General

mpep-researcher - Claude MCP Skill

Expert in searching and interpreting USPTO MPEP, 35 USC statutes, 37 CFR regulations using hybrid RAG search (FAISS + BM25 + HyDE)

SEO Guide: Enhance your AI agent with the mpep-researcher tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to expert in searching and interpreting uspto mpep, 35 usc statutes, 37 cfr regulations using hybrid ra... Download and configure this skill to unlock new capabilities for your AI workflow.

🌟1 stars • 34 forks
📥0 downloads

Documentation

SKILL.md
# MPEP Researcher

Expert system for USPTO legal research and compliance guidance.

## Expertise

- Manual of Patent Examining Procedure (MPEP)
- 35 USC (United States Code Title 35)
- 37 CFR (Code of Federal Regulations Title 37)
- Federal Register updates (post-Jan 2024)
- Hybrid RAG search (vector + keyword)
- HyDE query expansion
- Cross-encoder reranking

## When to Use This Agent

Use this agent when:
- Researching patent law requirements
- Finding MPEP guidance on specific topics
- Looking up statutory authority (35 USC)
- Finding regulatory requirements (37 CFR)
- Checking post-2024 policy updates
- Getting examiner guidance
- Citing legal authority

## Search Capabilities

### Hybrid Search
- FAISS vector search (semantic)
- BM25 keyword search (lexical)
- Reciprocal rank fusion (RRF)
- Cross-encoder reranking
- HyDE query expansion (optional)

### Filtering Options
- Source: MPEP, 35_USC, 37_CFR, SUBSEQUENT
- Statute type: procedural, patentability, etc.
- Regulation type: filing, examination, fees
- Updates: post-Jan 2024 only

### Coverage
- Complete MPEP manual (12,543 chunks)
- 35 USC statutes
- 37 CFR regulations
- Federal Register updates
- Consolidated laws/rules

## Tools Available

Via MCP server:
- `search_mpep` - Hybrid search with filters
- `get_mpep_section` - Retrieve full section

## Search Strategy

1. Use semantic search for concepts
2. Use keyword search for specific terms
3. Combine with RRF for best results
4. Filter by source when needed
5. Review top 3-5 results
6. Get full section for context

## Example Queries

- "claim definiteness requirements" (semantic)
- "35 USC 112(b)" (keyword)
- "enablement written description" (semantic)
- "MPEP 2163" (section number)
- "abstract requirements" (semantic)
- "37 CFR 1.72" (regulation)

## Output Format

Each result includes:
- Relevance score (0-1)
- Source (MPEP/35_USC/37_CFR)
- Section number
- Page numbers
- Full text content
- Metadata (statutes, regulations, updates)

Signals

Avg rating⭐ 0.0
Reviews0
Favorites0

Information

Repository
RobThePCGuy/Claude-Patent-Creator
Author
RobThePCGuy
Last Sync
11/3/2026
Repo Updated
11/1/2026
Created
1/15/2026

Reviews (0)

No reviews yet. Be the first to review this skill!

Related Skills

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

⭐ 9351

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

⭐ 9351

update-chrome-binaries-test-region

- Confirm the AWS CLI is logged into account `678892195805` by running `aws sts get-caller-identity`. If not, ask the user to log in.

⭐ 6396

visualize

Create inline visuals for code and explanations, or author persistent OpenClaw dashboard widgets with show_widget.

⭐ 6352

Related Guides