Detects and redacts PII in PDFs via regex and AI semantic analysis.
npx skills add https://github.com/CaseMark/redaction-tool --skill redaction-tool
Please help me install this Agent Skill. Skill: redaction-tool Source: https://github.com/CaseMark/redaction-tool/tree/main/.skill Command: npx skills add https://github.com/CaseMark/redaction-tool --skill redaction-tool
The Redaction Tool enables end-to-end detection and masking of PII in documents using a two-pass approach that combines fast regex patterns with AI-powered semantic analysis.
Load a sample document into the tool and run the two-pass PII detection to generate a redacted output.
High-intent search queries and answers about installing and using this skill.
Two-pass PII detection works by first applying fast regex patterns to identify standard sensitive data, then using AI-powered semantic analysis to catch contextual information. This combined approach ensures both standard and contextual PII are masked before document export.
You can redact PII from PDF files by loading a sample document into the tool and running the two-pass PII detection. The system processes the file using pdf.js and pdf-lib, applies redaction presets, and generates a redacted PDF output with audit logs.
Yes, you can use Case.dev LLM integration with Next.js 14 to perform AI-driven semantic analysis. This architecture enables scalable processing of text-heavy files, identifying contextual PII that standard regex patterns might miss during the redaction workflow.
Yes, the redaction tool supports preconfigured redaction presets and generates audit logs for compliant workflows. These features allow you to standardize the masking process and maintain a verifiable record of all redactions applied to your documents.
The best way to automate end-to-end PII detection is combining regex-based patterns with AI-driven semantic analysis in a two-pass workflow. This method handles both standard formats and contextual data in text-heavy files, enabling review workflows and compliant PDF export.
zinohomeExtract text from PDF documents using the pdftotext utility.
garethdaineDetect and redact PII from documents with configurable styles and audit logs.
OpenAEC-FoundationBridge PDF.js rendering and pdf-lib editing with coordinate transforms.
framerslabDetect and redact personally identifiable information from text using regex, NLP, and NER.
