[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FD6M6V55F8RF28MCCZA8WW":3,"skill-same:01M7FD6M6V55F8RF28MCCZA8WW":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7FD6M6V55F8RF28MCCZA8WW","patent-pipeline",null,"Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says \"写专利\", \"patent pipeline\", \"专利申请\", \"draft patent\", \"写权利要求书\", or wants to draft a complete patent application.","CZX-LBJ\u002Fdeepseek-science","CZX-LBJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204594689?v=4","01M7FC59WQ9PFXT04MKGJDCFFT","czx","01M7FC59XB2GW0BKWN9JTDBQS7",1,"MIT","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpatent-pipeline\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: patent-pipeline\ndescription: \"Full patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says \\\"写专利\\\", \\\"patent pipeline\\\", \\\"专利申请\\\", \\\"draft patent\\\", \\\"写权利要求书\\\", or wants to draft a complete patent application.\"\nargument-hint: \"[invention-description — jurisdiction]\"\nallowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex\n---\n\n# Patent Pipeline: From Invention to Filing\n\nDraft a complete patent application based on: **$ARGUMENTS**\n\n## Overview\n\nThis skill orchestrates the full patent drafting lifecycle -- from prior art search through jurisdiction-formatted filing documents. It chains sub-skills into a patent-specific pipeline:\n\n```\n\u002Fprior-art-search → \u002Fpatent-novelty-check → \u002Finvention-structuring → \u002Fclaims-drafting → \u002Fspecification-writing → \u002Fpatent-review → \u002Fjurisdiction-format\n     (search)           (verify)              (structure)             (claims)            (description)          (examiner)         (compile)\n                                                                                              ├── \u002Ffigure-description\n                                                                                              └── \u002Fembodiment-description\n```\n\n**This is a parallel branch, not part of the linear research pipeline.** After `\u002Fidea-discovery` produces validated ideas, the user can either:\n- Go to `\u002Fexperiment-bridge` → `\u002Fauto-review-loop` → `\u002Fpaper-writing` (publish track)\n- Go to `\u002Fgrant-proposal` (funding track)\n- Go to `\u002Fpatent-pipeline` (patent track) **\u003C-- this skill**\n\n```\n                    ┌→ \u002Fexperiment-bridge → \u002Fauto-review-loop → \u002Fpaper-writing  (publish track)\n\u002Fidea-discovery ────┤\n                    ├→ \u002Fgrant-proposal → [get funded] → ...  (funding track)\n                    └→ \u002Fpatent-pipeline → [file patent]       (patent track)\n```\n\nPatents are about **protecting inventions** (legal scope), not publishing results (academic contribution). This skill handles the unique requirements of patent drafting: prior art analysis, claims hierarchy design, specification writing with enablement support, embodiment descriptions, and jurisdiction-specific formatting.\n\n## Constants\n\n- **JURISDICTION = `CN`** — Target patent jurisdiction. Options: `CN` (CNIPA), `US` (USPTO), `EP` (EPO), `ALL` (generate all three). Override via argument (e.g., `\u002Fpatent-pipeline \"invention — US\"`).\n- **PATENT_TYPE = `invention`** — `invention` (发明专利, 20 year protection) or `utility_model` (实用新型, CN only, 10 year protection, apparatus claims only). Override via argument.\n- **REVIEWER_MODEL = `gpt-6-astra`** — Model used via Codex MCP for examiner-style review.\n- **MAX_REVIEW_ROUNDS = 2** — Maximum review-revision cycles.\n- **AUTO_PROCEED = false** — At each checkpoint, **always wait for explicit user confirmation**. Patent applications require inventor judgment at every stage. Set `true` only if user explicitly requests autonomous mode.\n- **LANGUAGE = `auto`** — Output language. Auto-detected from jurisdiction: CN->Chinese, US->English, EP->English. Override explicitly if needed.\n- **OUTPUT_DIR = `patent\u002F`** — Directory for generated patent files.\n- **OUTPUT_FORMAT = `markdown`** — Draft format. `markdown` for review, `docx` for filing-ready.\n\n> Override defaults via arguments: `\u002Fpatent-pipeline \"invention — US, utility model\"` or `\u002Fpatent-pipeline \"invention — ALL, language: Chinese\"`.\n\n## Patent Type Specifications\n\n### Invention Patent (发明专利)\n\n| Field | Detail |\n|-------|--------|\n| **Protection** | 20 years from filing date |\n| **Subject matter** | Methods, systems, products, compositions, processes |\n| **Examination** | Substantive examination required |\n| **Inventive step** | High (must involve an inventive step \u002F 创造性) |\n| **Timeline** | 2-4 years to grant (CN); 2-3 years (US); 3-5 years (EP) |\n| **Claims** | Method + system + product claims allowed |\n\n### Utility Model (实用新型) — CN Only\n\n| Field | Detail |\n|-------|--------|\n| **Protection** | 10 years from filing date |\n| **Subject matter** | Product shape, structure, or combination thereof only |\n| **Examination** | Formal examination only (no substantive examination) |\n| **Inventive step** | Lower than invention patent |\n| **Timeline** | 6-8 months to grant |\n| **Claims** | Apparatus\u002Fdevice claims only. NO method claims. |\n| **Restriction** | CN jurisdiction only |\n\n## State Persistence (Compact Recovery)\n\nPatent drafting is a long task that may trigger context compaction. Persist state to `patent\u002FPATENT_STATE.json` after each phase:\n\n```json\n{\n  \"phase\": 3,\n  \"jurisdiction\": \"CN\",\n  \"patent_type\": \"invention\",\n  \"language\": \"Chinese\",\n  \"codex_thread_id\": \"019cfcf4-...\",\n  \"invention_title\": \"...\",\n  \"claims_count\": 15,\n  \"status\": \"in_progress\",\n  \"timestamp\": \"2026-04-10T15:00:00\"\n}\n```\n\n**Write this file at the end of every phase.** On invocation, check for this file:\n- If absent or `status: \"completed\"` -> fresh start\n- If `status: \"in_progress\"` and within 24h -> **resume** from saved phase (read output files to restore context)\n- If older than 24h -> fresh start (stale state)\n\nOn completion, set `\"status\": \"completed\"`.\n\n## Workflow\n\n### Phase 0: Input Parsing & Context Gathering\n\nParse `$ARGUMENTS` to extract:\n\n1. **Invention description** — may be structured (references INVENTION_BRIEF.md), conversational with figures, or output from IDEA_REPORT.md\n2. **Jurisdiction** — detect from keywords (e.g., \"CN\" or \"中国\" -> CN, \"US\" or \"USPTO\" -> US, \"EP\" or \"EPO\" -> EP, \"ALL\")\n3. **Patent type** — detect from keywords (e.g., \"utility model\" or \"实用新型\" -> utility_model, default -> invention)\n4. **Overrides** — language, output format, review rounds\n\nThen gather context from the project directory:\n\n1. Read `INVENTION_BRIEF.md` if it exists (user filled in the template)\n2. Read `IDEA_REPORT.md` if it exists (from `\u002Fidea-discovery` -- can extract invention from research results)\n3. Read `refine-logs\u002FFINAL_PROPOSAL.md` if it exists\n4. Read `NARRATIVE_REPORT.md` if it exists (research results that may be patentable)\n5. Search for user-provided figures (PNG, JPG, SVG, PDF) in the project directory\n6. Check for `patent\u002FPATENT_STATE.json` (resume from prior interrupted run)\n\nIf insufficient context exists:\n- No invention description at all -> suggest user describe the invention or fill in `INVENTION_BRIEF.md`\n- Has IDEA_REPORT.md -> extract patentable aspects from the research\n- Has figures -> reference them in the invention brief\n- No figures -> note that figures will be needed and plan what drawings are required\n\n**If the input is conversational** (not a structured brief), parse the description into the invention brief structure and write `patent\u002FINVENTION_BRIEF.md` for downstream phases.\n\n### Phase 1: Prior Art Search & Novelty Assessment\n\n#### 1.1 Prior Art Search\n\nInvoke `\u002Fprior-art-search`:\n\n```\n\u002Fprior-art-search \"patent\u002FINVENTION_BRIEF.md\"\n```\n\nThis searches patent databases (Google Patents, Espacenet) and academic literature for relevant prior art.\n\n#### 1.2 Novelty Check\n\nInvoke `\u002Fpatent-novelty-check`:\n\n```\n\u002Fpatent-novelty-check \"patent\u002FINVENTION_BRIEF.md\"\n```\n\nThis assesses novelty and non-obviousness against the prior art found in step 1.1.\n\n**🚦 Checkpoint:** Present the prior art landscape and novelty assessment:\n\n```\nPrior art search complete:\n- [X] patent references found\n- [Y] non-patent literature references found\n- Closest prior art: [reference] -- [why it's closest]\n- Novelty assessment: [PATENTABLE \u002F PATENTABLE WITH AMENDMENTS \u002F NOT PATENTABLE]\n- Key risk areas: [list]\n\nReady to proceed with invention structuring?\n```\n\n**⛔ STOP HERE and wait for user response.** Do NOT auto-proceed unless AUTO_PROCEED=true.\n\nOptions:\n- Reply **\"go\"** -> proceed to Phase 2\n- Reply with **adjustments** -> refine the invention scope and re-check novelty\n- Reply **\"stop\"** -> save progress to `patent\u002FDRAFT_NOTES.md`\n\n**State**: Write `PATENT_STATE.json` with `phase: 1`.\n\n### Phase 2: Invention Structuring & Claims Design\n\n#### 2.1 Structure the Invention\n\nInvoke `\u002Finvention-structuring`:\n\n```\n\u002Finvention-structuring \"patent\u002FINVENTION_BRIEF.md\"\n```\n\nThis decomposes the invention into core inventive concept, supporting features, and optional features. Produces `patent\u002FINVENTION_DISCLOSURE.md`.\n\n#### 2.2 Draft Claims\n\nInvoke `\u002Fclaims-drafting`:\n\n```\n\u002Fclaims-drafting \"patent\u002FINVENTION_DISCLOSURE.md\"\n```\n\nThis drafts the claims hierarchy -- the most critical part of the patent. Produces `patent\u002FCLAIMS.md`.\n\n**🚦 Checkpoint:** Present the invention structure and claims:\n\n```\nInvention structured:\n- Core inventive concept: [summary]\n- Claim categories: [method, system, etc.]\n- Claims drafted: [X] independent + [Y] dependent = [Z] total\n- Independent claim 1 (broadest): [first 50 words of claim 1]\n- Examiner review score: [X]\u002F10\n\nThe claims define the legal scope of protection. Please review before proceeding to specification.\n```\n\n**⛔ STOP HERE and wait for user response.** Do NOT auto-proceed unless AUTO_PROCEED=true.\n\nOptions:\n- Reply **\"go\"** -> proceed to Phase 3\n- Reply with **adjustments** (e.g., \"broaden claim 1\", \"add more dependent claims\") -> revise claims\n- Reply **\"stop\"** -> save progress\n\n**State**: Write `PATENT_STATE.json` with `phase: 2`.\n\n### Phase 3: Specification Writing\n\nInvoke `\u002Fspecification-writing`:\n\n```\n\u002Fspecification-writing \"patent\u002FCLAIMS.md\"\n```\n\nThis writes the full specification section by section. Internally invokes `\u002Ffigure-description` (if user-provided figures exist) and `\u002Fembodiment-description` for the detailed description. The specification-writing skill handles figure processing and embodiment writing as sub-skills.\n\n**🚦 Checkpoint:** Present the specification overview:\n\n```\nSpecification written:\n- Title: [title]\n- Sections: Technical Field, Background, Summary, Drawings Description, Detailed Description, Abstract\n- Embodiments: [X]\n- Reference numerals: [Y] components mapped\n- Abstract length: [Z] words (limit: [jurisdiction limit])\n- Claim support: [all elements covered \u002F X elements missing]\n\nReady to proceed to review?\n```\n\n**⛔ STOP HERE and wait for user response.**\n\n**State**: Write `PATENT_STATE.json` with `phase: 3`.\n\n### Phase 4: Patent Review\n\nInvoke `\u002Fpatent-review`:\n\n```\n\u002Fpatent-review \"patent\u002F\"\n```\n\nThis runs 2 rounds of examiner-style review via GPT-6-Astra xhigh. The examiner evaluates clarity, written description, enablement, novelty, non-obviousness, and claim scope.\n\n**State**: Write `PATENT_STATE.json` with `phase: 4` and review score.\n\n### Phase 5: Jurisdiction Formatting & Output\n\nInvoke `\u002Fjurisdiction-format`:\n\n```\n\u002Fjurisdiction-format \"patent\u002F\"\n```\n\nThis compiles the application into the target jurisdiction format(s).\n\n#### Final Deliverables\n\n| Output | Location | Description |\n|--------|----------|-------------|\n| CN: 权利要求书 | `patent\u002Foutput\u002FCN\u002F` | Claims in CNIPA format |\n| CN: 说明书 | `patent\u002Foutput\u002FCN\u002F` | Description in CNIPA format |\n| CN: 说明书摘要 | `patent\u002Foutput\u002FCN\u002F` | Abstract (CN) |\n| US: Claims | `patent\u002Foutput\u002FUS\u002F` | Claims in USPTO format |\n| US: Specification | `patent\u002Foutput\u002FUS\u002F` | Description in USPTO format |\n| US: Abstract | `patent\u002Foutput\u002FUS\u002F` | Abstract (US) |\n| EP: Claims | `patent\u002Foutput\u002FEP\u002F` | Claims in EPO format |\n| EP: Description | `patent\u002Foutput\u002FEP\u002F` | Description in EPO format |\n| EP: Abstract | `patent\u002Foutput\u002FEP\u002F` | Abstract (EP) |\n\n#### Final Report\n\n```markdown\n## Patent Pipeline Complete\n\n### Application Summary\n- Title: [invention title]\n- Jurisdiction: [CN\u002FUS\u002FEP\u002FALL]\n- Patent Type: [Invention \u002F Utility Model]\n- Language: [Chinese\u002FEnglish]\n- Total Claims: [X] independent + [Y] dependent\n\n### Pipeline Scores\n| Phase | Score |\n|-------|-------|\n| Prior Art Search | [completeness assessment] |\n| Novelty Assessment | [PATENTABLE\u002FPATENTABLE WITH AMENDMENTS\u002FNOT PATENTABLE] |\n| Examiner Review Round 1 | [X]\u002F10 |\n| Examiner Review Round 2 | [Y]\u002F10 |\n| Final | [Z]\u002F10 |\n\n### Output Files\n[Table of all generated files with paths]\n\n### Next Steps\n- [ ] Have a patent attorney review the application\n- [ ] Conduct professional prior art search (this tool's search is preliminary)\n- [ ] Prepare formal drawings (if user figures need professional rendering)\n- [ ] File with the patent office\n- [ ] For utility model (CN): formal examination typically takes 6-8 months\n- [ ] For invention patent: substantive examination may take 2-4 years\n```\n\n**State**: Write `PATENT_STATE.json` with `phase: 5, status: \"completed\"`.\n\n## Key Rules\n\n- Never fabricate prior art references, patent numbers, or citations.\n- Claims must be supported by the specification (written description requirement).\n- Each jurisdiction has strict format requirements -- do not mix formats.\n- Utility model (实用新型) applies ONLY to CN jurisdiction and ONLY covers apparatus\u002Fdevice claims.\n- AUTO_PROCEED defaults to false -- patent applications require human review at every phase. Sub-skills inherit this flag: when AUTO_PROCEED=false, sub-skills present results and wait at their own internal checkpoints too.\n- The patent pipeline produces drafts for attorney review, not final filing documents.\n- Large file handling: if a Write operation fails, retry with Bash `cat \u003C\u003C'EOF'` heredoc.\n- Never include experimental results or empirical evaluations in the specification.\n- Consistent terminology is mandatory -- same word for the same concept throughout.\n- If `mcp__codex__codex` is not available (no OpenAI API key), skip external cross-model review and note it in the output. The pipeline must not fail due to missing reviewer access.\n\n## Composing with Other Workflows\n\nThe patent pipeline can start from multiple entry points:\n\n```\nUser describes invention directly ──→ \u002Fpatent-pipeline\n\n\u002Fidea-discovery produces IDEA_REPORT.md ──→ \u002Fpatent-pipeline (extract patentable aspects)\n\n\u002Fresearch-refine produces FINAL_PROPOSAL.md ──→ \u002Fpatent-pipeline (from refined research idea)\n\n\u002Fauto-review-loop produces strong results ──→ \u002Fpatent-pipeline (patent the method)\n```\n\n## Acknowledgements\n\nBuilt on the ARIS (Auto-claude-code-research-in-sleep) skill architecture. Patent writing principles adapted from MPEP (US), CN Patent Examination Guidelines (CN), and EPO Guidelines for Examination (EP).\n","# Patent Pipeline: From Invention to Filing\n\nDraft a complete patent application based on: **$ARGUMENTS**\n\n## Overview\n\nThis skill orchestrates the full patent drafting lifecycle -- from prior art search through jurisdiction-formatted filing documents. It chains sub-skills into a patent-specific pipeline:\n\n```\n\u002Fprior-art-search → \u002Fpatent-novelty-check → \u002Finvention-structuring → \u002Fclaims-drafting → \u002Fspecification-writing → \u002Fpatent-review → \u002Fjurisdiction-format\n     (search)           (verify)              (structure)             (claims)            (description)          (examiner)         (compile)\n                                                                                              ├── \u002Ffigure-description\n                                                                                              └── \u002Fembodiment-description\n```\n\n**This is a parallel branch, not part of the linear research pipeline.** After `\u002Fidea-discovery` produces validated ideas, the user can either:\n- Go to `\u002Fexperiment-bridge` → `\u002Fauto-review-loop` → `\u002Fpaper-writing` (publish track)\n- Go to `\u002Fgrant-proposal` (funding track)\n- Go to `\u002Fpatent-pipeline` (patent track) **\u003C-- this skill**\n\n```\n                    ┌→ \u002Fexperiment-bridge → \u002Fauto-review-loop → \u002Fpaper-writing  (publish track)\n\u002Fidea-discovery ────┤\n                    ├→ \u002Fgrant-proposal → [get funded] → ...  (funding track)\n                    └→ \u002Fpatent-pipeline → [file patent]       (patent track)\n```\n\nPatents are about **protecting inventions** (legal scope), not publishing results (academic contribution). This skill handles the unique requirements of patent drafting: prior art analysis, claims hierarchy design, specification writing with enablement support, embodiment descriptions, and jurisdiction-specific formatting.\n\n## Constants\n\n- **JURISDICTION = `CN`** — Target patent jurisdiction. Options: `CN` (CNIPA), `US` (USPTO), `EP` (EPO), `ALL` (generate all three). Override via argument (e.g., `\u002Fpatent-pipeline \"invention — US\"`).\n- **PATENT_TYPE = `invention`** — `invention` (发明专利, 20 year protection) or `utility_model` (实用新型, CN only, 10 year protection, apparatus claims only). Override via argument.\n- **REVIEWER_MODEL = `gpt-6-astra`** — Model used via Codex MCP for examiner-style review.\n- **MAX_REVIEW_ROUNDS = 2** — Maximum review-revision cycles.\n- **AUTO_PROCEED = false** — At each checkpoint, **always wait for explicit user confirmation**. Patent applications require inventor judgment at every stage. Set `true` only if user explicitly requests autonomous mode.\n- **LANGUAGE = `auto`** — Output language. Auto-detected from jurisdiction: CN->Chinese, US->English, EP->English. Override explicitly if needed.\n- **OUTPUT_DIR = `patent\u002F`** — Directory for generated patent files.\n- **OUTPUT_FORMAT = `markdown`** — Draft format. `markdown` for review, `docx` for filing-ready.\n\n> Override defaults via arguments: `\u002Fpatent-pipeline \"invention — US, utility model\"` or `\u002Fpatent-pipeline \"invention — ALL, language: Chinese\"`.\n\n## Patent Type Specifications\n\n### Invention Patent (发明专利)\n\n| Field | Detail |\n|-------|--------|\n| **Protection** | 20 years from filing date |\n| **Subject matter** | Methods, systems, products, compositions, processes |\n| **Examination** | Substantive examination required |\n| **Inventive step** | High (must involve an inventive step \u002F 创造性) |\n| **Timeline** | 2-4 years to grant (CN); 2-3 years (US); 3-5 years (EP) |\n| **Claims** | Method + system + product claims allowed |\n\n### Utility Model (实用新型) — CN Only\n\n| Field | Detail |\n|-------|--------|\n| **Protection** | 10 years from filing date |\n| **Subject matter** | Product shape, structure, or combination thereof only |\n| **Examination** | Formal examination only (no substantive examination) |\n| **Inventive step** | Lower than invention patent |\n| **Timeline** | 6-8 months to grant |\n| **Claims** | Apparatus\u002Fdevice claims only. NO method claims. |\n| **Restriction** | CN jurisdiction only |\n\n## State Persistence (Compact Recovery)\n\nPatent drafting is a long task that may trigger context compaction. Persist state to `patent\u002FPATENT_STATE.json` after each phase:\n\n```json\n{\n  \"phase\": 3,\n  \"jurisdiction\": \"CN\",\n  \"patent_type\": \"invention\",\n  \"language\": \"Chinese\",\n  \"codex_thread_id\": \"019cfcf4-...\",\n  \"invention_title\": \"...\",\n  \"claims_count\": 15,\n  \"status\": \"in_progress\",\n  \"timestamp\": \"2026-04-10T15:00:00\"\n}\n```\n\n**Write this file at the end of every phase.** On invocation, check for this file:\n- If absent or `status: \"completed\"` -> fresh start\n- If `status: \"in_progress\"` and within 24h -> **resume** from saved phase (read output files to restore context)\n- If older than 24h -> fresh start (stale state)\n\nOn completion, set `\"status\": \"completed\"`.\n\n## Workflow\n\n### Phase 0: Input Parsing & Context Gathering\n\nParse `$ARGUMENTS` to extract:\n\n1. **Invention description** — may be structured (references INVENTION_BRIEF.md), conversational with figures, or output from IDEA_REPORT.md\n2. **Jurisdiction** — detect from keywords (e.g., \"CN\" or \"中国\" -> CN, \"US\" or \"USPTO\" -> US, \"EP\" or \"EPO\" -> EP, \"ALL\")\n3. **Patent type** — detect from keywords (e.g., \"utility model\" or \"实用新型\" -> utility_model, default -> invention)\n4. **Overrides** — language, output format, review rounds\n\nThen gather context from the project directory:\n\n1. Read `INVENTION_BRIEF.md` if it exists (user filled in the template)\n2. Read `IDEA_REPORT.md` if it exists (from `\u002Fidea-discovery` -- can extract invention from research results)\n3. Read `refine-logs\u002FFINAL_PROPOSAL.md` if it exists\n4. Read `NARRATIVE_REPORT.md` if it exists (research results that may be patentable)\n5. Search for user-provided figures (PNG, JPG, SVG, PDF) in the project directory\n6. Check for `patent\u002FPATENT_STATE.json` (resume from prior interrupted run)\n\nIf insufficient context exists:\n- No invention description at all -> suggest user describe the invention or fill in `INVENTION_BRIEF.md`\n- Has IDEA_REPORT.md -> extract patentable aspects from the research\n- Has figures -> reference them in the invention brief\n- No figures -> note that figures will be needed and plan what drawings are required\n\n**If the input is conversational** (not a structured brief), parse the description into the invention brief structure and write `patent\u002FINVENTION_BRIEF.md` for downstream phases.\n\n### Phase 1: Prior Art Search & Novelty Assessment\n\n#### 1.1 Prior Art Search\n\nInvoke `\u002Fprior-art-search`:\n\n```\n\u002Fprior-art-search \"patent\u002FINVENTION_BRIEF.md\"\n```\n\nThis searches patent databases (Google Patents, Espacenet) and academic literature for relevant prior art.\n\n#### 1.2 Novelty Check\n\nInvoke `\u002Fpatent-novelty-check`:\n\n```\n\u002Fpatent-novelty-check \"patent\u002FINVENTION_BRIEF.md\"\n```\n\nThis assesses novelty and non-obviousness against the prior art found in step 1.1.\n\n**🚦 Checkpoint:** Present the prior art landscape and novelty assessment:\n\n```\nPrior art search complete:\n- [X] patent references found\n- [Y] non-patent literature references found\n- Closest prior art: [reference] -- [why it's closest]\n- Novelty assessment: [PATENTABLE \u002F PATENTABLE WITH AMENDMENTS \u002F NOT PATENTABLE]\n- Key risk areas: [list]\n\nReady to proceed with invention structuring?\n```\n\n**⛔ STOP HERE and wait for user response.** Do NOT auto-proceed unless AUTO_PROCEED=true.\n\nOptions:\n- Reply **\"go\"** -> proceed to Phase 2\n- Reply with **adjustments** -> refine the invention scope and re-check novelty\n- Reply **\"stop\"** -> save progress to `patent\u002FDRAFT_NOTES.md`\n\n**State**: Write `PATENT_STATE.json` with `phase: 1`.\n\n### Phase 2: Invention Structuring & Claims Design\n\n#### 2.1 Structure the Invention\n\nInvoke `\u002Finvention-structuring`:\n\n```\n\u002Finvention-structuring \"patent\u002FINVENTION_BRIEF.md\"\n```\n\nThis decomposes the invention into core inventive concept, supporting features, and optional features. Produces `patent\u002FINVENTION_DISCLOSURE.md`.\n\n#### 2.2 Draft Claims\n\nInvoke `\u002Fclaims-drafting`:\n\n```\n\u002Fclaims-drafting \"patent\u002FINVENTION_DISCLOSURE.md\"\n```\n\nThis drafts the claims hierarchy -- the most critical part of the patent. Produces `patent\u002FCLAIMS.md`.\n\n**🚦 Checkpoint:** Present the invention structure and claims:\n\n```\nInvention structured:\n- Core inventive concept: [summary]\n- Claim categories: [method, system, etc.]\n- Claims drafted: [X] independent + [Y] dependent = [Z] total\n- Independent claim 1 (broadest): [first 50 words of claim 1]\n- Examiner review score: [X]\u002F10\n\nThe claims define the legal scope of protection. Please review before proceeding to specification.\n```\n\n**⛔ STOP HERE and wait for user response.** Do NOT auto-proceed unless AUTO_PROCEED=true.\n\nOptions:\n- Reply **\"go\"** -> proceed to Phase 3\n- Reply with **adjustments** (e.g., \"broaden claim 1\", \"add more dependent claims\") -> revise claims\n- Reply **\"stop\"** -> save progress\n\n**State**: Write `PATENT_STATE.json` with `phase: 2`.\n\n### Phase 3: Specification Writing\n\nInvoke `\u002Fspecification-writing`:\n\n```\n\u002Fspecification-writing \"patent\u002FCLAIMS.md\"\n```\n\nThis writes the full specification section by section. Internally invokes `\u002Ffigure-description` (if user-provided figures exist) and `\u002Fembodiment-description` for the detailed description. The specification-writing skill handles figure processing and embodiment writing as sub-skills.\n\n**🚦 Checkpoint:** Present the specification overview:\n\n```\nSpecification written:\n- Title: [title]\n- Sections: Technical Field, Background, Summary, Drawings Description, Detailed Description, Abstract\n- Embodiments: [X]\n- Reference numerals: [Y] components mapped\n- Abstract length: [Z] words (limit: [jurisdiction limit])\n- Claim support: [all elements covered \u002F X elements missing]\n\nReady to proceed to review?\n```\n\n**⛔ STOP HERE and wait for user response.**\n\n**State**: Write `PATENT_STATE.json` with `phase: 3`.\n\n### Phase 4: Patent Review\n\nInvoke `\u002Fpatent-review`:\n\n```\n\u002Fpatent-review \"patent\u002F\"\n```\n\nThis runs 2 rounds of examiner-style review via GPT-6-Astra xhigh. The examiner evaluates clarity, written description, enablement, novelty, non-obviousness, and claim scope.\n\n**State**: Write `PATENT_STATE.json` with `phase: 4` and review score.\n\n### Phase 5: Jurisdiction Formatting & Output\n\nInvoke `\u002Fjurisdiction-format`:\n\n```\n\u002Fjurisdiction-format \"patent\u002F\"\n```\n\nThis compiles the application into the target jurisdiction format(s).\n\n#### Final Deliverables\n\n| Output | Location | Description |\n|--------|----------|-------------|\n| CN: 权利要求书 | `patent\u002Foutput\u002FCN\u002F` | Claims in CNIPA format |\n| CN: 说明书 | `patent\u002Foutput\u002FCN\u002F` | Description in CNIPA format |\n| CN: 说明书摘要 | `patent\u002Foutput\u002FCN\u002F` | Abstract (CN) |\n| US: Claims | `patent\u002Foutput\u002FUS\u002F` | Claims in USPTO format |\n| US: Specification | `patent\u002Foutput\u002FUS\u002F` | Description in USPTO format |\n| US: Abstract | `patent\u002Foutput\u002FUS\u002F` | Abstract (US) |\n| EP: Claims | `patent\u002Foutput\u002FEP\u002F` | Claims in EPO format |\n| EP: Description | `patent\u002Foutput\u002FEP\u002F` | Description in EPO format |\n| EP: Abstract | `patent\u002Foutput\u002FEP\u002F` | Abstract (EP) |\n\n#### Final Report\n\n```markdown\n## Patent Pipeline Complete\n\n### Application Summary\n- Title: [invention title]\n- Jurisdiction: [CN\u002FUS\u002FEP\u002FALL]\n- Patent Type: [Invention \u002F Utility Model]\n- Language: [Chinese\u002FEnglish]\n- Total Claims: [X] independent + [Y] dependent\n\n### Pipeline Scores\n| Phase | Score |\n|-------|-------|\n| Prior Art Search | [completeness assessment] |\n| Novelty Assessment | [PATENTABLE\u002FPATENTABLE WITH AMENDMENTS\u002FNOT PATENTABLE] |\n| Examiner Review Round 1 | [X]\u002F10 |\n| Examiner Review Round 2 | [Y]\u002F10 |\n| Final | [Z]\u002F10 |\n\n### Output Files\n[Table of all generated files with paths]\n\n### Next Steps\n- [ ] Have a patent attorney review the application\n- [ ] Conduct professional prior art search (this tool's search is preliminary)\n- [ ] Prepare formal drawings (if user figures need professional rendering)\n- [ ] File with the patent office\n- [ ] For utility model (CN): formal examination typically takes 6-8 months\n- [ ] For invention patent: substantive examination may take 2-4 years\n```\n\n**State**: Write `PATENT_STATE.json` with `phase: 5, status: \"completed\"`.\n\n## Key Rules\n\n- Never fabricate prior art references, patent numbers, or citations.\n- Claims must be supported by the specification (written description requirement).\n- Each jurisdiction has strict format requirements -- do not mix formats.\n- Utility model (实用新型) applies ONLY to CN jurisdiction and ONLY covers apparatus\u002Fdevice claims.\n- AUTO_PROCEED defaults to false -- patent applications require human review at every phase. Sub-skills inherit this flag: when AUTO_PROCEED=false, sub-skills present results and wait at their own internal checkpoints too.\n- The patent pipeline produces drafts for attorney review, not final filing documents.\n- Large file handling: if a Write operation fails, retry with Bash `cat \u003C\u003C'EOF'` heredoc.\n- Never include experimental results or empirical evaluations in the specification.\n- Consistent terminology is mandatory -- same word for the same concept throughout.\n- If `mcp__codex__codex` is not available (no OpenAI API key), skip external cross-model review and note it in the output. The pipeline must not fail due to missing reviewer access.\n\n## Composing with Other Workflows\n\nThe patent pipeline can start from multiple entry points:\n\n```\nUser describes invention directly ──→ \u002Fpatent-pipeline\n\n\u002Fidea-discovery produces IDEA_REPORT.md ──→ \u002Fpatent-pipeline (extract patentable aspects)\n\n\u002Fresearch-refine produces FINAL_PROPOSAL.md ──→ \u002Fpatent-pipeline (from refined research idea)\n\n\u002Fauto-review-loop produces strong results ──→ \u002Fpatent-pipeline (patent the method)\n```\n\n## Acknowledgements\n\nBuilt on the ARIS (Auto-claude-code-research-in-sleep) skill architecture. Patent writing principles adapted from MPEP (US), CN Patent Examination Guidelines (CN), and EPO Guidelines for Examination (EP).\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Skill, mcp__codex__codex","[invention-description — jurisdiction]","main","18193d71ea3441d7c033dbf195b8a7c75ac96f75","packages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpatent-pipeline",0,"https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science","https:\u002F\u002Fgithub.com\u002FCZX-LBJ","一个没事喜欢随便写点代码的小菜鸡\r\n","2026-10-22 09:48:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add CZX-LBJ\u002Fdeepseek-science --skill patent-pipeline",{"tool":40,"command":41},"bunx","bunx skills add CZX-LBJ\u002Fdeepseek-science --skill patent-pipeline",{"tool":43,"command":44},"pnpm","pnpm dlx skills add CZX-LBJ\u002Fdeepseek-science --skill patent-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fpatent-pipeline\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7FEEKSNMRMKW6JEK93PFDFY","bio-free-energy-calculations","Performs alchemical free-energy calculations including relative binding free energy (RBFE \u002F FEP+) and absolute binding free energy (ABFE) via OpenFE, FEP+, GROMACS, AMBER pmemd, and OpenMM with explicit lambda scheduling, soft-core potentials, MBAR\u002FBAR analysis, cycle-closure validation, and protocol-appropriate enhanced sampling. Compares ML alternatives (Boltz-2 affinity, DeepDock). Use when ranking analogs by binding affinity beyond docking accuracy, performing prospective lead optimization, or validating SAR predictions.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Ffree-energy-calculations\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FEE5CTE5QK55CEMXNNVWY9","bio-conformer-generation","Generates 3D conformer ensembles using RDKit ETKDGv3 with knowledge-enhanced distance geometry, MMFF94\u002FUFF force-field optimization, CREST + GFN2-xTB semi-empirical refinement, and macrocycle-aware torsion preferences. Provides explicit decision rules for single vs ensemble conformer use, RMSD pruning, energy windows, conformer count, and force-field choice. Use when preparing 3D ligands for docking, generating descriptor input for 3D QSAR, or sampling macrocycle\u002Fpeptide conformational ensembles.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fconformer-generation\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FEDNGFEMFWD1MSEDR5H7CY","bio-admet-prediction","Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG\u002FCYP\u002FAMES endpoints, and PAINS \u002F Lipinski \u002F Ro5 \u002F Veber \u002F BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Fbioskills\u002Fchemoinformatics\u002Fadmet-prediction\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FED69GFB54FRF7AV5066DN","writing-systems-papers","Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says \"写系统论文\", \"systems paper structure\", \"OSDI paper\", \"SOSP paper\", or wants fine-grained structural guidance for a systems conference submission.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwriting-systems-papers\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FECVVDWZ0X0VEDTCE4B4DZ","wiki-enrich","Fill in the per-paper TODO sections of research-wiki\u002Fpapers\u002F\u003Cslug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers\u002F as TODO scaffolds.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fwiki-enrich\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FECD4BCJ2MTSBDDSE3ZAJ5","web-debug-search","Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-world workarounds. Use for debugging and discovery only; results are not paper-citation evidence.","https:\u002F\u002Fgithub.com\u002FCZX-LBJ\u002Fdeepseek-science\u002Fblob\u002Fmain\u002Fpackages\u002Fskill\u002Fskill-science\u002Fassets\u002Fsources\u002Faris\u002Fskills\u002Fweb-debug-search\u002FSKILL.md",[],[]]