CtrlK
BlogDocsLog inGet started
Tessl Logo

research-topic-extractor

当用户明确要求"从文件/图片/网页/描述中提取综述主题"、"生成主题+关键词+核心问题结构化输出",或要求使用旧名 get-review-theme skill 时使用。支持文件(PDF/Word/Markdown/Tex)、文件夹、图片、自然语言描述、网页 URL 等多种输入源,自动识别输入类型并提取内容,生成可直接用于 research-literature-review 及其他文献综述技能的结构化输出。

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/research-topic-extractor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-organized, actionable instruction skill with a clear workflow and graceful error recovery, but it underuses its own bundle: the prompt-templates reference file is never referenced from the body, which both hurts progressive disclosure and leaves the most executable template unreachable.

Suggestions

Add an explicit link to references/prompt_templates.md in the 工作流 or 语义提取 section (e.g., 'See [prompt_templates.md](references/prompt_templates.md) for the executable prompt and per-input-type tuning') so the bundle is discoverable.

Inline a short concrete output example (one 主题/关键词/核心问题 triple) directly in the 输出 section to raise actionability without relying on the orphaned reference.

Trim or relocate the bensz-collect-bugs collaboration and BenszAPI workspace sections to a separate operational reference, since they do not serve the core extraction task and dilute conciseness.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence (no basic concept explanations), but the BenszAPI workspace and bensz-collect-bugs collaboration sections are tangential to the extraction task and could be trimmed — efficient with minor over-explanation.

4 / 5

Actionability

Gives concrete per-input-type handling (图片→LLM视觉, URL→网页读取工具失败则请用户提供正文, 文件夹→递归扫描 .md/.txt/.pdf) and precise output specs (一句话主题, 5-10 英文术语, 2-5 核心问题); missing an inline example/template keeps it at 4.

4 / 5

Workflow Clarity

A clear four-step sequence (识别输入类型→提取内容→语义提取→格式化) is paired with a dedicated error-handling section providing recovery feedback loops, but there are no explicit inline validation checkpoints, so not 5.

4 / 5

Progressive Disclosure

The body is well-sectioned, but the bundle file references/prompt_templates.md exists and is never linked or signaled from the body, leaving the reference orphaned and unnavigable — matching 'references present but not clearly signaled'.

3 / 5

Total

15

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly pairs a concrete capability statement with explicit trigger conditions and the legacy skill name. It is specific, well-triggered, and reasonably distinct, falling just short of perfect only on trigger synonym/extension breadth.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions ("自动识别输入类型并提取内容", "生成...结构化输出") spanning PDF/Word/Markdown/Tex, folders, images, URLs, and text — minor gaps in coverage keep it below 5.

4 / 5

Completeness

Explicitly answers both "what" (multi-source structured topic extraction feeding research-literature-review) and "when" ("当用户明确要求...时使用") with concrete trigger phrases, satisfying the Use-when requirement.

5 / 5

Trigger Term Quality

Includes explicit natural trigger phrases ("从文件/图片/网页/描述中提取综述主题", "生成主题+关键词+核心问题结构化输出") and the legacy name "get-review-theme", with good format coverage; a few synonyms/extensions are missing so not 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear 综述主题/literature-review-prep niche tied to a specific downstream skill and output schema, with only minor overlap risk against general content-extraction skills.

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
huangwb8/ChineseResearchLaTeX
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.