mineru-document-explorerREQUIRED for any task involving reading or understanding PDF contents. Use when a user asks about a .pdf file — reading pages, answering questions, extractin...
Install via ClawdBot CLI:
clawdbot install rise-1210/mineru-document-explorerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://staging.mineru.org.cn/rag/Uses known external API (expected, informational)
api.openai.comAI Analysis
The skill's external API calls are opt-in, documented, and consistent with its PDF analysis purpose. While it can run a local server and call external services, these require explicit user configuration and credentials, minimizing unauthorized data exfiltration risk. The primary concern is the potential for unsafe shell commands referenced in the rule-based signals, but the skill definition itself emphasizes safety checks and user control.
Generated Oct 2, 2026
An analyst uses the skill to initialize quarterly earnings PDFs, generates an outline, then searches for keywords like 'revenue' or 'EBITDA' to jump straight to relevant pages. Instead of manually scrolling through 80-page reports, they extract tables and figures verified via crop_path for downstream modeling.
Paralegals init long vendor contracts and use semantic search to find indemnification, termination, or liability clauses without reading every page. The skill returns only relevant pages, cutting contract review time dramatically while ensuring no clause is missed.
A researcher ingests arXiv PDFs of related papers and uses semantic search to locate methodology or results sections matching specific queries. Figures are extracted and verified, accelerating literature reviews and meta-analyses across dozens of papers.
Clinicians load scanned hospital guidelines, enable PageIndex with an OpenAI-compatible key to auto-generate outlines for non-text PDFs, then search for dosage or protocol pages. This lets staff retrieve treatment instructions quickly without paging through scanned manuals.
Support engineers init product manuals and run keyword/semantic searches to answer customer questions about specifications or troubleshooting steps. The CLI returns targeted pages and elements, enabling fast, accurate responses while avoiding full-document scans.
Offer the doc-search CLI and local processing free, while monetizing the optional cloud services: PageIndex outline generation, MinerU cloud OCR, and hosted embedding/reranker endpoints. Teams pay per API call or via subscription tiers that unlock higher quotas and managed infrastructure.
Package the skill into a turnkey enterprise product with on-prem deployment, SSO, audit logging, and custom integrations into DMS or CRM systems. Target legal, finance, and healthcare firms with compliance needs requiring private inference.
Distribute the skill as a plugin for AI agent marketplaces (e.g., Claude skills, LangChain tools) with a paid connector that routes heavy PDF workloads to managed OCR and search infrastructure. Developers embed it in their own document-centric apps via an API key.
💬 Integration Tip
Run the setup installer first and verify config-state.json's setup_complete flag; read the matching references/cmd-*.md file before every command to avoid guessing parameters, and remember --page_idxs is 0-indexed. Always search first, verify extracted figures via crop_path, and append new pitfalls to references/tips.md after each task.
Scored Oct 2, 2026
Audited Apr 16, 2026 · audit v1.0
Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.
Monitor RSS and Atom feeds for content research. Track blogs, news sites, newsletters, and any feed source. Use when monitoring competitors, tracking industr...
用 MinerU API 解析 PDF/Word/PPT/图片为 Markdown,支持公式、表格、OCR。适用于论文解析、文档提取。
Provides a personalized morning report with today's reminders, undone Notion tasks, and vault storage summary for daily planning.
Extract text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.
Fetch scheduled economic events and data releases from the FMP API for specified dates, filtering by impact, country, and type, and output a chronological ma...