fields to be confirmed |
integrationScenarioContext |
string | No | - | Explain the integrator, business process, call frequency, environment, dependent systems, and launch time |
See the complete machine-readable parameter structure at references/form-schema.json。
Parameter Value Reference
This skill currently has no categorical parameters that require additional lookup.
Supported Input Formats
This skill currently accepts JSON parameters directly; if the parameters contain link fields, please provide 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 '{"apiGuideFile":"上传接口资料"}'
Equivalent --params JSON:
{
"apiGuideFile": "上传接口资料"
}
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 uploaded interface materials (uploaded interface documentation, field tables, integration records, error code tables, or change notes.), interface documentation links (enter publicly accessible API documentation, SDK documentation, or developer guide links.), and interface documentation content (paste interface descriptions, authentication methods, request and response fields, error codes, and call limits.) 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 question about the "Risk Review 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: defaulthttps://ai-skills.aiAISKILLS_API_KEY: required, used for authenticated callsAISKILLS_TENANT_ID: defaultdefault