Patent Novelty and Non-Obviousness Check
Unverified●35/40Claude Code●WorksValid SKILL.md that declares allowed-tools
Cursor·UnknownWe have not crawled the repo tree, so we will not guess
Codex·UnknownWe have not crawled the repo tree, so we will not guess
Gemini CLI·UnknownThe spec defines no detection rule for Gemini
Copilot·UnknownWe have not crawled the repo tree, so we will not guess
npx agentalley add patent-novelty-checkWho is stuck, and on what
I've got an idea for a product I think is original, but I have no clue if someone has already done it. Paying a lawyer thousands just to find out feels like a gamble I can't afford to take blind.
What it gives you
A plain-language report telling you whether your invention looks new and non-obvious, which existing products or patents come closest, and what to tweak to make your case stronger.
When NOT to use it
It won't file the patent for you or replace a real patent attorney's legal sign-off.
The whole source
Frontmatter — 4 properties
| name | patent-novelty-check |
|---|---|
| description | Assess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\", \"patentability check\", or wants to evaluate if an invention is patentable. |
| argument-hint | [invention-description-or-brief-path] |
| allowed-tools | Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codex |
| 1 | --- |
| 2 | name: patent-novelty-check |
| 3 | description: "Assess patent novelty and non-obviousness against prior art. Use when user says \"专利查新\", \"patent novelty\", \"可专利性评估\", \"patentability check\", or wants to evaluate if an invention is patentable." |
| 4 | argument-hint: "[invention-description-or-brief-path]" |
| 5 | allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, mcp__codex__codexA4 — This skill pulls in web or user content but never says to treat that content as data. A signal, not proof. |
| 6 | --- |
| 7 | |
| 8 | # Patent Novelty and Non-Obviousness Check |
| 9 | |
| 10 | Assess patentability of: **$ARGUMENTS** |
| 11 | |
| 12 | Adapted from `/novelty-check` for patent legal standards. Research novelty is NOT the same as patent novelty. |
| 13 | |
| 14 | ## Constants |
| 15 | |
| 16 | - `REVIEWER_MODEL = gpt-6-astra` — Model used via Codex MCP for cross-model examiner verification |
| 17 | - `NOVELTY_STANDARD = patent` — Always use legal patentability standard, not research contribution standard |
| 18 | |
| 19 | ## Inputs |
| 20 | |
| 21 | 1. Invention description from `$ARGUMENTS` |
| 22 | 2. `patent/PRIOR_ART_REPORT.md` (output of `/prior-art-search`) |
| 23 | 3. `patent/INVENTION_BRIEF.md` if exists |
| 24 | |
| 25 | ## Shared References |
| 26 | |
| 27 | Load `../shared-references/patent-writing-principles.md` for novelty/non-obviousness standards. |
| 28 | Load `../shared-references/patent-format-us.md` for 102/103 analysis framework. |
| 29 | |
| 30 | ## Workflow |
| 31 | |
| 32 | ### Step 1: Define Claim Elements |
| 33 | |
| 34 | From the invention description, extract the key claim elements that would define the invention's scope: |
| 35 | 1. List the technical features that make the invention novel |
| 36 | 2. Identify which features are known from prior art vs. inventive |
| 37 | 3. Draft preliminary claim language for 2-3 independent claims (method + system) |
| 38 | |
| 39 | ### Step 2: Anticipation Analysis (Novelty) |
| 40 | |
| 41 | For each preliminary claim, test against EACH prior art reference in `PRIOR_ART_REPORT.md`: |
| 42 | |
| 43 | **Single-reference test**: Does any single reference disclose ALL claim elements? |
| 44 | |
| 45 | | Claim Element | Ref 1 | Ref 2 | Ref 3 | ... | |
| 46 | |--------------|-------|-------|-------|-----| |
| 47 | | Feature A | Yes/No + evidence | | | | |
| 48 | | Feature B | Yes/No + evidence | | | | |
| 49 | | Feature C | Yes/No + evidence | | | | |
| 50 | | Feature D | Yes/No + evidence | | | | |
| 51 | |
| 52 | **Verdict per reference**: |
| 53 | - ANTICIPATED: One reference discloses every element → claim is not novel |
| 54 | - NOT ANTICIPATED: At least one element missing from every single reference → claim is novel |
| 55 | |
| 56 | ### Step 3: Obviousness Analysis (Inventive Step) |
| 57 | |
| 58 | If the invention is novel (passes Step 2), test for obviousness: |
| 59 | |
| 60 | **Two/three-reference combination test**: Can 2-3 references be combined to render the claim obvious? |
| 61 | |
| 62 | For each combination of the top references: |
| 63 | 1. **Primary reference**: Which reference is closest to the claimed invention? |
| 64 | 2. **Secondary reference(s)**: Which reference(s) teach the missing element(s)? |
| 65 | 3. **Motivation to combine**: Would a POSITA have reason to combine these references? |
| 66 | - Explicit suggestion in the references themselves? |
| 67 | - Same field, same problem? |
| 68 | - Common design incentive? |
| 69 | - Known technique for improving similar devices? |
| 70 | |
| 71 | Format as a matrix: |
| 72 | |
| 73 | | Combination | Primary | Secondary | Missing Elements | Motivation to Combine | Obvious? | |
| 74 | |-------------|---------|-----------|-----------------|----------------------|----------| |
| 75 | | Ref1 + Ref2 | Ref1 | Ref2 | Feature D | Same field, similar problem | Yes/No | |
| 76 | |
| 77 | ### Step 4: Cross-Model Examiner Verification |
| 78 | |
| 79 | Call `REVIEWER_MODEL` via `mcp__codex__codex` with xhigh reasoning: |
| 80 | |
| 81 | ``` |
| 82 | mcp__codex__codex: |
| 83 | model: gpt-6-astra |
| 84 | config: {"model_reasoning_effort": "xhigh"} |
| 85 | prompt: | |
| 86 | You are a senior patent examiner at the [USPTO/CNIPA/EPO]. |
| 87 | Examine the following invention for patentability. |
| 88 | |
| 89 | INVENTION: [invention description + preliminary claims] |
| 90 | |
| 91 | PRIOR ART: [prior art references with key teachings] |
| 92 | |
| 93 | Please analyze: |
| 94 | 1. Anticipation (novelty): Does any single reference anticipate any claim? |
| 95 | 2. Obviousness: Can any combination of references render claims obvious? |
| 96 | 3. Claim scope: Are the claims broad enough to be valuable? |
| 97 | 4. Recommended amendments if any claim is rejected. |
| 98 | Be rigorous and cite specific references. |
| 99 | ``` |
| 100 | |
| 101 | ### Step 5: Jurisdiction-Specific Assessment |
| 102 | |
| 103 | For each target jurisdiction, provide a patentability assessment: |
| 104 | |
| 105 | **Under 35 USC 102/103 (US)**: |
| 106 | - Novelty: PASS / FAIL (cite specific reference if fail) |
| 107 | - Non-obviousness: PASS / FAIL (cite combination if fail) |
| 108 | |
| 109 | **Under Article 22 CN Patent Law (CN)**: |
| 110 | - 新颖性 (Novelty): 通过 / 未通过 |
| 111 | - 创造性 (Inventive Step): 通过 / 未通过 |
| 112 | |
| 113 | **Under Article 54/56 EPC (EP)**: |
| 114 | - Novelty: PASS / FAIL |
| 115 | - Inventive step: PASS / FAIL (problem-solution approach) |
| 116 | |
| 117 | ### Step 6: Output |
| 118 | |
| 119 | Write `patent/NOVELTY_ASSESSMENT.md`: |
| 120 | |
| 121 | ```markdown |
| 122 | ## Patentability Assessment |
| 123 | |
| 124 | ### Invention Summary |
| 125 | [description] |
| 126 | |
| 127 | ### Overall Assessment |
| 128 | [PATENTABLE / PATENTABLE WITH AMENDMENTS / NOT PATENTABLE] |
| 129 | |
| 130 | ### Anticipation Analysis |
| 131 | [claim-by-claim matrix against each reference] |
| 132 | |
| 133 | ### Obviousness Analysis |
| 134 | [combination analysis with motivation to combine] |
| 135 | |
| 136 | ### Cross-Model Examiner Review |
| 137 | [summary of GPT-6-Astra examiner feedback] |
| 138 | |
| 139 | ### Recommended Claim Amendments |
| 140 | [If claims need modification to overcome prior art, suggest specific amendments] |
| 141 | |
| 142 | ### Risk Factors |
| 143 | [What could cause rejection during actual prosecution?] |
| 144 | ``` |
| 145 | |
| 146 | ## Key Rules |
| 147 | |
| 148 | - Patent novelty is absolute: any public disclosure before the priority date counts as prior art, worldwide. |
| 149 | - Research novelty ("has anyone published this?") is NOT the same as patent novelty ("does any single reference teach every claim element?"). |
| 150 | - Obviousness requires BOTH: (1) a combination of references AND (2) a motivation to combine them. |
| 151 | - Never assume the invention is patentable just because no identical patent exists. |
| 152 | - The assessment is advisory only -- actual prosecution may reveal different prior art. |
| 153 | - If `mcp__codex__codex` is not available, skip cross-model examiner review and note it in the output. |
| 154 |
Reviews
Installed this one?Write the first review and take the Trailblazer badge.
Alternatives
Structure Your Invention For A Patent FilingDescribe your invention in plain words and get back a formal write-up that lays out the problem it solves, how it works, and which parts are worth protecting.●····●37/40Claims Drafting: The Core Patent SkillDescribe your invention in plain words and get back a numbered set of formal patent claims — the legal wording that defines exactly what you own.●····●36/40Patent Pipeline: From Invention to FilingDescribe your invention in plain words and get back a complete first-draft patent application — claims, full description, and abstract — ready to hand to a patent attorney.●····●35/40Codebase ScannerScans the codebase to generate project-doc.md and AGENTS.md. Use when bootstrapping a new agent-driven repo, refreshing project documentation after architectural changes, or running a delta scan to detect drift. Runs a full scan on first use and a smart delta scan on subsequent runs. Uses understand-anything + context-mode when available, falls back to native tools otherwise. Only updates AGENTS.md on detected architectural changes with human confirmation.◐◐◐◐◐●33/40