CtrlK
BlogDocsLog inGet started
Tessl Logo

mineru-sciverse

High-fidelity academic document parsing (MinerU) + scientific literature retrieval (SciVerse), with one-command setup. Use when the user wants to parse/convert a PDF, image, Word, PPT, or Excel into Markdown/JSON — especially papers with formulas, tables, or scanned/multi-column layout ("解析PDF", "PDF转markdown", "提取论文内容", "公式转LaTeX", "mineru", "pdf2md"); to search scientific papers / literature ("文献检索", "sciverse", "找论文", "semantic search papers"); or to bootstrap this toolchain on a new device ("配置文档解析环境", "新设备装 mineru/sciverse"). For generic PDF ops (merge, split, rotate, fill forms, plain text extract) prefer the built-in `pdf` skill.

70

Quality

85%

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

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.

A well-structured, actionable body with good workflow sequencing and validation, undermined by progressive-disclosure references to bundle files (reference.md, setup.sh) that are not actually present.

Suggestions

Add the missing `reference.md` file referenced for 'backends, REST endpoints, or disk/uninstall info', or remove the reference and inline the essential detail.

Add the missing `setup.sh` (or point to the repo-level `install/install.sh` consistently) so the 'Setup on a new device' workflow is executable.

Add an explicit output-verification step for batch parsing (e.g., confirm markdown was written per file) to lift workflow clarity from good to complete.

DimensionReasoningScore

Conciseness

Largely lean — tight decision tables, terse fallback bullets, and copy-paste code blocks — with only minor over-justification such as 'The local CLI is not an MCP, and the routing/fallback logic spans tools — so this guidance is needed on top of the raw MCP tool descriptions.'

4 / 5

Actionability

Provides concrete executable commands ('pdf2md paper.pdf', 'bash scripts/batch-local.sh', 'bash "$(dirname "$0")/scripts/check.sh"') and token URLs; cloud/sciverse usage is given as natural-language MCP prompts rather than exact tool invocations, a minor gap.

4 / 5

Workflow Clarity

Clear sequence (decision table → fallback → preflight → usage) with explicit validation checkpoints (check.sh preflight, retry-on-failure feedback loop for parses), satisfying the batch/destructive validation requirement; only minor gaps in output verification.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep references, but 'reference.md' and 'setup.sh' are referenced in the body and neither exists in the bundle, breaking navigation to the detail material.

3 / 5

Total

15

/

20

Passed

Description

100%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.

An exemplary description: concrete capabilities, bilingual trigger terms covering synonyms and tool names, explicit 'Use when' guidance, and clear boundary routing to avoid conflicts with the generic pdf skill.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'parse/convert a PDF, image, Word, PPT, or Excel into Markdown/JSON', 'search scientific papers / literature', 'bootstrap this toolchain on a new device' — with comprehensive coverage of the toolkit's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (parse/convert, search, bootstrap) and 'when' via a clear 'Use when the user wants to...' clause with concrete trigger phrases for each capability.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms including synonyms and tool names in both English and Chinese: '解析PDF', 'PDF转markdown', '公式转LaTeX', 'mineru', 'pdf2md', '文献检索', 'sciverse', '找论文', 'semantic search papers'.

5 / 5

Distinctiveness Conflict Risk

A clear niche (MinerU parsing + SciVerse search) with distinct triggers, and it explicitly routes generic PDF ops ('merge, split, rotate, fill forms, plain text extract') to the built-in `pdf` skill, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Ares960826/ares-agent-toolkit
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.