mang30/myskills/patent-review
- community
Checking that the SKILL.md file is still in the repository.
Get an external patent examiner review of a patent application. Use when user says \"专利审查\", \"patent review\", \"审查意见\", \"examiner review\", or wants critical feedback on patent claims and specification.
Install
npx vskill@latest install mang30/myskills/patent-reviewSKILL.md
Patent Examiner Review via Codex MCP (xhigh reasoning)
Get a multi-round patent examiner review of the patent application based on: $ARGUMENTS
Adapted from /research-review. The reviewer persona is a patent examiner, not a paper reviewer.
Constants
REVIEWER_MODEL = gpt-5.5— Model used via Codex MCPREVIEW_ROUNDS = 2— Number of review roundsEXAMINER_PERSONA = "patent-examiner"— GPT-5.4 persona
Prerequisites
- Codex MCP Server configured:
``bash claude mcp add codex -s user -- codex mcp-server ``
Inputs
patent/CLAIMS.md— all drafted claimspatent/specification/— all specification sectionspatent/figures/numeral_index.md— reference numeral mappingpatent/PRIOR_ART_REPORT.md— known prior artpatent/INVENTION_DISCLOSURE.md— invention structure
Workflow
Step 1: Gather Patent Context
Before calling the external reviewer, compile a comprehensive briefing:
- Read all claims (independent + dependent)
- Read specification sections (at least summary and detailed description)
- Read prior art report for context
- Identify: core inventive concept, claim scope, known prior art, target jurisdiction
Step 2: Round 1 — Full Examiner Review
Send to REVIEWER_MODEL via spawn_agent with xhigh reasoning:
Step 3: Implement Fixes (Round 1)
Based on the examiner's office action:
- CRITICAL issues (102 rejection, 112 indefiniteness, missing enablement):
- Must be fixed before proceeding
- Amend claims or add specification support
- MAJOR issues (103 obviousness, weak claim scope, missing support):
- Should be fixed or argued
- Consider claim amendments or specification additions
- MINOR issues (language quality, numeral consistency, formatting):
- Fix if time permits
- Document in output for later cleanup
For each fix:
- Show the specific change (old claim -> new claim)
- Explain how the fix addresses the examiner's concern
Step 4: Round 2 — Follow-Up Review
Use send_input with the saved reviewer id from Round 1:
Step 5: Generate Improvement Report
Write patent/PATENT_REVIEW.md:
Key Rules
- The reviewer persona must be a patent examiner, not a paper reviewer or academic.
- Always use
model_reasoning_effort: "xhigh"for maximum analysis depth. - Address CRITICAL and MAJOR issues before proceeding to the next phase.
- Document all changes in the review report for traceability.
- If the patentability score is below 5/10 after Round 2, recommend significant rework before filing.
- The review is advisory -- actual prosecution may proceed differently.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/skills-codex/patent-review/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mang30/myskills/patent-review)