[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MMA0V9KSAAM7FXWH73G6NC":3,"skill-same:01M6MMA0V9KSAAM7FXWH73G6NC":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":28,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":13,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6MMA0V9KSAAM7FXWH73G6NC","patent",null,"Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search \u002F freedom-to-operate \u002F competitive landscape \u002F acquisition diligence \u002F litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-research-patent-skills-patent-skill-d17fc8f7\u002FSKILL.md",[17,22,25],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"log","variant","for","editable","invention","competitive","audit log","full","family","document","docx","use","strategy","decisions","Rules","text","commits","search","google","2026-11-10 10:12:30",false,"---\nname: patent\ndescription: \"Patent prior-art and landscape intelligence skill — not generic patent help. Commits to one of five sub-use-cases via forcing intake (novelty search \u002F freedom-to-operate \u002F competitive landscape \u002F acquisition diligence \u002F litigation prior-art) before any search runs. Searches Google Patents, Espacenet, USPTO, and optionally Lens.org for citation-graph signals. Output is an editable Word document (.docx) with verdict, ranked closest art (claim-text extracted), CPC-class-aware landscape, family-resolved hits, geographic coverage, FTO flags where applicable, strategy recommendations, and full audit log. Use when the user asks for patent searching or analysis (e.g., 'prior art search for [invention]', 'freedom to operate analysis for [product]'). Produces search signal, not legal advice — always recommends consulting a patent attorney before filing or licensing decisions. Trademark, copyright, and trade-secret questions are out of scope.\"\nlicense: MIT\nmetadata:\n  source_spec: \"megaprompts\u002F11-patent-megaprompt.md\"\n  build_pattern: \"Path B (direct conversion)\"\n  research_pack_convention: \"Agent Integrity Rules verbatim per PR #657 audit; sub-use-case routing variant\"\n  version: 1.0.0\n---\n\n# Patent — Prior-Art + Landscape Intelligence\n\n> **Portability:** Requires `web_fetch` (Google Patents, Espacenet, USPTO), `WebSearch` (adjacent academic art), Node.js with `docx` package, and optionally Lens.org API key for citation-graph signals. Works in Claude Code CLI natively. In Claude.ai with web tools + Code Execution + BYOK Lens.org, the workflow is supported.\n\n> **Out of scope:** trademark, copyright, trade-secret. These are flagged at intake. Use a different skill or qualified counsel.\n\n> **Legal disclaimer:** This skill produces search signal, not legal advice. Verdicts are technical assessments. **Always consult a patent attorney before filing or licensing decisions.**\n\n## Non-Generic Framing — The Differentiator\n\nThis skill is **prior-art + landscape intelligence**. It **refuses to be a bucket**. Every invocation commits to one of five sub-use-cases via the grill-me intake before any search runs. The chosen sub-use-case dictates the entire search strategy, ranking heuristics, and DOCX emphasis.\n\n| Sub-use-case | Search strategy | DOCX emphasis |\n|---|---|---|\n| **Novelty search** | Narrow + claims-text focused; pre-filing date irrelevant | Closest art + claim-differentiation |\n| **Freedom-to-operate** | Broad + active patents only; jurisdiction-filtered | FTO flags + claim-by-claim risk |\n| **Competitive landscape** | Breadth + filer tally + CPC trends | Filer map + investment hotspots |\n| **Acquisition diligence** | Specific assignee + portfolio scope + assignment chain | Portfolio table + ownership verification |\n| **Litigation prior-art** | Specific target patent + adjacent art before priority date | Knock-out candidates ranked by relevance |\n\nSee [`references\u002Fsub_use_case_routing.md`](references\u002Fsub_use_case_routing.md) for the canon.\n\n## Agent Integrity Rules (Research-Pack Convention)\n\nLocked verbatim per PR #657 audit.\n\n- **Execution discipline.** Sequential search calls only. **1 query\u002Fsec rate limit.** Confirm response received before next call.\n- **Source discipline.** Cite only patents returned by THIS session's tool calls. Training knowledge labeled `[Not from search — reference information]` and excluded from counts.\n- **Three-count tracking.** Queries sent \u002F patents received (shown) \u002F patents cited. Surfaced in audit log.\n- **Retry policy.** On failure → wait 3s → retry once → log. After 3 consecutive failures across tools: stop, alert user, explain what's missing.\n- **Plan-tier detection.** Lens.org free tier = 1000 queries\u002Fmonth. Google Patents has no auth but rate-limits per IP. Detect and surface caps.\n\n## Phase 1: Grill-Me Intake (6 forcing questions, one at a time)\n\n### Q1 (root) — Invention description\n\n> **Describe the invention in 2–3 sentences. What does it do, and what's new about it?**\n>\n> *Why I'm asking:* Concept and keyword extraction depends entirely on a precise description. Vague descriptions (\"AI for healthcare\", \"a better widget\") will be rejected — push back and ask the user to specify what the invention does and what differentiates it from existing approaches.\n\n**Refuse mush.** If answer is generic, ask once more: \"What does it do that existing systems don't?\" Then commit (with caveat in DOCX).\n\n### Q2 (depends on Q1) — Sub-use-case commitment\n\n> **What's the purpose of this search? Pick one:**\n>\n> 1. Novelty search (am I novel enough to file)\n> 2. Freedom-to-operate (will I get sued if I ship)\n> 3. Competitive landscape (who else plays here)\n> 4. Acquisition diligence (does target really own X)\n> 5. Litigation prior-art hunting (kill a specific patent)\n>\n> *Why I'm asking:* Each path uses a fundamentally different search strategy. I'll **refuse to start without you picking one**.\n\nForcing format. If user says \"all of them\", push for the primary purpose — secondary purposes can run as follow-up searches.\n\n### Q3 (asked only if Q2 ∈ {FTO, landscape, diligence}) — Jurisdictions\n\n> **Which jurisdictions matter? Pick all that apply: US \u002F EP \u002F CN \u002F JP \u002F KR \u002F PCT \u002F worldwide.**\n>\n> *Why I'm asking:* FTO only matters where you'll sell. Landscape changes radically by region. Diligence requires checking all jurisdictions where the target operates.\n\nSkip for novelty (priority date is jurisdictionally portable) and litigation (jurisdiction is set by the target patent).\n\n### Q4 (depends on Q1) — Known prior art\n\n> **Have you already seen prior art close to this? Cite a patent number or paper.**\n>\n> *Why I'm asking:* If you know one piece of art, I can search adjacent to it — much more precise than starting cold. If you don't, that's fine — just confirm.\n\nAnchoring. Accept \"none\" but ask if the user has seen *any* related work even informally.\n\n### Q5 (depends on Q2) — Risk tolerance\n\n> **Risk tolerance for this search: strict (one close hit means abandon the path) or signal-gathering (you want the lay of the land regardless)?**\n>\n> *Why I'm asking:* Strict mode ranks aggressively and surfaces verdict-grade hits; signal mode prioritizes breadth and visualizations.\n\nAsked for novelty and FTO; skipped for pure landscape (always signal-gathering by definition).\n\n### Q6 (asked only if Q2 ∈ {novelty, FTO}) — Attorney status\n\n> **Have you spoken to a patent attorney? This skill produces search signal, not legal advice. Confirm you understand this is for technical assessment only.**\n>\n> *Why I'm asking:* Novelty and FTO have legal consequences. The skill's verdict is signal-grade; legal positions require qualified counsel.\n\n**Triggers the legal-disclaimer footer in the DOCX.** Skipped for landscape and diligence (lower legal exposure).\n\n**Stop condition:** After Q6 (or earlier if dependency skips applied), commit and start Phase 2. Never re-open intake after Phase 2 begins.\n\n## Phase 2: Search Strategy Selection\n\nDeterministic from intake answers. Use `scripts\u002Fsub_use_case_router.py`:\n\n```bash\npython scripts\u002Fsub_use_case_router.py \\\n  --sub-use-case novelty \\\n  --jurisdictions \"\" \\\n  --risk strict \\\n  --known-art \"US10000000B2\"\n```\n\nReturns: query plan (5-8 queries) + ranking heuristic + DOCX emphasis flags.\n\n## Phase 3: Multi-Source Search (Sequential)\n\n### Source priority\n\n1. **Google Patents** (https:\u002F\u002Fpatents.google.com) — workhorse, no auth required, broad coverage\n2. **Espacenet** (https:\u002F\u002Fworldwide.espacenet.com) — global coverage, good for non-US art\n3. **USPTO PPS** (https:\u002F\u002Fppubs.uspto.gov) — US deep dive\n4. **Lens.org** (https:\u002F\u002Fwww.lens.org) — citation graph, BYOK API key required\n\n### Per-sub-use-case query patterns\n\n**Novelty:**\n- 3 narrow queries on invention-specific terminology (Google Patents)\n- 2 broad concept queries with synonyms (Google Patents + Espacenet)\n- 1 CPC-class-restricted query if class identified from initial hits\n\n**FTO:**\n- Jurisdiction-filtered: only active patents (not expired, not abandoned)\n- Date filter: priority \u003C today\n- Active-claim text extraction for each hit\n\n**Competitive landscape:**\n- Broader queries on the technology space\n- CPC class identification → tally top filers in that class\n- 10-year filing trend by year per top-5 filer\n\n**Acquisition diligence:**\n- Specific assignee searches (target company + subsidiaries + named inventors)\n- Assignment chain check (USPTO assignment recordation)\n- Family resolution for deduplication\n\n**Litigation prior-art:**\n- Target patent input required (number)\n- Priority date extraction\n- Search for art before priority date in same CPC classes\n- Adjacent-claim-language search\n\n### Sequential discipline\n\n1 q\u002Fsec across ALL sources combined. Tracked via `scripts\u002Fcitation_tracker.py` with timestamp-enforced gap.\n\n## Phase 4: Claim Extraction + Relevance Scoring\n\nFor each closest-art hit:\n- Pull **independent claim 1** (the broadest claim — primary anticipation\u002Fobviousness vehicle)\n- Pull **key dependent claims** (claims that add the inventive step)\n- Score relevance against invention description (overlap of claim language with Q1 terminology)\n\nRank by score. Verdict per sub-use-case (NOVEL \u002F POTENTIALLY NOVEL \u002F NOT NOVEL for novelty; CLEAR \u002F FLAGGED \u002F HIGH RISK per jurisdiction for FTO).\n\n## Phase 5: Citation Graph + Family Resolution\n\n### Citation graph (Lens.org BYOK)\n\nIf user provides Lens.org API key:\n- Foundational-patent identification (cited-by count > threshold, typically 50+)\n- Recent high-cite signals (citations in last 24 months as proxy for current activity)\n- Forward citations from target patent (litigation prior-art) or from closest art (novelty)\n\nIf no Lens.org key: skip; note in audit log; recommend manual citation review on Google Patents.\n\n### Family resolution\n\nSame invention often filed in multiple jurisdictions (US + EP + JP + CN). Group by family ID or priority number to avoid double-counting. Use `scripts\u002Ffamily_resolver.py`:\n\n```bash\npython scripts\u002Ffamily_resolver.py --hits-file hits.json\n# Returns: deduplicated family list + family-member jurisdictions\n```\n\n## CPC\u002FIPC Classification Awareness\n\n**Critical:** keyword search alone misses adjacent art. After initial search, extract the CPC\u002FIPC classes from top 5 hits and run **one class-restricted query**. This consistently surfaces art that keyword search misses.\n\nSee [`references\u002Fcpc_classification_canon.md`](references\u002Fcpc_classification_canon.md) for the canon.\n\n## Phase 6: DOCX Generation (8 Sections)\n\nSub-use-case-dependent emphasis. Via Node.js + `docx` library.\n\n1. **Executive Summary + Verdict** — Sub-use-case banner + one-line verdict (NOVEL \u002F FLAGGED \u002F etc.) + 3-4 key findings + legal disclaimer footer\n2. **Closest Prior Art** — 5-10 patents in ranked order. Per hit: hyperlinked title + assignee + filing\u002Fpriority dates + independent claim 1 text (italicized) + relevance score + relevance rationale (1-2 sentences)\n3. **Patent Landscape** — Top filers table (top 10 by count) + 10-year filing trend description + CPC class distribution table. Only for landscape and diligence; abbreviated otherwise.\n4. **Citation Graph Signals** — Foundational patents (if Lens-enabled) + recent high-cite activity. If Lens unavailable, note \"manual review recommended\" and skip table.\n5. **Geographic Coverage** — Filings by jurisdiction for top 10 hits. Only for FTO, landscape, diligence; skipped for novelty and litigation.\n6. **FTO Flags** (FTO only) — Active patents posing infringement risk. Per flag: hyperlinked patent + jurisdiction + relevant claims + risk level (HIGH\u002FMEDIUM\u002FLOW) + mitigation note.\n7. **Strategy + Recommendations** — Sub-use-case-specific:\n   - Novelty → claim differentiation suggestions\n   - FTO → design-around hints + jurisdiction strategy\n   - Landscape → who-to-watch list\n   - Diligence → red flags in portfolio\n   - Litigation → ranked knock-out candidates\n   - **Mandatory disclaimer to consult patent attorney** for any filing\u002Flicensing decision.\n8. **Audit Log** — Searches table (#, query, source, results, status), counts (sent\u002Fshown\u002Fcited), tool constraints (plan-tier notes), failed steps, attorney-consultation reminder\n\n### Styling\n\nArial 12pt body, navy headings (#1a3a5c), light blue table headers (#e8f0f8), red FTO-flag callout. `ExternalHyperlink` patterns:\n- Google Patents: `https:\u002F\u002Fpatents.google.com\u002Fpatent\u002F[number]`\n- Espacenet: `https:\u002F\u002Fworldwide.espacenet.com\u002Fpatent\u002F...`\n- USPTO: `https:\u002F\u002Fpatents.uspto.gov\u002Fpatent\u002F...`\n\n## Date Discipline\n\nDistinguish at every hit:\n- **Filing date** — when the application was first submitted\n- **Priority date** — earliest claim of priority (often earlier than filing)\n- **Publication date** — when the application became public (typically 18 months after priority)\n- **Grant date** — when the patent was granted (later than publication)\n\nSurface the **legally-relevant date** per sub-use-case:\n- Novelty → priority date (vs invention's anticipated filing date)\n- FTO → grant date + status (active vs expired)\n- Landscape → publication date (when public knowledge began)\n- Diligence → grant date + assignment date\n- Litigation → priority date of target patent (sets the prior-art cutoff)\n\n## Phase 7: Deliver\n\n- Save: `\u003Coutput-dir>\u002Fpatent_\u003Cinvention-slug>_\u003Csub-use-case>_\u003CYYYY-MM-DD>.docx`\n- Chat summary: file path + sub-use-case + verdict + audit counts + plan-tier\n- Validate: check zip integrity with `python3 -c \"import zipfile,sys; zipfile.ZipFile(sys.argv[1]).testzip()\" \u003Cdocx>` (no output = intact), then confirm the required sections are present\n- Reminder: \"Consult patent attorney before filing\u002Flicensing\"\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fcitation_tracker.py` | Multi-source three-count audit (Google Patents + Espacenet + USPTO + Lens.org) at `~\u002F.patent_sessions\u002F\u003Csession>.json` |\n| `scripts\u002Ffamily_resolver.py` | Group same-invention filings across jurisdictions by family ID \u002F priority number |\n| `scripts\u002Fsub_use_case_router.py` | Deterministic search-strategy selection from intake answers |\n\n## References\n\n- [`references\u002Fsub_use_case_routing.md`](references\u002Fsub_use_case_routing.md) — 5-sub-use-case canon (7+ sources)\n- [`references\u002Fcpc_classification_canon.md`](references\u002Fcpc_classification_canon.md) — CPC\u002FIPC class follow-up rationale (7+ sources)\n- [`references\u002Flegal_disclaimer_discipline.md`](references\u002Flegal_disclaimer_discipline.md) — when + why disclaimer mandatory (7+ sources)\n\n## Error Handling\n\n| Failure | Behavior |\n|---|---|\n| User refuses to commit to sub-use-case | Refuse to proceed. Re-ask Q2 with examples. |\n| Invention description is generic | Reject answer. Re-ask Q1 with \"what does it do that existing systems don't?\" |\n| Google Patents rate-limits | Wait 3s, retry once. Fall back to Espacenet for that query. Log in audit. |\n| Lens.org key missing | Skip citation graph section, note \"manual review recommended\" in DOCX. |\n| Claim text extraction fails | Fall back to abstract; flag as \"abstract-only\" in relevance rationale. |\n| Family resolution incomplete | Note in audit; same-invention duplicates may appear; suggest manual deduplication. |\n| All searches return \u003C3 hits | Surface explicitly as \"either niche art or genuine gap\"; never fabricate. |\n| 3 consecutive tool failures | Stop, alert user, explain what's missing. |\n| DOCX generation fails | Save raw data as JSON fallback so user doesn't lose work. |\n| Target patent number invalid (litigation) | Validate format before search; ask user to confirm. |\n\n## Anti-Patterns To Reject\n\n- Starting any search before user commits to a sub-use-case (refuses generic \"patent help\")\n- Batching all intake questions instead of one at a time\n- Accepting vague invention descriptions (\"AI for healthcare\")\n- Keyword-only search without CPC\u002FIPC class follow-up\n- Treating family members as separate hits (must be deduplicated)\n- Confusing filing date with priority date with publication date\n- Skipping the legal disclaimer when sub-use-case has legal consequences\n- Reporting a verdict without claim-text evidence\n- Fabricating Lens.org citation data when key is absent\n- Suggesting design-arounds without acknowledging attorney review is required\n- Skipping the audit log\n\n---\n\n**Version:** 1.0.0\n**Source spec:** `megaprompts\u002F11-patent-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)\n**Build pattern:** Path B (direct conversion). Research-pack sibling, sub-use-case routing variant.\n","# Patent — Prior-Art + Landscape Intelligence\n\n> **Portability:** Requires `web_fetch` (Google Patents, Espacenet, USPTO), `WebSearch` (adjacent academic art), Node.js with `docx` package, and optionally Lens.org API key for citation-graph signals. Works in Claude Code CLI natively. In Claude.ai with web tools + Code Execution + BYOK Lens.org, the workflow is supported.\n\n> **Out of scope:** trademark, copyright, trade-secret. These are flagged at intake. Use a different skill or qualified counsel.\n\n> **Legal disclaimer:** This skill produces search signal, not legal advice. Verdicts are technical assessments. **Always consult a patent attorney before filing or licensing decisions.**\n\n## Non-Generic Framing — The Differentiator\n\nThis skill is **prior-art + landscape intelligence**. It **refuses to be a bucket**. Every invocation commits to one of five sub-use-cases via the grill-me intake before any search runs. The chosen sub-use-case dictates the entire search strategy, ranking heuristics, and DOCX emphasis.\n\n| Sub-use-case | Search strategy | DOCX emphasis |\n|---|---|---|\n| **Novelty search** | Narrow + claims-text focused; pre-filing date irrelevant | Closest art + claim-differentiation |\n| **Freedom-to-operate** | Broad + active patents only; jurisdiction-filtered | FTO flags + claim-by-claim risk |\n| **Competitive landscape** | Breadth + filer tally + CPC trends | Filer map + investment hotspots |\n| **Acquisition diligence** | Specific assignee + portfolio scope + assignment chain | Portfolio table + ownership verification |\n| **Litigation prior-art** | Specific target patent + adjacent art before priority date | Knock-out candidates ranked by relevance |\n\nSee [`references\u002Fsub_use_case_routing.md`](references\u002Fsub_use_case_routing.md) for the canon.\n\n## Agent Integrity Rules (Research-Pack Convention)\n\nLocked verbatim per PR #657 audit.\n\n- **Execution discipline.** Sequential search calls only. **1 query\u002Fsec rate limit.** Confirm response received before next call.\n- **Source discipline.** Cite only patents returned by THIS session's tool calls. Training knowledge labeled `[Not from search — reference information]` and excluded from counts.\n- **Three-count tracking.** Queries sent \u002F patents received (shown) \u002F patents cited. Surfaced in audit log.\n- **Retry policy.** On failure → wait 3s → retry once → log. After 3 consecutive failures across tools: stop, alert user, explain what's missing.\n- **Plan-tier detection.** Lens.org free tier = 1000 queries\u002Fmonth. Google Patents has no auth but rate-limits per IP. Detect and surface caps.\n\n## Phase 1: Grill-Me Intake (6 forcing questions, one at a time)\n\n### Q1 (root) — Invention description\n\n> **Describe the invention in 2–3 sentences. What does it do, and what's new about it?**\n>\n> *Why I'm asking:* Concept and keyword extraction depends entirely on a precise description. Vague descriptions (\"AI for healthcare\", \"a better widget\") will be rejected — push back and ask the user to specify what the invention does and what differentiates it from existing approaches.\n\n**Refuse mush.** If answer is generic, ask once more: \"What does it do that existing systems don't?\" Then commit (with caveat in DOCX).\n\n### Q2 (depends on Q1) — Sub-use-case commitment\n\n> **What's the purpose of this search? Pick one:**\n>\n> 1. Novelty search (am I novel enough to file)\n> 2. Freedom-to-operate (will I get sued if I ship)\n> 3. Competitive landscape (who else plays here)\n> 4. Acquisition diligence (does target really own X)\n> 5. Litigation prior-art hunting (kill a specific patent)\n>\n> *Why I'm asking:* Each path uses a fundamentally different search strategy. I'll **refuse to start without you picking one**.\n\nForcing format. If user says \"all of them\", push for the primary purpose — secondary purposes can run as follow-up searches.\n\n### Q3 (asked only if Q2 ∈ {FTO, landscape, diligence}) — Jurisdictions\n\n> **Which jurisdictions matter? Pick all that apply: US \u002F EP \u002F CN \u002F JP \u002F KR \u002F PCT \u002F worldwide.**\n>\n> *Why I'm asking:* FTO only matters where you'll sell. Landscape changes radically by region. Diligence requires checking all jurisdictions where the target operates.\n\nSkip for novelty (priority date is jurisdictionally portable) and litigation (jurisdiction is set by the target patent).\n\n### Q4 (depends on Q1) — Known prior art\n\n> **Have you already seen prior art close to this? Cite a patent number or paper.**\n>\n> *Why I'm asking:* If you know one piece of art, I can search adjacent to it — much more precise than starting cold. If you don't, that's fine — just confirm.\n\nAnchoring. Accept \"none\" but ask if the user has seen *any* related work even informally.\n\n### Q5 (depends on Q2) — Risk tolerance\n\n> **Risk tolerance for this search: strict (one close hit means abandon the path) or signal-gathering (you want the lay of the land regardless)?**\n>\n> *Why I'm asking:* Strict mode ranks aggressively and surfaces verdict-grade hits; signal mode prioritizes breadth and visualizations.\n\nAsked for novelty and FTO; skipped for pure landscape (always signal-gathering by definition).\n\n### Q6 (asked only if Q2 ∈ {novelty, FTO}) — Attorney status\n\n> **Have you spoken to a patent attorney? This skill produces search signal, not legal advice. Confirm you understand this is for technical assessment only.**\n>\n> *Why I'm asking:* Novelty and FTO have legal consequences. The skill's verdict is signal-grade; legal positions require qualified counsel.\n\n**Triggers the legal-disclaimer footer in the DOCX.** Skipped for landscape and diligence (lower legal exposure).\n\n**Stop condition:** After Q6 (or earlier if dependency skips applied), commit and start Phase 2. Never re-open intake after Phase 2 begins.\n\n## Phase 2: Search Strategy Selection\n\nDeterministic from intake answers. Use `scripts\u002Fsub_use_case_router.py`:\n\n```bash\npython scripts\u002Fsub_use_case_router.py \\\n  --sub-use-case novelty \\\n  --jurisdictions \"\" \\\n  --risk strict \\\n  --known-art \"US10000000B2\"\n```\n\nReturns: query plan (5-8 queries) + ranking heuristic + DOCX emphasis flags.\n\n## Phase 3: Multi-Source Search (Sequential)\n\n### Source priority\n\n1. **Google Patents** (https:\u002F\u002Fpatents.google.com) — workhorse, no auth required, broad coverage\n2. **Espacenet** (https:\u002F\u002Fworldwide.espacenet.com) — global coverage, good for non-US art\n3. **USPTO PPS** (https:\u002F\u002Fppubs.uspto.gov) — US deep dive\n4. **Lens.org** (https:\u002F\u002Fwww.lens.org) — citation graph, BYOK API key required\n\n### Per-sub-use-case query patterns\n\n**Novelty:**\n- 3 narrow queries on invention-specific terminology (Google Patents)\n- 2 broad concept queries with synonyms (Google Patents + Espacenet)\n- 1 CPC-class-restricted query if class identified from initial hits\n\n**FTO:**\n- Jurisdiction-filtered: only active patents (not expired, not abandoned)\n- Date filter: priority \u003C today\n- Active-claim text extraction for each hit\n\n**Competitive landscape:**\n- Broader queries on the technology space\n- CPC class identification → tally top filers in that class\n- 10-year filing trend by year per top-5 filer\n\n**Acquisition diligence:**\n- Specific assignee searches (target company + subsidiaries + named inventors)\n- Assignment chain check (USPTO assignment recordation)\n- Family resolution for deduplication\n\n**Litigation prior-art:**\n- Target patent input required (number)\n- Priority date extraction\n- Search for art before priority date in same CPC classes\n- Adjacent-claim-language search\n\n### Sequential discipline\n\n1 q\u002Fsec across ALL sources combined. Tracked via `scripts\u002Fcitation_tracker.py` with timestamp-enforced gap.\n\n## Phase 4: Claim Extraction + Relevance Scoring\n\nFor each closest-art hit:\n- Pull **independent claim 1** (the broadest claim — primary anticipation\u002Fobviousness vehicle)\n- Pull **key dependent claims** (claims that add the inventive step)\n- Score relevance against invention description (overlap of claim language with Q1 terminology)\n\nRank by score. Verdict per sub-use-case (NOVEL \u002F POTENTIALLY NOVEL \u002F NOT NOVEL for novelty; CLEAR \u002F FLAGGED \u002F HIGH RISK per jurisdiction for FTO).\n\n## Phase 5: Citation Graph + Family Resolution\n\n### Citation graph (Lens.org BYOK)\n\nIf user provides Lens.org API key:\n- Foundational-patent identification (cited-by count > threshold, typically 50+)\n- Recent high-cite signals (citations in last 24 months as proxy for current activity)\n- Forward citations from target patent (litigation prior-art) or from closest art (novelty)\n\nIf no Lens.org key: skip; note in audit log; recommend manual citation review on Google Patents.\n\n### Family resolution\n\nSame invention often filed in multiple jurisdictions (US + EP + JP + CN). Group by family ID or priority number to avoid double-counting. Use `scripts\u002Ffamily_resolver.py`:\n\n```bash\npython scripts\u002Ffamily_resolver.py --hits-file hits.json\n# Returns: deduplicated family list + family-member jurisdictions\n```\n\n## CPC\u002FIPC Classification Awareness\n\n**Critical:** keyword search alone misses adjacent art. After initial search, extract the CPC\u002FIPC classes from top 5 hits and run **one class-restricted query**. This consistently surfaces art that keyword search misses.\n\nSee [`references\u002Fcpc_classification_canon.md`](references\u002Fcpc_classification_canon.md) for the canon.\n\n## Phase 6: DOCX Generation (8 Sections)\n\nSub-use-case-dependent emphasis. Via Node.js + `docx` library.\n\n1. **Executive Summary + Verdict** — Sub-use-case banner + one-line verdict (NOVEL \u002F FLAGGED \u002F etc.) + 3-4 key findings + legal disclaimer footer\n2. **Closest Prior Art** — 5-10 patents in ranked order. Per hit: hyperlinked title + assignee + filing\u002Fpriority dates + independent claim 1 text (italicized) + relevance score + relevance rationale (1-2 sentences)\n3. **Patent Landscape** — Top filers table (top 10 by count) + 10-year filing trend description + CPC class distribution table. Only for landscape and diligence; abbreviated otherwise.\n4. **Citation Graph Signals** — Foundational patents (if Lens-enabled) + recent high-cite activity. If Lens unavailable, note \"manual review recommended\" and skip table.\n5. **Geographic Coverage** — Filings by jurisdiction for top 10 hits. Only for FTO, landscape, diligence; skipped for novelty and litigation.\n6. **FTO Flags** (FTO only) — Active patents posing infringement risk. Per flag: hyperlinked patent + jurisdiction + relevant claims + risk level (HIGH\u002FMEDIUM\u002FLOW) + mitigation note.\n7. **Strategy + Recommendations** — Sub-use-case-specific:\n   - Novelty → claim differentiation suggestions\n   - FTO → design-around hints + jurisdiction strategy\n   - Landscape → who-to-watch list\n   - Diligence → red flags in portfolio\n   - Litigation → ranked knock-out candidates\n   - **Mandatory disclaimer to consult patent attorney** for any filing\u002Flicensing decision.\n8. **Audit Log** — Searches table (#, query, source, results, status), counts (sent\u002Fshown\u002Fcited), tool constraints (plan-tier notes), failed steps, attorney-consultation reminder\n\n### Styling\n\nArial 12pt body, navy headings (#1a3a5c), light blue table headers (#e8f0f8), red FTO-flag callout. `ExternalHyperlink` patterns:\n- Google Patents: `https:\u002F\u002Fpatents.google.com\u002Fpatent\u002F[number]`\n- Espacenet: `https:\u002F\u002Fworldwide.espacenet.com\u002Fpatent\u002F...`\n- USPTO: `https:\u002F\u002Fpatents.uspto.gov\u002Fpatent\u002F...`\n\n## Date Discipline\n\nDistinguish at every hit:\n- **Filing date** — when the application was first submitted\n- **Priority date** — earliest claim of priority (often earlier than filing)\n- **Publication date** — when the application became public (typically 18 months after priority)\n- **Grant date** — when the patent was granted (later than publication)\n\nSurface the **legally-relevant date** per sub-use-case:\n- Novelty → priority date (vs invention's anticipated filing date)\n- FTO → grant date + status (active vs expired)\n- Landscape → publication date (when public knowledge began)\n- Diligence → grant date + assignment date\n- Litigation → priority date of target patent (sets the prior-art cutoff)\n\n## Phase 7: Deliver\n\n- Save: `\u003Coutput-dir>\u002Fpatent_\u003Cinvention-slug>_\u003Csub-use-case>_\u003CYYYY-MM-DD>.docx`\n- Chat summary: file path + sub-use-case + verdict + audit counts + plan-tier\n- Validate: check zip integrity with `python3 -c \"import zipfile,sys; zipfile.ZipFile(sys.argv[1]).testzip()\" \u003Cdocx>` (no output = intact), then confirm the required sections are present\n- Reminder: \"Consult patent attorney before filing\u002Flicensing\"\n\n## Tooling\n\n| Script | Role |\n|---|---|\n| `scripts\u002Fcitation_tracker.py` | Multi-source three-count audit (Google Patents + Espacenet + USPTO + Lens.org) at `~\u002F.patent_sessions\u002F\u003Csession>.json` |\n| `scripts\u002Ffamily_resolver.py` | Group same-invention filings across jurisdictions by family ID \u002F priority number |\n| `scripts\u002Fsub_use_case_router.py` | Deterministic search-strategy selection from intake answers |\n\n## References\n\n- [`references\u002Fsub_use_case_routing.md`](references\u002Fsub_use_case_routing.md) — 5-sub-use-case canon (7+ sources)\n- [`references\u002Fcpc_classification_canon.md`](references\u002Fcpc_classification_canon.md) — CPC\u002FIPC class follow-up rationale (7+ sources)\n- [`references\u002Flegal_disclaimer_discipline.md`](references\u002Flegal_disclaimer_discipline.md) — when + why disclaimer mandatory (7+ sources)\n\n## Error Handling\n\n| Failure | Behavior |\n|---|---|\n| User refuses to commit to sub-use-case | Refuse to proceed. Re-ask Q2 with examples. |\n| Invention description is generic | Reject answer. Re-ask Q1 with \"what does it do that existing systems don't?\" |\n| Google Patents rate-limits | Wait 3s, retry once. Fall back to Espacenet for that query. Log in audit. |\n| Lens.org key missing | Skip citation graph section, note \"manual review recommended\" in DOCX. |\n| Claim text extraction fails | Fall back to abstract; flag as \"abstract-only\" in relevance rationale. |\n| Family resolution incomplete | Note in audit; same-invention duplicates may appear; suggest manual deduplication. |\n| All searches return \u003C3 hits | Surface explicitly as \"either niche art or genuine gap\"; never fabricate. |\n| 3 consecutive tool failures | Stop, alert user, explain what's missing. |\n| DOCX generation fails | Save raw data as JSON fallback so user doesn't lose work. |\n| Target patent number invalid (litigation) | Validate format before search; ask user to confirm. |\n\n## Anti-Patterns To Reject\n\n- Starting any search before user commits to a sub-use-case (refuses generic \"patent help\")\n- Batching all intake questions instead of one at a time\n- Accepting vague invention descriptions (\"AI for healthcare\")\n- Keyword-only search without CPC\u002FIPC class follow-up\n- Treating family members as separate hits (must be deduplicated)\n- Confusing filing date with priority date with publication date\n- Skipping the legal disclaimer when sub-use-case has legal consequences\n- Reporting a verdict without claim-text evidence\n- Fabricating Lens.org citation data when key is absent\n- Suggesting design-arounds without acknowledging attorney review is required\n- Skipping the audit log\n\n---\n\n**Version:** 1.0.0\n**Source spec:** `megaprompts\u002F11-patent-megaprompt.md` (maintainer-local draft spec — gitignored, not present in the public repository)\n**Build pattern:** Path B (direct conversion). Research-pack sibling, sub-use-case routing variant.\n",{"name":5,"license":14,"metadata":53,"description":7},{"version":54,"source_spec":55,"build_pattern":56,"research_pack_convention":57},"1.0.0","megaprompts\u002F11-patent-megaprompt.md","Path B (direct conversion)","Agent Integrity Rules verbatim per PR #657 audit; sub-use-case routing variant","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-research-patent-skills-patent-skill-d17fc8f7","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill patent",{"tool":70,"command":71},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill patent",{"tool":73,"command":74},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill patent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-research-patent-skills-patent-skill-d17fc8f7\u002FSKILL.md",true,[],[79,103,131,160,188,222],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":48},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[81,86,87,88,89,90,91,92,93,94,95,96,97,40,98,99,100,101,31,102],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","ready","unrelated","app","scope","webmcp",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":107,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":48},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"vardoger analyze","analyze","directory","cli","github copilot","copilot","run","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":141,"publishedAt":48},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[137,140],{"categoryNo":138,"categoryName":139,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":26,"categoryName":27,"taxonomyType":20,"taxonomyTypeDesc":21},[142,143,144,145,146,147,148,149,150,151,152,153,154,40,155,156,157,158,31,159],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":169,"publishedAt":48},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[166],{"categoryNo":167,"categoryName":168,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[170,171,172,173,174,175,176,177,178,40,179,180,181,182,183,184,185,186,187,31],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":205,"publishedAt":48},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[194,197,202],{"categoryNo":195,"categoryName":196,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":198,"categoryName":199,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":203,"categoryName":204,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000038","人力资源",[46,206,207,208,209,210,211,212,112,213,40,214,215,216,217,218,219,220,31,221],"Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":48},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[229,230,231,232,233,208,234,40,218,235,236,237,238,239,240,241,242,243,31,244],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]