Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/RobThePCGuy/Claude-Patent-Creatornpx agentmods add skills/robthepcguy/claude-patent-creator/troubleshooting-assistantWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/robthepcguy/claude-patent-creator/troubleshooting-assistant)<a href="https://agentmods.dev/skills/robthepcguy/claude-patent-creator/troubleshooting-assistant"><img src="https://agentmods.dev/badge/skills/robthepcguy/claude-patent-creator/troubleshooting-assistant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/robthepcguy/claude-patent-creator/troubleshooting-assistant"><img src="https://agentmods.dev/badge/skills/robthepcguy/claude-patent-creator/troubleshooting-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01059 |
| Opus 5 | $0.00018 | $0.00530 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
troubleshooting-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- troubleshooting-assistant — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
| Issue | Quick Fix |
|---|---|
| MCP server not loading | claude mcp list -> Re-register if missing |
| GPU not detected | Reinstall PyTorch with CUDA |
| BigQuery auth fails | gcloud auth application-default login |
| Index not found | patent-creator rebuild-index |
| Import errors | Activate venv: venv\Scripts\activate |
| Slow searches | Check GPU usage, reduce top_k, disable HyDE |
| Irrelevant results | Rephrase 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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 160 lines · 37 tokens per session scan A bb9e25d5a054
troubleshooting-assistant is a skill published in the GitHub repository RobThePCGuy/Claude-Patent-Creator (180 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,059 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
inventory
Codebase inventory skill — scans the repo for a named pattern (inline SQL, fetch calls, feature flags, debug leftovers, deprecated APIs, etc.) defined by a YAML "recipe pack" and emits a structured Markdown inventory cross-referenced with framework metadata (routes, handlers). The engine is language-agnostic and…
debug
Read-only bug investigation skill. Takes a bug description + optional stack trace + optional repro steps; orients via code-explorer (Haiku grep/excerpt), then dispatches the debugger persona to emit N ranked hypotheses (1/3/5 on --quick/--normal/--deep) with file:line evidence, verification steps, and confidence…
code-graph
Query the Code Graph knowledge graph for this codebase. Use when the user asks about code structure, call relationships, dependencies, blast radius, or wants to run SPARQL queries against the project graph. Requires the backend and MCP server to be running.
errors
Error explanation for the Ayrshare MCP server: translate an Ayrshare error code into a plain-English cause, a classification, and a fix. Use whenever a code or numeric error needs decoding: "what does Ayrshare error 156 mean", "why did that post fail with code 272", "explain this error", "what is error code 110 on…
fix
A debugging workflow that investigates software bugs by turning a plain-language report into a small failing test, then comparing possible causes using evidence.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.