get-review-theme

Get Review Theme

Collaboration agreement with bensz-collect-bugs

• When a bug caused by a design flaw in this skill appears in the user's environment, prioritize using bensz-collect-bugs to record it according to the specification in ~/.bensz-skills/bugs/. It is strictly forbidden to directly modify the source code of the skill already installed in the user's local Claude Code / Codex.
• If the AI can still complete the user's task through a workaround, it should first record the bug, then continue completing the current task.
• When the user explicitly requests a public reporting action such as "report bensz skills bugs", call the local gh and bensz-collect-bugs, and only upload newly added bugs to huangwb8/bensz-bugs; do not pull / clone the entire bug repository.

Positioning

• Extract a structured review topic from files, images, webpages, folders, or natural language descriptions.
• The output directly serves systematic-literature-review or other literature review workflows.
• Highest principle: the topic must be actionable, the keywords must be searchable, and the core questions must be specific.

Input

Required:

• {输入源}: file path, URL, folder path, image path, or direct text description

Optional:

• {输出格式}：text / yaml / json, default text

Output

Always includes three items:

• 主题
• 关键词
• 核心问题

Format is chosen by the user:

• text
• yaml
• json

Workflow

1. Identify the input type

• Natural language description
• Image
• URL
• Text file
• PDF
• Word
• Folder

2. Extract content

• Natural language: use directly
• Image: rely on the LLM's native visual capabilities
• URL: prefer a webpage reading tool; if it fails, ask the user to provide the main text
• Text / PDF / Word: read directly
• Folder: recursively scan and merge .md/.txt/.pdf and other core materials

Principles:

• Prefer the host's native capabilities and existing standard tools
• Degrade gracefully when tools are unavailable, without introducing additional script dependencies

3. Semantic extraction

Produce output around the following tasks:

• Summarize the topic in one sentence
• Extract 5-10 standard English terms
• Extract 2-5 specific research questions or challenges

4. Formatting

• text: suitable for direct copying to a downstream skill
• yaml / json: suitable for structured connection

Quality requirements

• The topic must include the research object and the core question or method
• Keywords should preferably use standard search terms
• Core questions must be specific; avoid empty phrases like "of great significance / many challenges"

Error handling

• File does not exist: prompt the user to change the path or paste the content directly
• Unsupported format: prompt conversion
• Content extraction failed: ask the user to provide the text manually
• URL parsing failed: ask the user to copy the webpage main text or provide a PDF
• Image semantics unclear: ask the user to add a sentence of description

Relationship with downstream skills

• topic can be fed directly to systematic-literature-review
• keywords can supplement the search strategy
• core_questions Can serve as a review boundary and reference for inclusion/exclusion criteria