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.
Patent research and IP landscape: prior-art search, claim mapping, landscape analysis, and freedom-to-operate.
Install Patent
$ npx skills add borghei/Claude-Skills --skill patent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install borghei/Claude-Skills patent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/research/patent .claude/skills/patent && rm -rf skills-srcUse ~/.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/
Install the "patent" agent skill from https://github.com/borghei/Claude-Skills/tree/main/research/patent into .claude/skills/patent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "patent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/borghei/Claude-Skills/tree/main/research/patentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add borghei/Claude-Skills --skill patent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install borghei/Claude-Skills patent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/research/patent .agents/skills/patent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "patent" agent skill from https://github.com/borghei/Claude-Skills/tree/main/research/patent into .agents/skills/patent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "patent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add borghei/Claude-Skills --skill patent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install borghei/Claude-Skills patent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/research/patent .cursor/skills/patent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "patent" agent skill from https://github.com/borghei/Claude-Skills/tree/main/research/patent into .cursor/skills/patent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "patent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/borghei/Claude-Skills.git --path research/patent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add borghei/Claude-Skills --skill patent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install borghei/Claude-Skills patent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/research/patent .gemini/skills/patent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "patent" agent skill from https://github.com/borghei/Claude-Skills/tree/main/research/patent into .gemini/skills/patent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "patent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install borghei/Claude-Skills patentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add borghei/Claude-Skills --skill patent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/research/patent .github/skills/patent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "patent" agent skill from https://github.com/borghei/Claude-Skills/tree/main/research/patent into .github/skills/patent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "patent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add borghei/Claude-Skills --skill patent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install borghei/Claude-Skills patent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/research/patent .opencode/skills/patent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "patent" agent skill from https://github.com/borghei/Claude-Skills/tree/main/research/patent into .opencode/skills/patent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "patent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
patent- GitHub stars
- 881
- Token cost
- ~1.7k tokens
- SKILL.md length
- 748 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 349
- Repo updated
- First seen
- Licence
- MIT
At a glance
Patent research and IP landscape: prior-art search, claim mapping, landscape analysis, and freedom-to-operate.
- Works in 4 steps: Define invention claims (key novel… → Identify search classifications (CPC /… → Run prior_art_search_planner.py to… → …
- Conducting a prior-art search
- SKILL.md covers When to use this skill, Inputs the advisor expects, Clarify First and Workflows, plus 5 more sections
- Runs Python scripts from its folder; calls python3
What it does
Patent is an agent skill from borghei/Claude-Skills. Patent research and IP landscape: prior-art search, claim mapping, landscape analysis, and freedom-to-operate. Use when conducting a prior-art search, mapping an IP landscape, evaluating patentability, or running an FTO analysis.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/claim-mapping-and-landscape.md`, `references/freedom-to-operate-and-patentability.md` and `references/prior-art-search-strategy.md`).
It sits in Legal & Compliance, covering Intellectual property. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.
When your agent uses it
- Conducting a prior-art search
- Mapping an IP landscape
- Evaluating patentability
- Running an FTO analysis
Example prompts
- “/patent”
Requirements
- Python 3
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Define invention claims (key novel features).
- Identify search classifications (CPC / IPC) + keywords.
- Run prior_art_search_planner.py to produce a search plan.
- Execute on USPTO / EPO / Espacenet / Google Patents / WIPO.
What it can do on your machine
Read from SKILL.md and the folder at commit 4a698e8. 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
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Patent loads about 1.7k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 59 tokens; SKILL.md has 748 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 748 words, ~1,735 tokens.
Download SKILL.mdSave it as
.claude/skills/patent/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- patent
- description
- Patent research and IP landscape: prior-art search, claim mapping, landscape analysis, and freedom-to-operate. Use when conducting a prior-art search, mapping an IP landscape, evaluating patentability, or running an FTO analysis.
- license
- MIT + Commons Clause
- metadata.version
- 1.0.0
- metadata.author
- borghei
- metadata.category
- research
- metadata.domain
- research
- metadata.updated
- 2026-05-27
- metadata.tags
- patent, ip, prior-art, freedom-to-operate, patentability, claims, landscape
Patent Research
A research-focused patent skill (not legal filing). Covers prior-art search, IP landscape mapping, claim analysis, freedom-to-operate, and patentability. For formal patent prosecution, work with a licensed patent attorney.
When to use this skill
- Conducting a prior-art search before filing a provisional patent
- Mapping the IP landscape in a technology area
- Evaluating the patentability of an invention
- Assessing freedom-to-operate before launching a product
- Tracking competitive patent activity in a market
- Preparing a patent strategy for a startup or R&D group
Inputs the advisor expects
- Invention description (problem, solution, novelty)
- Technology area + relevant CPC/IPC classifications
- Target jurisdictions (US, EU, JP, CN — IP is jurisdictional)
- Existing prior art known (key references)
- Competitor list
- Timeline pressure (filing deadline, product launch)
Clarify First
Before running the analysis, confirm these inputs. If any is unknown or vague, ASK — do not assume:
- Analysis type (prior-art search, patentability, FTO, or landscape) — these are different deliverables with different methods and outputs
- Invention description (problem, solution, novelty) — drives the claims and search classifications
- Target jurisdictions (US, EU, JP, CN) — IP is jurisdictional; changes FTO scope and filing strategy
- Technology area + CPC/IPC classifications — drives a search beyond keywords (which misses synonyms/translations)
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Workflows
Workflow 1 — Plan a prior-art search
- Define invention claims (key novel features).
- Identify search classifications (CPC / IPC) + keywords.
- Run
prior_art_search_planner.pyto produce a search plan. - Execute on USPTO / EPO / Espacenet / Google Patents / WIPO.
python3 patent/scripts/prior_art_search_planner.py \
--input invention.json --format markdownWorkflow 2 — Map the IP landscape
- Capture identified patents (yours, competitors', adjacent).
- Run
claim_landscape_mapper.pyto cluster by claim type, owner, technology subarea, recency; surface white space + crowded areas.
python3 patent/scripts/claim_landscape_mapper.py \
--input patents.json --format markdownWorkflow 3 — Score patentability of an invention
- Capture invention + closest prior art.
- Run
patentability_scorer.pyto rate novelty, non-obviousness, utility, subject matter eligibility.
python3 patent/scripts/patentability_scorer.py \
--input patentability.json --format markdownDecision frameworks
The three patentability criteria (US baseline)
- Novelty (35 USC §102): not previously disclosed
- Non-obviousness (35 USC §103): not obvious to person skilled in the art
- Utility (35 USC §101): useful, with practical application
Plus:
- Subject matter eligibility (§101): not abstract idea, not law of nature
- Enablement (§112): described well enough to be made by skilled artisan
- Definiteness (§112): claims clearly distinguish
Prior-art categories
- Patents (issued + published applications)
- Non-patent literature (papers, conference, dissertations, technical reports)
- Commercial products (sold publicly before filing)
- Public disclosures (talks, demos, blog posts — yes, including your own > 1 year prior)
- Sales activity (offers for sale, even pre-launch)
Inventors often miss non-patent prior art; this is where searches break.
Show full SKILL.md (319 more words)Show less
Freedom-to-operate (FTO)
Different from patentability. FTO asks: can I commercialize without infringing someone else's patent?
- Patentability ≠ FTO (your patent could still infringe another)
- FTO is jurisdiction-specific
- Active patents only (not expired); typically 20 years from filing
- Patent attorney involvement essential for formal opinion
IP strategy by stage
- Pre-seed: capture inventions; consider provisional filings; don't over-file
- Seed/Series A: strategic provisionals; key utility filings
- Series B+: PCT international; continuations to maintain pendency
- Mature: portfolio management; licensing; enforcement
Common engagements
"We have a new algorithm. Should we patent?"
- Subject matter eligibility check (§101 — algorithms are tricky)
- Prior art search (someone has probably published)
- Strategic value (does patent enable / defend a business position?)
- Cost-benefit ($5-25K provisional; $30-100K full prosecution)
- Often answer: keep as trade secret, not patent
"Run an FTO before our launch"
- Identify candidate blocking patents (search + competitor review)
- For each: review claims; assess infringement risk
- Identify mitigations: design-around, license, abandon, challenge
- Get formal opinion from patent counsel (insurance against willful infringement)
"Map the patent landscape in our space"
- Identify key players (companies + universities)
- Search by classification + keyword
- Cluster: by company, by sub-technology, by year
- Surface white space (uncovered areas) + crowded zones
- Strategy implications (where to play, where to design-around)
Anti-patterns to avoid
- Searching only keywords (no classification). Misses translations + synonyms.
- Searching only USPTO. EPO + WIPO + JP have unique art.
- Searching only patents. Non-patent prior art is huge.
- Public disclosure before filing. Loses patentability outside US (1-year grace in US only).
- Filing without prior-art search. Reviewer finds it; patent invalid.
- No FTO before product launch. Surprise injunctions.
- Patenting everything. $30K per patent adds up; portfolio bloat distracts.
- Filing without commercial strategy. Patents are means, not ends.
References
references/prior-art-search-strategy.md— search databases, classifications, query patternsreferences/claim-mapping-and-landscape.md— claim analysis, landscape visualizationreferences/freedom-to-operate-and-patentability.md— FTO process, patentability criteria
Related skills
legal/contract-review— IP licensing contractsc-level-advisor/general-counsel-advisor— strategic IP counselresearch/litreview— non-patent literature search overlap
© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (scripts, references) in research/patent of borghei/Claude-Skills.
- SKILL.md
- references/claim-mapping-and-landscape.md
- references/freedom-to-operate-and-patentability.md
- references/prior-art-search-strategy.md
- scripts/claim_landscape_mapper.py
- scripts/patentability_scorer.py
- scripts/prior_art_search_planner.py
Open the folder on GitHubat commit 4a698e8
Compare with similar skills
Patent 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Patent this skillborghei/Claude-Skills | 881 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Paper to Chinese Patent DrafterYuan1z0825/nature-skills | 46k | 1 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper To Cn Patentsnipp-zha/Paper-to-patent-Skill | 105 | 1 repos | ~959 | Automated safety check: Pass | None | |
| Patent Examinegfodor/legal-skills | 393 | — | ~4.8k | Automated safety check: Pass | GPL-3.0 | |
| Patent Auditgfodor/legal-skills | 393 | — | ~2.9k | Automated safety check: Pass | GPL-3.0 | |
| Patent Workaroundgfodor/legal-skills | 393 | — | ~5.7k | Automated safety check: Pass | GPL-3.0 |
Similar skills
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.
Patent Examine
gfodor/legal-skills
Iteratively examine and revise a draft U.S. An agent skill from gfodor/legal-skills.
Patent Audit
gfodor/legal-skills
Audit a draft U.S. An agent skill from gfodor/legal-skills.
Patent Workaround
gfodor/legal-skills
Adversarially pressure-test a draft or pending U.S. An agent skill from gfodor/legal-skills.
Replica Brand
Jakeschincariol/replica-skill
Names and rebrands an app clone so it is the user's own: name candidates with the trademark, domain, store and handle checks to run, a new palette checked for contrast, a logo brief, a voice guide…
More from borghei/Claude-Skills
All 349 skills in this repoAgents In The Team
borghei/Claude-Skills
Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.
AI Content Disclosure
borghei/Claude-Skills
Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.
AI Prototyping
borghei/Claude-Skills
Idea to AI-generated prototype to customer validation to engineering handoff.
Analytics Engineer
borghei/Claude-Skills
Analytics engineering across data modeling, dbt, transformation, and semantic layers.
Ansoff Matrix
borghei/Claude-Skills
Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.
Brainstorm Okrs
borghei/Claude-Skills
OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.
Related
Categories
Questions about Patent
What does Patent do?
Patent research and IP landscape: prior-art search, claim mapping, landscape analysis, and freedom-to-operate. Patent is an agent skill from borghei/Claude-Skills. Patent research and IP landscape: prior-art search, claim mapping, landscape analysis, and freedom-to-operate.
When should I use Patent?
Patent fits situations like: conducting a prior-art search; mapping an IP landscape; evaluating patentability; running an FTO analysis.
How do I install Patent in Claude Code?
Run `npx skills add borghei/Claude-Skills --skill patent -a claude-code`. Or copy the skill folder (research/patent in borghei/Claude-Skills) into .claude/skills/patent in your project. Claude Code loads it when a task matches its description.
How do I install Patent in Codex?
Run `npx skills add borghei/Claude-Skills --skill patent -a codex`. Or copy the skill folder (research/patent in borghei/Claude-Skills) into .agents/skills/patent in your project. Codex loads it when a task matches its description.
Can I use Patent 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 borghei/Claude-Skills --skill patent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/patent, .gemini/skills/patent, .github/skills/patent and .opencode/skills/patent in your project.
What does Patent need to run?
Going by SKILL.md and its folder, Patent needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Patent 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 Patent 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Patent use?
Patent is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Patent use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.4k tokens, read only when the agent opens those files.
What are the alternatives to Patent?
Skills that share tags, products or a category with Patent: Paper to Chinese Patent Drafter (Yuan1z0825/nature-skills, 46k stars), Paper To Cn Patent (snipp-zha/Paper-to-patent-Skill, 105 stars), Patent Examine (gfodor/legal-skills, 393 stars) and Patent Audit (gfodor/legal-skills, 393 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Patent?
borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 881 GitHub stars. The repository holds 349 skills in this directory. The repository was last updated on October 7, 2026.
Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.