research-topic-extractor

Research Topic Extractor

• Extract a structured review topic from files, images, webpages, folders, or natural language descriptions.
• Output directly serves research-literature-review or other literature review workflows.
• Compatible with prompt triggering of the legacy name get-review-theme ; system-level legacy directories are cleaned up by the installer.
• 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

Process

Input

Provide the necessary input according to the user request and configuration file; missing information should be clearly listed and steps depending on that input should be stopped.

Execution Steps

• 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 skills 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 public reporting actions 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.

Identify Input Type

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

Extract Content

• Natural language: use directly
• Image: rely on the LLM's native visual capabilities
• URL: prefer a webpage reading tool; if that 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

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

Formatting

• text: suitable for direct copying to downstream skills

• yaml / json: suitable for structured connection

• topic can be fed directly to research-literature-review

• keywords can supplement the search strategy

• core_questions can serve as reference for review boundaries and inclusion/exclusion

Output

Always include three items:

• 主题
• 关键词
• 核心问题

Format is chosen by the user:

• text
• yaml
• json

Output Management

Intermediate files for new tasks of this Skill are uniformly written to ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/{skill名}/input|output|log/. The same task reuses one task root directory; only multi-Skill collaboration creates shared/. Formal deliverables are not written to this directory; historical hidden directories only allow explicit compatible reading, migration, or cleanup.

Validation

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

Failure and recovery

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

Constraints

Comply with the following common constraints, and enforce this Skill's exclusive boundaries.

Common hard constraints

• When a task needs to be persisted to disk, use the unique ./.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/ root directory; place shared materials in shared/, and place Skill-exclusive materials in that Skill's input/、output/、log/。
• Formal deliverables, source code, and formal plans are saved according to project conventions and are not written into the task workspace; do not overwrite, delete, migrate, or write remotely without authorization.
• Project maintenance changes check BAC availability and record requirements, AI outputs, tool results, file changes, and verification summaries; BAC only performs process auditing and does not replace attribution, responsibility, or compliance judgment.
• Do not record API Keys, access tokens, passwords, Cookies, environment/credential files, private Prompts, identity information, local usernames, hostnames, or unnecessary large volumes of raw data.
• File paths must be normalized and restricted to the authorized project scope; external URLs, subprocesses, and network access follow least privilege to prevent path traversal, SSRF, and command injection.
• The Skill version is recorded uniquely in its own config.yaml:skill_info.version; changes to public APIs, protocols, directories, or configurations are synchronized with the documentation and CHANGELOG.md。
• Only design flaws in the Skill or Bensz infrastructure itself are reported to bensz-collect-bugs; first write a sanitized version to ~/.bensz-skills/bugs/, the current task is not interrupted, public reporting occurs only when the user explicitly requests it, and directly modifying the source code of a Skill already installed by the user is prohibited.

Skill-exclusive constraints

Do not exceed the scope declared in this Skill description and the process above; do not disguise unverified information as definitive conclusions.