research-topic-extractor

Original：🇨🇳 Chinese

Translated

This skill is used when users explicitly request to "extract review themes from files/images/webpages/descriptions", "generate structured output of theme + keywords + core questions", or request to use the old name "get-review-theme" skill. It supports multiple input sources including files (PDF/Word/Markdown/Tex), folders, images, natural language descriptions, and webpage URLs. It automatically identifies the input type, extracts content, and generates structured output that can be directly used for research-literature-review and other literature review skills.

2installs

Sourcehuangwb8/chineseresearchlatex

Added on2026-09-05

NPX Install

npx skill4agent add huangwb8/chineseresearchlatex research-topic-extractor

SKILL.md Content (Chinese)

View Translation Comparison →

Research Topic Extractor

Extract structured review themes from files, images, webpages, folders, or natural language descriptions.
Output directly serves
```
research-literature-review
```
or other literature review workflows.
Compatible with prompt triggers using the old name
```
get-review-theme
```
; system-level old directories are cleaned up by the installer.
Overarching principles: Themes must be actionable, keywords must be searchable, and core questions must be specific.

Input

Required:

```
{Input Source}
```
: File path, URL, folder path, image path, or direct text description

Optional:

```
{Output Format}
```
:
```
text
```
/
```
yaml
```
/
```
json
```
, default is
```
text
```

Workflow

Input

Provide necessary inputs according to user requests and configuration files; if information is missing, clearly list it and stop steps that depend on that input.

Execution Steps

When bugs caused by design flaws of this skill occur in the user's environment, prioritize using
```
bensz-collect-bugs
```
to record them in
```
~/.bensz-skills/bugs/
```
according to specifications. Strictly prohibit directly modifying the source code of already installed skills in the user's local Claude Code / Codex.
If the AI can still complete the user's task via a workaround, record the bug first, then continue with the current task.
When the user explicitly requests actions such as "report bensz skills bugs", call the local
```
gh
```
and
```
bensz-collect-bugs
```
, and only upload new bugs to
```
huangwb8/bensz-bugs
```
; do not pull / clone the entire bug repository.

Input Type Identification

Natural language description
Image
URL
Text file
PDF
Word
Folder

Content Extraction

Natural language: Use directly
Image: Rely on native visual capabilities of LLM
URL: Prioritize webpage reading tools; if failed, ask the user to provide the main text
Text / PDF / Word: Read directly
Folder: Recursively scan and merge core materials such as
```
.md/.txt/.pdf
```

Principles:

Prioritize using host native capabilities and existing standard tools
Gracefully degrade when tools are unavailable; do not introduce additional script dependencies

Semantic Extraction

Output around the following tasks:

Summarize the theme 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 integration
```
topic
```
can be directly fed to
```
research-literature-review
```
```
keywords
```
can supplement retrieval strategies
```
core_questions
```
can serve as reference for review boundaries and inclusion/exclusion criteria

Output

Always include three items:

```
Theme
```
```
Keywords
```
```
Core Questions
```

Format selected 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}-{brief description}/{skill name}/input|output|log/

. Reuse the same task root directory for the same task; create

shared/

only for multi-Skill collaboration. Formal deliverables are not written to this directory; historical hidden directories only allow explicit compatible reading, migration, or cleanup.

Validation

The theme must include the research object and core question or method
Keywords prioritize standard retrieval terms
Core questions must be specific; avoid empty phrases like "great significance/many challenges"

Failure and Recovery

File does not exist: Prompt the user to correct the path or paste the content directly
Format not supported: Prompt conversion
Content extraction failed: Ask the user to manually provide the text
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 description

Constraints

Comply with the following public constraints and implement the exclusive boundaries of this Skill.

Public Hard Constraints

When tasks require disk storage, use the unique root directory
```
./.bensz-api/task-{yyyymmdd-hhmm}-{brief description}/
```
; place shared materials in
```
shared/
```
, and Skill-specific materials in the Skill's
```
input/
```
,
```
output/
```
,
```
log/
```
.
Formal deliverables, source code, and formal plans are saved according to project agreements and not written to the task workspace; do not overwrite, delete, migrate, or remotely write without authorization.
For project maintenance changes, check BAC availability and record requirements, AI outputs, tool results, file changes, and verification summaries; BAC only performs process audits and does not replace signature, responsibility, or compliance judgments.
Do not record API Keys, access tokens, passwords, Cookies, environment/credential files, private Prompts, identity information, local usernames, hostnames, or unnecessary large-volume raw data.
File paths must be standardized and restricted within authorized project scopes; external URLs, subprocesses, and network access follow the principle of least privilege to prevent path traversal, SSRF, and command injection.
Skill versions are uniquely recorded in its own
```
config.yaml:skill_info.version
```
; changes to public APIs, protocols, directories, or configurations are synchronized with documents and
```
CHANGELOG.md
```
.
Only submit design flaws of the Skill or Bensz infrastructure itself to
```
bensz-collect-bugs
```
; first desensitize and write to
```
~/.bensz-skills/bugs/
```
, do not interrupt the current task, and only report publicly if explicitly requested by the user. Prohibit directly modifying the source code of already installed Skills by the user.

Skill-Specific Constraints

Do not exceed the scope stated in this Skill's description and the workflow above; do not disguise unverified information as definitive conclusions.

research-topic-extractor

NPX Install

Tags

SKILL.md Content (Chinese)

Research Topic Extractor

Input

Workflow

Input

Execution Steps

Input Type Identification

Content Extraction

Semantic Extraction

Formatting

Output

Output Management

Validation

Failure and Recovery

Constraints

Public Hard Constraints

Skill-Specific Constraints