Fallback workflow for regulatory research when web extraction tools fail on government PDFs
This skill provides a systematic approach to gathering regulatory/compliance information when primary web extraction tools fail on government or regulatory website URLs.
read_webpage returns "unknown error" on .gov or regulatory PDF URLssearch_web fails to retrieve current regulatory informationFirst, try standard web extraction tools:
1. Use read_webpage on the regulatory URL
2. Use search_web for supplementary regulatory information
3. Document which tools failed and with what errors
When primary tools fail, delegate to shell_agent for secondary research:
Task: "Research [TOPIC] compliance requirements using available system tools.
Gather information from alternative sources including:
- State/federal regulatory summaries
- Industry compliance guides
- Professional association resources
Focus on actionable checklist items for [SPECIFIC REQUIREMENT]"
Example shell_agent task for pharmacy compliance:
"Research pharmacy compliance requirements for [state]. Gather information
about licensing, storage, dispensing, and documentation requirements from
available sources. Create structured notes on mandatory compliance areas."
When sources remain inaccessible, use established domain knowledge:
For pharmacy compliance, standard areas include:
- Licensing and registration requirements
- Controlled substance handling
- Prescription record-keeping
- Storage and security protocols
- Patient counseling requirements
- Continuing education obligations
Structure output with clear sourcing transparency:
## [Requirement Area]
**Status**: Based on standard regulatory framework (primary sources inaccessible)
**Key Requirements**:
- [Item 1] - Standard industry requirement
- [Item 2] - Common regulatory expectation
- [Item 3] - Best practice guideline
**Note**: Verify with [specific agency] for jurisdiction-specific requirements
Always include disclaimers when using fallback approach:
⚠️ **Verification Required**: This checklist was created using secondary
sources due to primary regulatory website inaccessibility. Please verify
all requirements with the official [Agency Name] before implementation.
# [Compliance Area] Checklist
## Source Transparency
This document was created using secondary research methods due to
inaccessibility of primary regulatory sources. All items should be
verified with official authorities.
## Core Requirements
[Checklist items based on standard regulatory framework]
## Verification Steps
[List of specific items requiring official confirmation]
## Recommended Next Actions
1. Contact [Agency] for current requirements
2. Review [Official Publication] when accessible
3. Consult with [Professional Association] for updates
This workflow applies to: