[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78F1ASF95ZXDTCPC96DJ1PP":3,"skill-same:01M78F1ASF95ZXDTCPC96DJ1PP":51},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M78F1ASF95ZXDTCPC96DJ1PP","recipe-invention-disclosure",null,"Prosecution recipe for turning an inventor conversation into a complete invention disclosure form (IDF) — structured technical capture, bar-date audit, novelty pre-check across patents and literature, landscape context, and a filing recommendation. Trigger when the user asks to document an invention, create an invention disclosure, or run a pre-filing novelty sanity check.","flowleap-ai\u002Fflowleap-plugins","flowleap-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F308447201?v=4","01M78EW41SDYP0XH04G056G4GS","01M78EW42W8DAJJK73C3Z95PEA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fflowleap\u002Fskills\u002Frecipe-invention-disclosure\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: recipe-invention-disclosure\ndescription: Prosecution recipe for turning an inventor conversation into a complete invention disclosure form (IDF) — structured technical capture, bar-date audit, novelty pre-check across patents and literature, landscape context, and a filing recommendation. Trigger when the user asks to document an invention, create an invention disclosure, or run a pre-filing novelty sanity check.\nmetadata:\n  requires:\n    skills: [\"flowleap-shared\", \"flowleap-patent\", \"flowleap-academic\", \"flowleap-npl\"]\n---\n\n# Recipe: Invention Disclosure (IDF)\n\nCapture an invention completely enough that an attorney can draft from it.\n\nIn a chat client with the FlowLeap connector or in the FlowLeap Patent AI app, call the tools named in the `flowleap-shared` tool table instead of these commands, and never run a `flowleap` command there. The steps stay the same.\n\n## Step 1: Structured Capture\n\nInterview for these sections (push past marketing language to mechanisms):\n\n1. **Problem** — what fails today, and why existing approaches fall short\n2. **Prior approaches** — what the inventors know exists, including their own\n   earlier work\n3. **The inventive concept** — the mechanism of the solution, not the benefit\n4. **Key elements** — minimum set needed for the invention to work\n5. **Variations** — alternative embodiments, ranges, materials, algorithms\n6. **Evidence** — prototypes, test data, figures\n7. **People and dates** — inventors and contribution; conception date;\n   **any public disclosure, sale, offer, or publication with dates** (bar\n   dates differ by jurisdiction — flag anything older than 12 months)\n\n## Step 2: Novelty Pre-Check\n\nWrite the queries yourself from the Step 1 capture — the \"key elements\" list\nis your term extraction. Keep the phrases that discriminate (the mechanism,\nnot the benefit), probe the count, then search both offices (method in\n`flowleap-patent`; the disclosure never has to leave the machine to become a\nquery):\n\n```bash\nflowleap --json tools run search_patents query='\u003Cself-written CQL>' range=1-1 details=false\nflowleap --json patent search --query \"\u003Cself-written CQL>\" --limit 20\nflowleap --json uspto search --query \"\u003Cself-written ODP Lucene>\" --limit 20   # title + metadata only\n\n# Literature — inventors' own field publishes here first\nflowleap --json academic search \"\u003Cconcept keywords>\" --limit 15\nflowleap --json npl \"\u003Cconcept keywords>\" --limit 10\n```\n\nFor anything close, pull claims and record how the invention differs:\n\n```bash\nflowleap --json ops claims \u003Cclose-patent>\n```\n\nThis is a sanity check, not a professional prior-art search — say so in the IDF.\n\n## Step 3: Landscape Context\n\n```bash\nflowleap --json analytics --keyword \"\u003Ctechnology>\" --date-from 2018-01-01\n```\n\nFiling trends and top assignees tell the reviewer whether this space is\ncrowded, growing, or abandoned — context for the filing decision.\n\n## Step 4: Assemble the IDF\n\nSections: title; inventors + contributions; problem; prior approaches\n(including Step 2 findings with the differences recorded); detailed\ndescription of the inventive concept; key elements; variations; evidence;\ndisclosure\u002Fbar-date audit; landscape summary.\n\n## Step 5: Recommendation\n\nClose with one of: **file now** (novelty check clean, bar clock running),\n**develop further** (concept not yet enabled), or **defensive publication**\n(crowded space, low claim scope) — with the reasoning.\n\n## Output\n\nA complete IDF document plus the raw novelty pre-check data (queries used,\nhits reviewed, differences noted) as an appendix.\n","# Recipe: Invention Disclosure (IDF)\n\nCapture an invention completely enough that an attorney can draft from it.\n\nIn a chat client with the FlowLeap connector or in the FlowLeap Patent AI app, call the tools named in the `flowleap-shared` tool table instead of these commands, and never run a `flowleap` command there. The steps stay the same.\n\n## Step 1: Structured Capture\n\nInterview for these sections (push past marketing language to mechanisms):\n\n1. **Problem** — what fails today, and why existing approaches fall short\n2. **Prior approaches** — what the inventors know exists, including their own\n   earlier work\n3. **The inventive concept** — the mechanism of the solution, not the benefit\n4. **Key elements** — minimum set needed for the invention to work\n5. **Variations** — alternative embodiments, ranges, materials, algorithms\n6. **Evidence** — prototypes, test data, figures\n7. **People and dates** — inventors and contribution; conception date;\n   **any public disclosure, sale, offer, or publication with dates** (bar\n   dates differ by jurisdiction — flag anything older than 12 months)\n\n## Step 2: Novelty Pre-Check\n\nWrite the queries yourself from the Step 1 capture — the \"key elements\" list\nis your term extraction. Keep the phrases that discriminate (the mechanism,\nnot the benefit), probe the count, then search both offices (method in\n`flowleap-patent`; the disclosure never has to leave the machine to become a\nquery):\n\n```bash\nflowleap --json tools run search_patents query='\u003Cself-written CQL>' range=1-1 details=false\nflowleap --json patent search --query \"\u003Cself-written CQL>\" --limit 20\nflowleap --json uspto search --query \"\u003Cself-written ODP Lucene>\" --limit 20   # title + metadata only\n\n# Literature — inventors' own field publishes here first\nflowleap --json academic search \"\u003Cconcept keywords>\" --limit 15\nflowleap --json npl \"\u003Cconcept keywords>\" --limit 10\n```\n\nFor anything close, pull claims and record how the invention differs:\n\n```bash\nflowleap --json ops claims \u003Cclose-patent>\n```\n\nThis is a sanity check, not a professional prior-art search — say so in the IDF.\n\n## Step 3: Landscape Context\n\n```bash\nflowleap --json analytics --keyword \"\u003Ctechnology>\" --date-from 2018-01-01\n```\n\nFiling trends and top assignees tell the reviewer whether this space is\ncrowded, growing, or abandoned — context for the filing decision.\n\n## Step 4: Assemble the IDF\n\nSections: title; inventors + contributions; problem; prior approaches\n(including Step 2 findings with the differences recorded); detailed\ndescription of the inventive concept; key elements; variations; evidence;\ndisclosure\u002Fbar-date audit; landscape summary.\n\n## Step 5: Recommendation\n\nClose with one of: **file now** (novelty check clean, bar clock running),\n**develop further** (concept not yet enabled), or **defensive publication**\n(crowded space, low claim scope) — with the reasoning.\n\n## Output\n\nA complete IDF document plus the raw novelty pre-check data (queries used,\nhits reviewed, differences noted) as an appendix.\n",{"name":5,"metadata":23,"description":7},{"requires":24},{"skills":25},[26,27,28,29],"flowleap-shared","flowleap-patent","flowleap-academic","flowleap-npl","main","83ea326400c9270816882fce38d9a026bd78d023","plugins\u002Fflowleap\u002Fskills\u002Frecipe-invention-disclosure",0,"https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins","https:\u002F\u002Fgithub.com\u002Fflowleap-ai","2026-11-03 00:32:37",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add flowleap-ai\u002Fflowleap-plugins --skill recipe-invention-disclosure",{"tool":43,"command":44},"bunx","bunx skills add flowleap-ai\u002Fflowleap-plugins --skill recipe-invention-disclosure",{"tool":46,"command":47},"pnpm","pnpm dlx skills add flowleap-ai\u002Fflowleap-plugins --skill recipe-invention-disclosure","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fflowleap\u002Fskills\u002Frecipe-invention-disclosure\u002FSKILL.md",true,[],[52,59,65,72,79,85],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M78F35H37QQZ9YPMHPRFTV1H","totally-different-name","This skill's frontmatter name does not match its folder 'baz-skill' and must be rejected.","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Finvalid-skill-name-mismatch\u002Fplugins\u002Fbaz\u002Fskills\u002Fbaz-skill\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M78F32ETQQ73XTJ0QQ2RTDPT","bar-skill","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Finvalid-skill-missing-description\u002Fplugins\u002Fbar\u002Fskills\u002Fbar-skill\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M78F2Z98DYP2PV9Q3ATDRAAA","qux-skill","A valid skill in a plugin whose README is too short.","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Finvalid-plugin-readme-short\u002Fplugins\u002Fqux\u002Fskills\u002Fqux-skill\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M78F2WEH2WYVZMMW8MHFQ8GN","grault-skill","A valid skill in a plugin whose .mcp.json server is broken.","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Finvalid-mcp-server-url-scheme\u002Fplugins\u002Fgrault\u002Fskills\u002Fgrault-skill\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M78F2SY7AVXS8SM6Z33584XZ","corge-skill","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Finvalid-mcp-server-no-endpoint\u002Fplugins\u002Fcorge\u002Fskills\u002Fcorge-skill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M78F2R4APKHKDNW8MBK8M93D","quux-skill","A valid skill in a plugin whose .mcp.json is malformed.","https:\u002F\u002Fgithub.com\u002Fflowleap-ai\u002Fflowleap-plugins\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Finvalid-mcp-json\u002Fplugins\u002Fquux\u002Fskills\u002Fquux-skill\u002FSKILL.md",[],[]]