patent-drafter
A full patent specification drafting pipeline. An agent team collaborates to generate prior art search, claims, specification, and drawing descriptions in a single pass. Use this skill for contexts such as 'write a patent specification', 'patent application', 'invention patent', 'draft claims', 'prior art search', 'patent draft', 'patent specification draft', 'convert invention report to patent', 'turn an idea into a patent', and other patent specification drafting tasks. Note: Actual patent office filing, patent examination responses (opinion statements/amendments), patent litigation, and international filing (PCT/Paris Convention) practice are outside the scope of this skill.
Best use case
patent-drafter is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
A full patent specification drafting pipeline. An agent team collaborates to generate prior art search, claims, specification, and drawing descriptions in a single pass. Use this skill for contexts such as 'write a patent specification', 'patent application', 'invention patent', 'draft claims', 'prior art search', 'patent draft', 'patent specification draft', 'convert invention report to patent', 'turn an idea into a patent', and other patent specification drafting tasks. Note: Actual patent office filing, patent examination responses (opinion statements/amendments), patent litigation, and international filing (PCT/Paris Convention) practice are outside the scope of this skill.
Teams using patent-drafter should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/patent-drafter/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How patent-drafter Compares
| Feature / Agent | patent-drafter | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
A full patent specification drafting pipeline. An agent team collaborates to generate prior art search, claims, specification, and drawing descriptions in a single pass. Use this skill for contexts such as 'write a patent specification', 'patent application', 'invention patent', 'draft claims', 'prior art search', 'patent draft', 'patent specification draft', 'convert invention report to patent', 'turn an idea into a patent', and other patent specification drafting tasks. Note: Actual patent office filing, patent examination responses (opinion statements/amendments), patent litigation, and international filing (PCT/Paris Convention) practice are outside the scope of this skill.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Patent Drafter — Patent Specification Drafting Pipeline
Converts an invention's technical idea into a systematic patent specification set.
## Execution Mode
**Agent Team** — 5 agents communicate directly via SendMessage and cross-verify each other's work.
## Agent Composition
| Agent | File | Role | Type |
|-------|------|------|------|
| prior-art-researcher | `.claude/agents/prior-art-researcher.md` | Prior art search, novelty/inventive step analysis | general-purpose |
| claim-drafter | `.claude/agents/claim-drafter.md` | Independent/dependent claim drafting, claim scope design | general-purpose |
| specification-writer | `.claude/agents/specification-writer.md` | Detailed description of invention, embodiment writing | general-purpose |
| drawing-designer | `.claude/agents/drawing-designer.md` | Drawing composition, reference numeral descriptions | general-purpose |
| patent-reviewer | `.claude/agents/patent-reviewer.md` | Consistency cross-verification, description deficiency check | general-purpose |
## Workflow
### Phase 1: Preparation (Performed Directly by Orchestrator)
1. Extract from user input:
- **Title of Invention**: Technical title
- **Technical Field**: The field to which the invention belongs
- **Invention Overview**: Core technical concept, components, operating principles
- **Problem to be Solved**: Problems with existing technology and the problem to be solved
- **Existing Materials** (optional): Invention report, technical documents, prototype information
2. Create the `_workspace/` directory in the project root
3. Organize the input and save to `_workspace/00_input.md`
4. Determine the **execution mode** based on the requested scope
### Phase 2: Team Assembly and Execution
| Order | Task | Owner | Dependencies | Output |
|-------|------|-------|-------------|--------|
| 1 | Prior Art Search | prior-art-researcher | None | `_workspace/01_prior_art_report.md` |
| 2 | Claim Drafting | claim-drafter | Task 1 | `_workspace/02_claims.md` |
| 3a | Specification Writing | specification-writer | Tasks 1, 2 | `_workspace/03_specification.md` |
| 3b | Drawing Design | drawing-designer | Task 2 | `_workspace/04_drawings.md` |
| 4 | Patent Review | patent-reviewer | Tasks 1, 2, 3a, 3b | `_workspace/05_review_report.md` |
Tasks 3a (Specification) and 3b (Drawing) are executed **in parallel**. Both depend on claims, so they can start simultaneously after Task 2 is complete. However, both sides communicate for reference numeral coordination.
**Inter-agent Communication Flow:**
- prior-art-researcher completes -> Delivers differentiation points and design-around direction to claim-drafter
- claim-drafter completes -> Delivers elements and terms to specification-writer, structure to drawing-designer
- specification-writer <-> drawing-designer: Mutual coordination of reference numeral system
- patent-reviewer cross-verifies all deliverables. If Red must-fix items found, requests revision from relevant agent (up to 2 times)
### Phase 3: Integration and Final Deliverables
1. Review all files in `_workspace/`
2. Verify that all Red must-fix items from the review report have been addressed
3. Report the final summary to the user:
- Prior Art Search Report — `01_prior_art_report.md`
- Claim Set — `02_claims.md`
- Detailed Description of Invention — `03_specification.md`
- Drawing Description — `04_drawings.md`
- Review Report — `05_review_report.md`
## Modes by Request Scope
| User Request Pattern | Execution Mode | Agents Deployed |
|---------------------|----------------|-----------------|
| "Write the full patent specification" | **Full Pipeline** | All 5 agents |
| "Just search prior art" | **Search Mode** | prior-art-researcher only |
| "Just draft claims" | **Claims Mode** | claim-drafter + reviewer |
| "Write spec from these claims" (existing claims) | **Specification Mode** | specification-writer + drawing-designer + reviewer |
| "Review this specification" | **Review Mode** | patent-reviewer only |
## Data Transfer Protocol
| Strategy | Method | Purpose |
|----------|--------|---------|
| File-based | `_workspace/` directory | Storing and sharing main deliverables |
| Message-based | SendMessage | Real-time delivery of key info, numeral coordination, revision requests |
File naming convention: `{order}_{agent}_{deliverable}.{extension}`
## Error Handling
| Error Type | Strategy |
|-----------|----------|
| Web search failure | Prior art researcher works based on general knowledge, notes "DB search not performed" |
| Insufficient invention info | Request additional info from user, draft with minimum information |
| Agent failure | Retry once -> if failed, proceed without that deliverable, note omission in review report |
| Red items found in review | Request revision from relevant agent -> rework -> re-verify (up to 2 times) |
| Reference numeral mismatch | drawing-designer and specification-writer mutually coordinate |
## Test Scenarios
### Normal Flow
**Prompt**: "Write a patent specification for an IoT-based smart flowerpot automatic watering system. It measures with a soil moisture sensor and AI adjusts the watering amount based on plant type."
**Expected Results**:
- Prior Art Search: 5+ prior patents related to IoT watering systems and smart flowerpots
- Claims: Apparatus independent claim + method independent claim + 5+ dependent claims
- Specification: Complete structure from technical field through embodiments
- Drawings: System block diagram + detailed structure diagram + flowchart
- Review: All consistency matrix items verified
### Partial Flow
**Prompt**: "Just search prior art for this invention idea"
**Expected Results**:
- Switches to search mode (prior-art-researcher only)
- Prior art list + in-depth analysis + novelty/inventive step assessment
### Error Flow
**Prompt**: "Write a patent specification, the idea is new battery technology"
**Expected Results**:
- Full pipeline execution, additional questions due to insufficient invention details
- When drafting with minimum info, many items marked "inventor verification needed"
- Review report includes "recommend rewriting after supplementing detailed information"
## Agent Extension Skills
| Agent | Extension Skill | Purpose |
|-------|----------------|---------|
| claim-drafter, patent-reviewer | `claim-drafting-patterns` | Claim drafting patterns, claim scope design strategy |
| prior-art-researcher | `prior-art-search-strategy` | Prior art search strategy, novelty/inventive step analysis framework |Related Skills
patent-valuation
Patent valuation framework. Referenced by the ip-analyst and license-strategist agents when calculating the economic value of IP assets. Use for 'patent value', 'IP valuation', or 'royalty calculation' requests. Legal patent infringement assessment and litigation representation are out of scope.
sustainability-audit
Full audit pipeline for ESG/sustainability where an agent team collaborates to generate environmental, social, and governance assessments along with an integrated report and improvement plan. Use this skill for requests such as 'run an ESG audit', 'write a sustainability report', 'ESG assessment', 'carbon emissions calculation', 'ESG rating diagnosis', 'governance review', 'social responsibility assessment', 'GRI report', 'TCFD disclosure', 'ESG improvement plan', and other ESG/sustainability tasks. Also supports assessment of specific pillars (E/S/G) only or improving existing reports. However, actual on-site audit execution, third-party verification certificate issuance, ESG rating agency score changes, and carbon credit trading are outside the scope of this skill.
materiality-assessment
ESG materiality assessment matrix. Referenced by the esg-reporter and improvement-planner agents when evaluating ESG issue materiality and setting priorities. Use for 'materiality assessment', 'importance analysis', or 'Materiality Matrix' requests. Stakeholder surveys and external certification are out of scope.
ghg-protocol
GHG Protocol detailed guide. Referenced by the environmental-analyst agent when calculating and reporting greenhouse gas emissions. Use for 'GHG Protocol', 'carbon emissions', 'Scope 1/2/3', or 'carbon footprint' requests. Carbon credit trading and CDM project execution are out of scope.
citation-standards
Academic citation and reference standards guide. Referenced by the paper-writer and submission-preparer agents when composing citations and references. Use for 'citation format', 'APA', or 'references' requests. Original paper retrieval and professional database access are out of scope.
academic-paper
Full research pipeline for academic paper writing where an agent team collaborates to generate research design, experiment protocols, analysis, manuscript writing, and submission preparation. Use this skill for requests such as 'write an academic paper', 'research paper writing', 'help me write a paper', 'design a study', 'run statistical analysis', 'prepare journal submission', 'manuscript writing', 'research methodology design', 'hypothesis testing', 'academic writing', and other academic research paper tasks. Also supports analysis, rewriting, and submission preparation when existing data or drafts are available. However, actual data collection execution, official IRB submission, journal system login and upload, and running actual statistical software are outside the scope of this skill.
product-copy-formulas
Product copy formula library. Referenced by the detail-page-writer and marketing-manager agents when writing purchase-driving copy. Use for 'product copy', 'marketing copy', or 'ad copy' requests. Ad placement and design mockup creation are out of scope.
ecommerce-launcher
Full launch pipeline for e-commerce products where an agent team collaborates to generate product planning, detail pages, pricing strategy, marketing, and CS setup all at once. Use this skill for requests such as 'launch an e-commerce product', 'prepare a product launch', 'register a product on Naver Smart Store', 'launch on Coupang', 'create a detail page', 'develop a pricing strategy', 'create a marketing plan', 'launch prep', 'product planning brief', 'e-commerce CS manual', and other e-commerce product launch tasks. Also supports supplementing pricing/marketing/CS even when existing briefs or detail pages are provided. However, actual platform API integration (automated product registration), payment system development, logistics system integration, and real-time order management are outside the scope of this skill.
conversion-optimization
Purchase conversion optimization framework. Referenced by the detail-page-writer and pricing-strategist agents when designing detail pages and pricing with a conversion focus. Use for 'conversion rate optimization', 'CRO', or 'purchase psychology' requests. A/B testing tool setup and funnel automation are out of scope.
real-estate-analyst
Real estate investment analysis pipeline. An agent team collaborates to produce market research, location analysis, profitability analysis, risk assessment, and investment reports. Use this skill for requests such as 'analyze this real estate', 'apartment investment analysis', 'studio apartment yield', 'real estate market research', 'location analysis', 'real estate investment report', 'buy vs lease', 'reconstruction investment analysis', 'commercial property yield analysis', and other general real estate investment analysis tasks. Actual purchase contracts, brokerage services, interior design, and property management are outside the scope of this skill.
location-scoring
Location scoring scorecard. Referenced by the location-analyst agent for systematic real estate location evaluation. Use for requests involving 'location analysis', 'location assessment', or 'commercial area analysis'. On-site inspections and surveying are out of scope.
cap-rate-calculator
Real estate yield calculator. Reference formulas and models used by the profitability-analyst agent for quantitative investment return analysis. Use for requests involving 'Cap Rate', 'yield analysis', 'DCF', or 'cash flow analysis'. Tax advisory and loan underwriting are out of scope.