Contract workflows, forms, document review, archive search, and evidence-oriented legal and compliance support.
- Live page: https://agentskillexchange.com/industry-skills/#legal-ops-compliance
- Homepage access: Curated Collections on https://agentskillexchange.com/
- Legal operations, compliance, and records teams that need document intake, review, redaction, and archive workflows.
- Teams preparing evidence packets where provenance and review boundaries matter.
- Convert scanned PDFs and office files into searchable text.
- Extract clauses, tables, attachments, and metadata from mixed records.
- Run cited research and matter knowledge retrieval with source boundaries.
- Build diligence review tables and route higher-risk agent actions through approval gates.
- Redact sensitive data before sharing or indexing.
- Search large archives before manual review.
- Document review packet: OCR → extract text and tables → redact PII → search archive → export review notes
- Signing and forms: Prepare PDF forms → route signature → store final packet → index metadata
- Research and diligence support: Search cited sources → ingest matter documents → extract review-table fields → gate external actions → preserve decision evidence
| Skill | What it does here | Persona | Install | Stars |
|---|---|---|---|---|
| Documenso Open Source Document Signing Platform | Adds an auditable signing path for contract and approval packets. | Legal ops / contract admin | High | 12.6k |
| DocuSeal Open Source Document Signing and PDF Form Platform | Combines PDF form preparation and signatures for document-heavy approval flows. | Legal ops / forms administrator | Medium | 11.7k |
| OCRmyPDF Searchable PDF OCR Pipeline | Turns scanned evidence and records into searchable PDFs before review. | Records manager / compliance analyst | Medium | 33.2k |
| Apache Tika Document Extractor | Provides broad-format document extraction when matter files include Office docs, PDFs, and attachments. | eDiscovery engineer / records ops | High | 3.7k |
| Apache Tika Document Parser | Extracts metadata and embedded objects from heterogeneous files for archive triage. | Compliance engineer / archive specialist | High | 3.7k |
| Extract structured text, metadata, tables, and images from mixed documents through an MCP server with Kreuzberg | Adds an MCP-accessible extraction layer for PDFs, Office files, images, HTML, and other mixed matter inputs before review or indexing. | Matter knowledge engineer / eDiscovery ops | High | 7.6k |
| pdfplumber Python PDF Text and Table Extraction Library | Pulls tables, text, and layout clues from contract exhibits and regulatory PDFs. | Legal analyst / data wrangler | Medium | 10.1k |
| Parse local PDFs into agent-ready text, JSON, and screenshots with LiteParse | Creates text, spatial JSON, and screenshots so reviewers can inspect what an agent saw. | Document review lead / AI ops | Medium | 5.1k |
| Search PDFs, Office files, ebooks, and archives with one query before manual review | Finds relevant records across mixed archives before humans spend time opening files one by one. | Investigator / records analyst | Low | 9.6k |
| Paperless-ngx Document OCR and Archive Management System | Provides a durable archive system for scanned paperwork, tags, correspondents, and retrieval. | Compliance ops / records manager | High | 38.1k |
| LangExtract LLM-Powered Structured Text Extraction | Extracts named entities, obligations, dates, and clauses into auditable structured outputs. | Legal analyst / compliance reviewer | Medium | 35k |
| Turn messy document collections into structured rows with DocETL | Turns large contract, diligence, or evidence sets into repeatable structured rows with failure review across the corpus. | Diligence lead / legal data analyst | High | 3.7k |
| Redact PII from text before sharing or indexing with scrubadub | Redacts sensitive identifiers before content enters search, summarization, or external review. | Privacy analyst / compliance ops | Low | 421 |
| Search large PDFs and read only the relevant pages before answering | Limits review to relevant pages of long PDFs instead of pushing full documents through an agent. | Legal researcher / review analyst | Medium | 17 |
| Run local deep research workflows with Local Deep Research | Runs private cited research across web, academic, and local document sources while preserving source links and a controlled knowledge base. | Legal researcher / knowledge manager | High | 7.9k |
| Process, redact, OCR, and sign documents with Nutrient Agent Skill | Bundles OCR, redaction, form filling, conversion, and signing for governed document operations. | Document automation lead | High | 5 |
| Convert dense PDFs into LLM-ready text and page-aligned markdown with olmOCR | Converts dense scanned or layout-heavy PDFs into page-aligned text for cited review. | eDiscovery analyst / knowledge engineer | High | 17.1k |
| Turn documents into validated knowledge graphs with Docling Graph | Extracts schema-checked entities and relationships when matters need structured fact maps. | Knowledge engineer / compliance analyst | High | 134 |
| Use RAGFlow as a retrieval and context layer for agent workflows | Provides a supervised RAG layer for matter document knowledge bases with traceable source support before agent answers are reviewed. | Matter knowledge manager / legal AI ops | High | 79.8k |
| Extract structured markdown, JSON, and tagged-PDF-ready outputs from PDFs with OpenDataLoader PDF | Produces markdown, coordinate-aware JSON, and accessibility-oriented outputs from PDF packets. | Document processing engineer | High | 19.1k |
| Enrich Paperless-ngx documents with AI-generated titles tags and correspondents using paperless-gpt | Improves archive metadata after ingestion so humans can search and route records faster. | Records manager / knowledge ops | High | 2.3k |
| Capture a live webpage as a clean PDF or readable archive for offline review with Percollate | Preserves web evidence as readable offline artifacts for citation and handoff. | Investigator / compliance analyst | Low | 4.6k |
| Extract structured data and attachments from raw email with MailParser | Normalizes raw email evidence and attachments before archive search or review. | Legal ops / mailbox reviewer | Medium | 1.7k |
| Strip quoted email history and signatures before summarizing inbound replies | Separates the newest human reply from long threads so summaries do not duplicate history. | Case manager / legal assistant | Low | 78 |
| Load .mbox mail archives into SQLite for offline search, audits, and dataset joins | Turns mailbox archives into queryable SQLite evidence stores for offline audit work. | Investigator / data analyst | Medium | 39 |
| MarkItDown Document-to-Markdown Converter by Microsoft | Converts Office files, PDFs, email-like documents, and other matter inputs into Markdown for review packets and audit summaries. | Legal ops analyst / compliance reviewer | Medium | 93.2k |
| MinerU PDF-to-Markdown Document Parser | Handles complex PDFs with layout-aware Markdown and JSON output for contract packets, exhibits, and long-form compliance evidence. | eDiscovery engineer / records analyst | High | 57.8k |
| Put approval gates and audit-ready policy checks between agents and external actions with DashClaw | Adds approval gates and replayable decision evidence when legal AI workflows need human review before external actions. | Legal AI governance lead / compliance ops | High | 241 |
| Extract OCR-ready Markdown from documents with Zerox | Turns scanned contracts, exhibits, and evidence PDFs into reviewable Markdown before legal search or redaction workflows. | Legal ops / document review lead | Medium | 12.2k |
| Build managed document parsing pipelines with LlamaCloud Services | Provides a managed parsing path for high-volume contract and policy packets where local parsers are too brittle. | Legal ops automation engineer | Medium | 4.2k |
| Prepare agent-ready PDF and document extraction with PyMuPDF | Gives legal ops a fast source-backed PDF extraction step before contract review, diligence packets, or clause analysis. | Legal ops analyst / contract reviewer | Medium | 10.1k |
| Convert complex PDFs and document images into agent-ready Markdown with OCRFlux | Turns scanned or layout-heavy legal documents into Markdown that downstream review agents can cite and inspect. | Legal document intake specialist | High | 2.5k |
| Parse agent-ready PDFs and document images with MonkeyOCR | Adds an OCR path for mixed legal PDFs and document images before matter summaries or compliance checks. | Paralegal / compliance intake operator | High | 6.6k |
| Evaluate document parsers for agent ingestion with ParseBench | Lets teams compare extraction quality before standardizing a parser for legal review workflows. | Legal automation lead / document QA | Medium | 474 |
- The collection avoids legal-advice framing; these are intake, evidence, and operations tools.
- Document-centric entries are favored over general security scanners unless they support compliance evidence work directly.
- Research and RAG picks are framed as source-grounded support for legal operations and human review, not automated legal advice.
- Do not let infra-policy scanners take over this collection. Keep v1 document-centric.