Agent skill

Index Manager

by RobThePCGuy in RobThePCGuy/Claude-Patent-Creator

Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.

MITAuto-check passedLegal & Compliance

Install Index Manager

skills CLI
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill index-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install RobThePCGuy/Claude-Patent-Creator index-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/index-manager .claude/skills/index-manager && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
index-manager
GitHub stars
196
Token cost
~994 tokens
SKILL.md length
239 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.

  • Works in 5 steps: PDF Management → Index Building → Verification → …
  • Tasks that involve Intellectual property
  • SKILL.md covers When to Use, Index Lifecycle, Phase 1: PDF Management and Phase 2: Index Building, plus 6 more sections
  • Calls python and wget; reaches uspto.gov

What it does

Index Manager is an agent skill from RobThePCGuy/Claude-Patent-Creator. Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.

Its SKILL.md is about 990 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Legal & Compliance, covering Intellectual property. The repository describes itself as: USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks… The licence is MIT.

When your agent uses it

  • Tasks that involve Intellectual property

Example prompts

  • “Use the index-manager skill to manage MPEP index lifecycle including downloads, building, maintenance, and optimization”
  • “/index-manager”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. PDF Management
  2. Index Building
  3. Verification
  4. Maintenance
  5. Content Updates

What it can do on your machine

Read from SKILL.md and the folder at commit a089731. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • wget

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • uspto.gov

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Index Manager loads about 994 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 239 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~994

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from RobThePCGuy/Claude-Patent-Creator at commit a089731, republished under its MIT licence (© RobThePCGuy). 239 words, ~994 tokens.

Download SKILL.mdSave it as .claude/skills/index-manager/SKILL.md (or your agent's skills folder).
name
index-manager
description
Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.

Index Manager Skill

Expert system for managing MPEP search index lifecycle: PDF downloads, index building, maintenance, updates, optimization.

FOR CLAUDE: All dependencies installed, system operational.

  • Go directly to appropriate phase
  • Scripts/tools in mcp_server/
  • Use patent-creator CLI when available
  • Only run diagnostics if operations fail

When to Use

Building/rebuilding MPEP index, corruption/missing files, optimization, adding content, troubleshooting.

Index Lifecycle

PDFs Not Present -> Download (2-5 min, 500MB)
  -> Extract & Parse (500MB data)
  -> Generate Embeddings (5-10 min GPU, 35-65 min CPU)
  -> Build FAISS + BM25 Indexes
  -> Index Ready (mcp_server/index/)
  -> Maintenance (Verify -> Optimize -> Update)

Phase 1: PDF Management

Check Status:

bash
ls pdfs/  # Should show mpep-*.pdf, consolidated_laws.pdf, consolidated_rules.pdf

Download PDFs:

bash
patent-creator download-mpep
# Or: python install.py (Select "Download MPEP PDFs")

Verify Integrity:

bash
python -c "
import fitz
from pathlib import Path
for pdf in Path('pdfs').glob('*.pdf'):
    try:
        doc = fitz.open(pdf)
        print(f'[OK] {pdf.name}: {len(doc)} pages')
        doc.close()
    except Exception as e:
        print(f'[X] {pdf.name}: ERROR - {e}')
"

Phase 2: Index Building

bash
patent-creator rebuild-index
# Or: python mcp_server/server.py --rebuild-index

Timeline:

  • Load PDFs: 30s
  • Extract text: 1-2 min
  • Chunk text (500 tokens): 30s
  • Generate embeddings: 5-10 min (GPU) or 35-65 min (CPU)
  • Build FAISS/BM25: 1 min
  • Save to disk: 10s

Total: 5-15 min (GPU) or 35-65 min (CPU)

Custom Build:

python
from mcp_server.mpep_search import MPEPIndex
index = MPEPIndex(use_hyde=False)
index.build_index(
    chunk_size=500,
    overlap=50,
    batch_size=32  # Reduce to 16/8 if OOM
)

Phase 3: Verification

bash
# Check files
ls -lh mcp_server/index/
# Expected: mpep_index.faiss (~150MB), mpep_metadata.json (~80MB), mpep_bm25.pkl (~60MB)

# Verify health
patent-creator health
# Should show: [OK] MPEP Index: Ready (12,543 chunks)

# Manual test
python -c "
from mcp_server.mpep_search import MPEPIndex
index = MPEPIndex()
index.build_index()
print(f'Chunks: {len(index.chunks)}')
results = index.search('claim definiteness', top_k=3)
print(f'Search results: {len(results)}')
"

Phase 4: Maintenance

When to Rebuild:

  • MPEP updates (quarterly check uspto.gov)
  • Index corruption
  • After adding new PDFs
  • Performance degradation
  • Machine migration

Rebuild Process:

bash
# Backup (optional)
cp -r mcp_server/index mcp_server/index_backup_$(date +%Y%m%d)

# Rebuild
patent-creator rebuild-index

# Verify
patent-creator health

# Remove backup if successful
rm -rf mcp_server/index_backup_*

Phase 5: Content Updates

bash
# Download new PDF
wget https://www.uspto.gov/web/offices/pac/mpep/mpep-2900.pdf -O pdfs/mpep-2900.pdf

# Rebuild (includes new section)
patent-creator rebuild-index

Note: Incremental updates not supported. Full rebuild required.

Troubleshooting

  • OOM errors during build
  • Build taking too long
  • Corrupted index files
  • Search returning no results

Performance Tuning

  • Embedding generation speed (GPU vs CPU)
  • Search latency optimization
  • Index size reduction
  • Batch size tuning

Quick Reference

CommandPurpose
patent-creator download-mpepDownload MPEP PDFs
patent-creator rebuild-indexBuild/rebuild search index
patent-creator healthCheck index health
ls -lh mcp_server/index/View index files

Best Practices:

  1. Backup before rebuild
  2. Verify PDFs before building
  3. Use GPU for 10x faster builds
  4. Test after rebuild
  5. Keep PDFs until verified
  6. Weekly health checks

© RobThePCGuy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/index-manager of RobThePCGuy/Claude-Patent-Creator.

Open the folder on GitHubat commit a089731

Compare with similar skills

Index Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Index Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Index Manager this skillRobThePCGuy/Claude-Patent-Creator196—~994Automated safety check: PassMIT
Researchalirezarezvani/claude-skills28k—~4.3kAutomated safety check: PassMIT
Linkfox Zhihuiya PDF Datalinkfox-ai/linkfox-skills1061 repos~1.8kAutomated safety check: PassMIT
Paper to Chinese Patent DrafterYuan1z0825/nature-skills46k1 repos~1.1kAutomated safety check: PassApache-2.0
Paper2patent7toCR/paper2patent649—~2.5kAutomated safety check: PassMIT
Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill1051 repos~959Automated safety check: PassNone

Similar skills

  • Research

    alirezarezvani/claude-skills

    Default entry point for any research request — a hybrid router that classifies the question deterministically and either delegates to a specialist research skill (pulse for trends/sentiment, grants…

    28k GitHub stars~4.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Linkfox Zhihuiya PDF Data

    linkfox-ai/linkfox-skills

    通过专利ID或公开号从智慧芽专利数据库下载专利PDF全文文档。当用户提到专利PDF下载、专利全文、专利文件获取、公开号查询、专利家族PDF替代、批量专利PDF导出、patent PDF download, patent full-text document, patent file download, PatSnap, patent…

    106 GitHub starsUsed in 1 repo~1.8k tokens
    Legal & ComplianceAuto-check passed
  • Paper to Chinese Patent Drafter

    Yuan1z0825/nature-skills

    Drafts Chinese invention patent applications and technical disclosures from research papers or inventor materials, tying each claim feature to source evidence.

    46k GitHub starsUsed in 1 repo~1.1k tokens
    Legal & ComplianceAuto-check passed
  • Paper2patent

    7toCR/paper2patent

    Turn an academic paper (PDF, LaTeX, pasted text, thesis chapter or technical disclosure) into a Chinese invention patent application draft — 说明书摘要、摘要附图、权利要求书、说明书、说明书附图 — delivered as DOCX/PDF with…

    649 GitHub stars~2.5k tokensUpdated 2 days ago
    Documents & OfficeAuto-check passed
  • Paper To Cn Patent

    snipp-zha/Paper-to-patent-Skill

    Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts.

    105 GitHub starsUsed in 1 repo~959 tokens
    Legal & ComplianceAuto-check passed
  • Patent Examine

    gfodor/legal-skills

    Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.

    393 GitHub stars~4.8k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

More from RobThePCGuy/Claude-Patent-Creator

All 17 skills in this repo
  • Patent Claims Analyzer

    RobThePCGuy/Claude-Patent-Creator

    Automated analysis of patent claims for USPTO compliance with 35 USC 112(b) requirements - antecedent basis, definiteness, claim structure

    196 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Patent Reviewer

    RobThePCGuy/Claude-Patent-Creator

    Expert system for reviewing utility patent applications against USPTO MPEP guidelines.

    196 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Bigquery Patent Search

    RobThePCGuy/Claude-Patent-Creator

    Fast, cloud-based patent searching across 100 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval

    196 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check: notes
  • Development Assistant

    RobThePCGuy/Claude-Patent-Creator

    Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.

    196 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check: notes
  • Epc Search

    RobThePCGuy/Claude-Patent-Creator

    RAG search across EPC provisions, EPO Guidelines for Examination, and PCT rules for European and international patent law research

    196 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • Epo Patent Analyzer

    RobThePCGuy/Claude-Patent-Creator

    Automated analysis of patent applications for EPO compliance with Art.

    196 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

Questions about Index Manager

What does Index Manager do?

Manages MPEP index lifecycle including downloads, building, maintenance, and optimization. Index Manager is an agent skill from RobThePCGuy/Claude-Patent-Creator. Manages MPEP index lifecycle including downloads, building, maintenance, and optimization.

When should I use Index Manager?

Index Manager fits situations like: tasks that involve Intellectual property.

How do I install Index Manager in Claude Code?

Run `npx skills add RobThePCGuy/Claude-Patent-Creator --skill index-manager -a claude-code`. Or copy the skill folder (skills/index-manager in RobThePCGuy/Claude-Patent-Creator) into .claude/skills/index-manager in your project. Claude Code loads it when a task matches its description.

How do I install Index Manager in Codex?

Run `npx skills add RobThePCGuy/Claude-Patent-Creator --skill index-manager -a codex`. Or copy the skill folder (skills/index-manager in RobThePCGuy/Claude-Patent-Creator) into .agents/skills/index-manager in your project. Codex loads it when a task matches its description.

Can I use Index Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RobThePCGuy/Claude-Patent-Creator --skill index-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/index-manager, .gemini/skills/index-manager, .github/skills/index-manager and .opencode/skills/index-manager in your project.

What does Index Manager need to run?

Going by SKILL.md and its folder, Index Manager needs the command-line tools its instructions call (python and wget). Our summary lists: Python 3.

Does Index Manager access the network?

SKILL.md names 1 domain. In commands or code: uspto.gov; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Index Manager safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Index Manager use?

Index Manager is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Index Manager use?

About 994 tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Index Manager?

Skills that share tags, products or a category with Index Manager: Research (alirezarezvani/claude-skills, 28k stars), Linkfox Zhihuiya PDF Data (linkfox-ai/linkfox-skills, 106 stars), Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 46k stars) and Paper2patent (7toCR/paper2patent, 649 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Index Manager?

RobThePCGuy (a GitHub user) maintains it in RobThePCGuy/Claude-Patent-Creator, which has 196 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 2026.

Source: RobThePCGuy/Claude-Patent-Creator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.