ai-research-refine

ai-research-refine Research Refinement Assistant

Overview

The Research Refinement Assistant is used to answer "Is the research question clear?", conduct research analysis, source verification, and evidence summarization. It is suitable for marketing, operations, software, and education and training to call after clarifying business goals, content materials, or analysis objects. It combines inputs such as research questions or material excerpts, questions to be verified, candidate sources, webpage excerpts, literature leads, or comparative viewpoints, organizes the key context, and outputs research summaries, comparative insights, and decision recommendations for continued execution, review, or delivery.

When to Use

Applicable Scenarios

When users ask questions such as "Is the research question clear?" and need to quickly break down goals, determine priorities, and form executable results
When marketing, operations, software, and education and training need to generate research summaries, comparative insights, and decision recommendations around the Research Refinement Assistant
When users have already prepared research goals (explain the questions to be answered, comparison dimensions, judgment criteria, or delivery purpose.), research audience (explain the readers, roles, markets, courses, or usage scenarios that the research conclusions should serve.), public webpage links (provide publicly accessible webpages, reports, or material links; for restricted content, upload files or paste excerpts instead.), and want to organize them into executable analysis or optimization results
When users need to turn materials related to the Research Refinement Assistant into clear conclusions, priorities, and next 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 '{"goal":"研究目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	Explain the questions to be answered, comparison dimensions, judgment criteria, or delivery purpose
`audience`	string	No	-	Explain the readers, roles, markets, courses, or usage scenarios that the research conclusions should serve
`materialUrl`	string	No	-	Provide publicly accessible webpages, reports, or material links; for restricted content, upload files or paste excerpts instead; must pass an accessible complete URL
`materialFile`	string	No	-	Upload research materials, webpage excerpts, literature notes, tables, or reports, suitable when the materials are long or the original text needs to be preserved
`materialText`	string	No	-	Paste questions to be verified, candidate sources, webpage excerpts, literature leads, or comparative viewpoints
`brandRequirements`	string	No	-	Supplement source scope, time range, credibility requirements, sources that cannot be used, conclusion risks, or key points for manual review

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 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, the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"goal":"研究目标"}'

Equivalent --params JSON：

{
  "goal": "研究目标"
}

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

Research summary, comparative insights, decision recommendations: organize core results around user goals that can be directly read, reviewed, or delivered.
Interpretation of input materials: combine the research goal (explain the questions to be answered, comparison dimensions, judgment criteria, or delivery purpose.), research audience (explain the readers, roles, markets, courses, or use scenarios the research conclusions are intended to serve.), public web links (provide publicly accessible webpages, reports, or material links; for restricted content, upload files or paste excerpts instead.) to extract key context and basis for judgment.
Next steps: provide priorities, execution suggestions, 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 "Research Refinement Assistant".
Then check whether the results cover the research summary, comparative insights, and decision recommendations, 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 source 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