Agent skill

Troubleshooting Assistant

by RobThePCGuy in RobThePCGuy/Claude-Patent-Creator

Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

MITAuto-check passedDatabases

Install Troubleshooting Assistant

skills CLI
$ npx skills add RobThePCGuy/Claude-Patent-Creator --skill troubleshooting-assistant -a claude-code

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

GitHub CLI
$ gh skill install RobThePCGuy/Claude-Patent-Creator troubleshooting-assistant --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/troubleshooting-assistant .claude/skills/troubleshooting-assistant && 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
troubleshooting-assistant
GitHub stars
196
Token cost
~1.2k tokens
SKILL.md length
328 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

  • Works in 8 steps: Regular health checks (weekly… → Monitor logs for warnings/errors → Keep dependencies updated (test before… → …
  • Tasks that involve Data warehousing
  • SKILL.md covers When to Use, Troubleshooting Methodology, Common Issues & Quick Fixes and Detailed Issue Guides, plus 3 more sections
  • Calls python, claude and gcloud

What it does

Troubleshooting Assistant is an agent skill from RobThePCGuy/Claude-Patent-Creator. Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

Its SKILL.md is about 1.2k 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 Databases, covering Data warehousing, Intellectual property and MCP servers. It works with Model Context Protocol, Google BigQuery and CUDA. 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 Data warehousing
  • Tasks that involve Intellectual property
  • Tasks that involve MCP servers

Example prompts

  • “Use the troubleshooting-assistant skill to diagnose and resolves MCP server registration failures, GPU detection, BigQuery authentication, index…”
  • “/troubleshooting-assistant”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Regular health checks (weekly patent-creator health)
  2. Monitor logs for warnings/errors
  3. Keep dependencies updated (test before deploying)
  4. Backup before changes (especially index rebuilds)
  5. Document modifications
  6. Test after changes (run test suite)
  7. Version control (use git)
  8. Environment consistency (same Python/CUDA versions)

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
    • claude
    • gcloud

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

  • Network

    No URLs in SKILL.md. Its commands use gcloud, which can reach the network depending on how they are called.

    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

Troubleshooting Assistant loads about 1.2k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 328 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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). 328 words, ~1,174 tokens.

Download SKILL.mdSave it as .claude/skills/troubleshooting-assistant/SKILL.md (or your agent's skills folder).
name
troubleshooting-assistant
description
Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

Troubleshooting Assistant Skill

Expert diagnostic system for identifying and resolving Claude Patent Creator issues.

When to Use

System not working, error messages, slow performance, MCP server not loading, search returns no results/errors, GPU not detected, BigQuery auth fails, index build fails, tests failing, unexpected behavior.

Troubleshooting Methodology

Problem Reported
  |
[1] Gather Information (errors, recent changes, system state)
  |
[2] Reproduce Issue (minimal test case, consistent?)
  |
[3] Isolate Component (which part failing? dependencies?)
  |
[4] Diagnose Root Cause (check logs, test components, verify config)
  |
[5] Apply Fix (targeted solution, verify works)
  |
[6] Prevent Recurrence (document, add monitoring, update checks)

Common Issues & Quick Fixes

IssueQuick Fix
MCP server not loadingclaude mcp list -> Re-register if missing
GPU not detectedReinstall PyTorch with CUDA
BigQuery auth failsgcloud auth application-default login
Index not foundpatent-creator rebuild-index
Import errorsActivate venv: venv\Scripts\activate
Slow searchesCheck GPU usage, reduce top_k, disable HyDE
Irrelevant resultsRephrase query with MPEP terminology

Detailed Issue Guides

MCP Server Issues

Problems: Server not loading, tools don't work/return errors

  • 5-step diagnostic workflow
  • Path verification and correction
  • Dependency troubleshooting
  • Server restart procedures
GPU & BigQuery Issues

Problems: GPU not detected, slow performance, BigQuery auth fails, query timeouts

  • CUDA detection and PyTorch reinstallation
  • Performance diagnostics and optimization
  • BigQuery authentication and permissions
  • Timeout configuration
Index, Dependencies & Configuration

Problems: Index not found, build fails, ModuleNotFoundError, import errors, env vars not loading, irrelevant search results

  • Index rebuild procedures
  • OOM (Out of Memory) solutions
  • Virtual environment activation
  • Pydantic validation errors
  • Configuration troubleshooting
  • Search quality tuning

Diagnostic Tools

Health Check Suite
bash
# Full system health
patent-creator health

# Individual components
python scripts/test_gpu.py
python scripts/test_bigquery.py
python scripts/test_analyzers.py
python scripts/test_install.py
Component Isolation
python
# Test MPEP search
python -c "from mcp_server.mpep_search import MPEPIndex; \
           index = MPEPIndex(); index.build_index(); \
           print('OK' if index.search('test', top_k=1) else 'FAILED')"

# Test BigQuery
python -c "from mcp_server.bigquery_search import BigQueryPatentSearch; \
           search = BigQueryPatentSearch(); \
           print('OK' if search.search_by_keywords('neural network', limit=1) else 'FAILED')"

# Test analyzers
python -c "from mcp_server.claims_analyzer import ClaimsAnalyzer; \
           analyzer = ClaimsAnalyzer(); \
           print('OK' if analyzer.analyze('1. A test claim.') else 'FAILED')"
  • Log analysis (debug mode)
  • MCP communication debugging
  • Performance profiling
  • Memory profiling
  • Issue escalation procedures

Best Practices for Prevention

  1. Regular health checks (weekly patent-creator health)
  2. Monitor logs for warnings/errors
  3. Keep dependencies updated (test before deploying)
  4. Backup before changes (especially index rebuilds)
  5. Document modifications
  6. Test after changes (run test suite)
  7. Version control (use git)
  8. Environment consistency (same Python/CUDA versions)

Quick Reference

Most Common Errors
ErrorCategorySolution
"Tool not found"MCPclaude mcp list
"ModuleNotFoundError"DependenciesActivate venv, reinstall
"CUDA not available"GPUReinstall PyTorch with CUDA
"Permission denied" (BigQuery)Authgcloud auth application-default login
"Index not found"Indexpatent-creator rebuild-index
"Out of memory"Index BuildReduce batch size
"Validation error"InputCheck Pydantic model parameters
Diagnostic Commands
bash
# System health
patent-creator health

# Test components
python scripts/test_gpu.py
python scripts/test_bigquery.py
python scripts/test_install.py

# Check registration
claude mcp list

# Check paths
patent-creator verify-config

# Enable debug logging
export PATENT_LOG_LEVEL=DEBUG

© 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/troubleshooting-assistant of RobThePCGuy/Claude-Patent-Creator.

Open the folder on GitHubat commit a089731

Compare with similar skills

Troubleshooting Assistant 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.

Troubleshooting Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Troubleshooting Assistant this skillRobThePCGuy/Claude-Patent-Creator196—~1.2kAutomated safety check: PassMIT
Semantic Analystsidequery/sidemantic129—~982Automated safety check: PassAGPL-3.0
Google Cloud Storage Basicsgoogle/skills21k—~2.8kAutomated safety check: PassApache-2.0
Pytorch Clickhousepytorch/test-infra113—~2.8kAutomated safety check: PassCustom licence
Imaging Data CommonsK-Dense-AI/scientific-agent-skills48k1 repos~7.8kAutomated safety check: PassMIT
Moraine Sandbox QAeric-tramel/moraine117—~668Automated safety check: PassApache-2.0

Similar skills

  • Semantic Analyst

    sidequery/sidemantic

    Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer.

    129 GitHub stars~982 tokensUpdated today
    DatabasesAuto-check passed
  • Official

    Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets.

    21k GitHub stars~2.8k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Pytorch Clickhouse

    pytorch/test-infra

    Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.

    113 GitHub stars~2.8k tokensUpdated today
    DatabasesAuto-check passed
  • Imaging Data Commons

    K-Dense-AI/scientific-agent-skills

    Queries and downloads public cancer imaging data from NCI Imaging Data Commons.

    48k GitHub starsUsed in 1 repo~7.8k tokens
    DatabasesAuto-check passed
  • Moraine Sandbox QA

    eric-tramel/moraine

    Run isolated Moraine dev sandbox validation. An agent skill from eric-tramel/moraine.

    117 GitHub stars~668 tokensUpdated 2 days ago
    DatabasesAuto-check passed
  • Bigquery Basics

    davila7/claude-code-templates

    Manages datasets, tables, and jobs in BigQuery, and integrates with BigQuery ML and Gemini for advanced data analytics and AI-driven insights.

    32k GitHub stars~1.1k tokensUpdated today
    DatabasesAuto-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

Categories

Questions about Troubleshooting Assistant

What does Troubleshooting Assistant do?

Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems. Troubleshooting Assistant is an agent skill from RobThePCGuy/Claude-Patent-Creator. Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

When should I use Troubleshooting Assistant?

Troubleshooting Assistant fits situations like: tasks that involve Data warehousing; tasks that involve Intellectual property; tasks that involve MCP servers.

How do I install Troubleshooting Assistant in Claude Code?

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

How do I install Troubleshooting Assistant in Codex?

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

Can I use Troubleshooting Assistant 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 troubleshooting-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/troubleshooting-assistant, .gemini/skills/troubleshooting-assistant, .github/skills/troubleshooting-assistant and .opencode/skills/troubleshooting-assistant in your project.

What does Troubleshooting Assistant need to run?

Going by SKILL.md and its folder, Troubleshooting Assistant needs the command-line tools its instructions call (python, claude and gcloud). Our summary lists: Python 3.

Does Troubleshooting Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Troubleshooting Assistant 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 Troubleshooting Assistant use?

Troubleshooting Assistant 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 Troubleshooting Assistant use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Troubleshooting Assistant?

Skills that share tags, products or a category with Troubleshooting Assistant: Semantic Analyst (sidequery/sidemantic, 129 stars), Google Cloud Storage Basics (google/skills, 21k stars), Pytorch Clickhouse (pytorch/test-infra, 113 stars) and Imaging Data Commons (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Troubleshooting Assistant?

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.