ai-content-research-writer

ai-content-research-writer Research Assistant

Overview

The Research Assistant is used to answer "What are the key points of this material?", content production, copy optimization, and publishing preparation. It is suitable for content creators, marketers, operations staff, and content media to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as topic, draft or reference materials, pasted topic, draft, channel requirements, reference materials, selling point information, or publishing goals to organize key context and output content diagnosis, optimization suggestions, and execution checklists for further execution, review, or delivery.

When to Use

Applicable Scenarios

When users ask questions such as "What are the key points of this material?" and need to quickly break down the goals, determine priorities, and form actionable results
When content creators, marketers, operations staff, and content media need to generate content diagnosis, optimization suggestions, and execution checklists around the Research Assistant
When users have already prepared content goals (explain the desired publishing goals, conversion goals, rewriting direction, or evaluation criteria.), target audience (explain the audience, roles, purchase stages, or usage scenarios the content is aimed at.), reference content links (fill in publicly accessible articles, pages, competitor content, or reference links; for restricted content, please upload or paste instead.), and want to organize them into actionable analysis or optimization results
When users need to turn materials related to the Research Assistant into clear conclusions, priorities, and next steps

How to Invoke

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

Command Examples

Basic Invocation

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

Invocation with Common Parameters

python3 scripts/run.py --params '{"goal":"内容目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	Explain the desired publishing goals, conversion goals, rewriting direction, or evaluation criteria
`audience`	string	No	-	Explain the audience, roles, purchase stages, or usage scenarios the content is aimed at
`materialUrl`	string	No	-	Fill in publicly accessible articles, pages, competitor content, or reference links; for restricted content, please upload or paste instead; a complete accessible URL is required
`materialFile`	string	No	-	Upload drafts, brand materials, channel requirements, reference materials, or content planning documents
`materialText`	string	No	-	Paste topic, draft, channel requirements, reference materials, selling point information, or publishing goals
`brandRequirements`	string	No	-	Supplement brand tone, channel rules, format requirements, immutable facts, compliance restrictions, or pre-publishing review priorities

For the complete machine-readable parameter structure, see references/form-schema.json。

Parameter Value Reference

This skill currently has no categorical parameters that require additional table lookup.

Supported Input Formats

This skill directly accepts JSON parameters; if the parameters contain link fields, please 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 '{"goal":"内容目标"}'

Equivalent --params JSON：

{
  "goal": "内容目标"
}

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

Content diagnosis, optimization suggestions, execution checklist: organize core results around the user's goals that can be directly read, reviewed, or delivered.
Input material interpretation: combine the content goal (state the desired publishing goal, conversion goal, rewriting direction, or evaluation criteria.), target audience (state the audience, role, purchase stage, or usage scenario the content is aimed at.), reference content links (fill in publicly accessible articles, pages, competitor content, or reference links; for restricted content, please upload or paste instead.) to extract key context and the basis for judgment.
Next steps: give 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 question about the "Material Organization Assistant".
Then check whether the results cover the content diagnosis, optimization suggestions, and execution checklist, and whether clear next steps are given.
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