[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A3FD2Q4MTCSHGZPS8XYV7C":3,"skill-same:01M7A3FD2Q4MTCSHGZPS8XYV7C":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7A3FD2Q4MTCSHGZPS8XYV7C","prior-art-scan",null,"Search patents, papers and preprints together to see whether an idea is already known. Use when a team asks if their invention is novel, before filing, before committing engineering effort to an approach, or when preparing to meet a patent attorney.","LNdme\u002FSUniv","LNdme","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F224572198?v=4","01M7A3DPMXT60BVWPK0X7PMGCZ","01M7A3DPNJRTKYPJVQNHNCWE0W",1,"MIT","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fdeploy\u002Flayers\u002Fsuniv\u002Fsandbox\u002Fskills\u002Fprior-art-scan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prior-art-scan\ndescription: Search patents, papers and preprints together to see whether an idea is already known. Use when a team asks if their invention is novel, before filing, before committing engineering effort to an approach, or when preparing to meet a patent attorney.\n---\n\n# prior-art-scan — what is already known, from every direction at once\n\nAn examiner does not care whether prior art appeared in a patent, a journal, a\npreprint or a conference proceeding. A team searching only one of those is\nbuilding a false picture of its own novelty.\n\n## Search all of it, and say so\n\n```bash\nsuniv-patent \"\u003Ctechnical terms>\" --limit 25\nsuniv-search \"\u003Ctechnical terms>\" --limit 25\nsuniv-search \"\u003Ctechnical terms>\" --from \u003Cyear> --sort year --limit 15\n```\n\nPatent language is not paper language. The same invention is a \"graphene-based\ngas sensor\" in a paper and \"a sensing element comprising a carbon monolayer\" in\na patent — deliberately broad, because breadth is what a claim buys. Search both\nvocabularies: run the team's own words first, then re-search with the phrasing\nthat comes back from the patent hits.\n\nSearch the function, not just the implementation. Prior art that solves the same\nproblem a different way still bears on obviousness.\n\n## What the results can and cannot tell you\n\n`suniv-patent` returns bibliographic data. **A patent's scope is defined by its\nclaims, and the claims are not retrieved.** An abstract describes what the\ninvention is about; it does not delimit what is covered. Never tell a team they\nare clear of a patent, or blocked by one, from an abstract. Point them at the\npublication number and say the claims need reading.\n\nTwo silences that are not evidence of absence:\n\n- **The eighteen-month window.** Applications publish about a year and a half\n  after filing. The most relevant prior art may exist and be invisible today.\n  This alone makes any agent-run search provisional.\n- **Vocabulary.** Not finding something usually means not having guessed the\n  right term.\n\nSo report the outcome as a search, with its bounds: what was queried, in which\ndatabases, with which terms, and what came back. \"I found nothing\" is a\nstatement about the search. \"There is nothing\" is a claim no one can make here.\n\n## Reading what you find\n\nFor each relevant hit, say plainly why it bears on the idea:\n\n- **the same thing** — same problem, same mechanism;\n- **the same mechanism elsewhere** — which is what makes an invention obvious,\n  and is the most commonly missed category;\n- **the same problem, differently solved** — context for the argument, and often\n  the strongest position the team can build from;\n- **adjacent** — worth knowing, not a threat.\n\nDistinguish what is granted and in force from what is merely published or\nabandoned; an expired patent is free to use, and teams routinely mistake one for\nthe other.\n\nWhere a patent and a paper describe the same work, say so — an inventor\npublishing their own work is common, and it collapses two apparent hits into one.\n\n## Close by handing the work forward\n\nGive the team what their attorney will ask for: the closest art with publication\nnumbers, the terms searched, the databases covered, and where the picture is\nthin. Then say clearly what this was not — not a freedom-to-operate opinion, not\na clearance search, not legal advice. It is the preparation that makes the paid\nhour productive.\n\nIf the idea looks novel and the team is about to publish, `disclosure-guard`\napplies immediately, and it is more urgent than anything in this skill.\n","# prior-art-scan — what is already known, from every direction at once\n\nAn examiner does not care whether prior art appeared in a patent, a journal, a\npreprint or a conference proceeding. A team searching only one of those is\nbuilding a false picture of its own novelty.\n\n## Search all of it, and say so\n\n```bash\nsuniv-patent \"\u003Ctechnical terms>\" --limit 25\nsuniv-search \"\u003Ctechnical terms>\" --limit 25\nsuniv-search \"\u003Ctechnical terms>\" --from \u003Cyear> --sort year --limit 15\n```\n\nPatent language is not paper language. The same invention is a \"graphene-based\ngas sensor\" in a paper and \"a sensing element comprising a carbon monolayer\" in\na patent — deliberately broad, because breadth is what a claim buys. Search both\nvocabularies: run the team's own words first, then re-search with the phrasing\nthat comes back from the patent hits.\n\nSearch the function, not just the implementation. Prior art that solves the same\nproblem a different way still bears on obviousness.\n\n## What the results can and cannot tell you\n\n`suniv-patent` returns bibliographic data. **A patent's scope is defined by its\nclaims, and the claims are not retrieved.** An abstract describes what the\ninvention is about; it does not delimit what is covered. Never tell a team they\nare clear of a patent, or blocked by one, from an abstract. Point them at the\npublication number and say the claims need reading.\n\nTwo silences that are not evidence of absence:\n\n- **The eighteen-month window.** Applications publish about a year and a half\n  after filing. The most relevant prior art may exist and be invisible today.\n  This alone makes any agent-run search provisional.\n- **Vocabulary.** Not finding something usually means not having guessed the\n  right term.\n\nSo report the outcome as a search, with its bounds: what was queried, in which\ndatabases, with which terms, and what came back. \"I found nothing\" is a\nstatement about the search. \"There is nothing\" is a claim no one can make here.\n\n## Reading what you find\n\nFor each relevant hit, say plainly why it bears on the idea:\n\n- **the same thing** — same problem, same mechanism;\n- **the same mechanism elsewhere** — which is what makes an invention obvious,\n  and is the most commonly missed category;\n- **the same problem, differently solved** — context for the argument, and often\n  the strongest position the team can build from;\n- **adjacent** — worth knowing, not a threat.\n\nDistinguish what is granted and in force from what is merely published or\nabandoned; an expired patent is free to use, and teams routinely mistake one for\nthe other.\n\nWhere a patent and a paper describe the same work, say so — an inventor\npublishing their own work is common, and it collapses two apparent hits into one.\n\n## Close by handing the work forward\n\nGive the team what their attorney will ask for: the closest art with publication\nnumbers, the terms searched, the databases covered, and where the picture is\nthin. Then say clearly what this was not — not a freedom-to-operate opinion, not\na clearance search, not legal advice. It is the preparation that makes the paid\nhour productive.\n\nIf the idea looks novel and the team is about to publish, `disclosure-guard`\napplies immediately, and it is more urgent than anything in this skill.\n",{"name":5,"description":7},"main","0ec1548c4ee09bdd34556c95adba28e98014fe13","deploy\u002Flayers\u002Fsuniv\u002Fsandbox\u002Fskills\u002Fprior-art-scan",0,"https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv","https:\u002F\u002Fgithub.com\u002FLNdme","Code, Startup, Innovation","2026-11-12 20:56:27",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add LNdme\u002FSUniv --skill prior-art-scan",{"tool":37,"command":38},"bunx","bunx skills add LNdme\u002FSUniv --skill prior-art-scan",{"tool":40,"command":41},"pnpm","pnpm dlx skills add LNdme\u002FSUniv --skill prior-art-scan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fdeploy\u002Flayers\u002Fsuniv\u002Fsandbox\u002Fskills\u002Fprior-art-scan\u002FSKILL.md",true,[],[46,53,61,68,75,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7A3HDC3JGX00FD71DXQ3ZHB","use-shared-credential","When you need to call a service the org has a SHARED credential for (a SERP\u002Fsearch key, a paid-API key, a data-vendor feed, a Git remote) — and the platform has told you that credential is available to this conversation — make the call BY PROXY through the credential broker. You never see the secret; the core stamps it onto the outbound request for you.","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Fuse-shared-credential\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":57,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M7A3HAP05FJJT3N54W3MKZPH","taste-skill","Design taste and process for anything a person will look at in a browser — landing page, dashboard, prototype, deck. The default design driver for a browsable artifact, with an anti-slop playbook for the visual language.","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Ftaste-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Ftaste-skill\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7A3H6FDDJY6GFTKDNN9Y76F","publish","Publish a long-lived internal web app, site, or dashboard from the agent computer. Scope-bound (only the owner's scope, plus whoever you share it with, can reach it), immutable versions with rollback, a stable friendly link. No public URL.","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Fpublish\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M7A3H34CF5J86QMAX3FX4X5T","popular-web-designs","54 real-world design systems (Stripe, Linear, Vercel, Notion, Apple…) as ready-to-paste HTML\u002FCSS — exact colors, typography, components, and spacing for styling a page after a known brand.","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Fpopular-web-designs\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M7A3H0Z7SNWP9VXPZBTY59ZZ","morning-digest","Assemble and deliver one short morning digest for the person who owns the cron — what changed overnight in the sources they already connected, and what it means for their day.","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Fmorning-digest\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M7A3GXSXPNKHRNC7M6KC6BV5","memory","Deliberately search, add to, or curate your long-term memory with the `memory` tool — beyond the automatic recall\u002Fcapture every turn already does. Use when asked who someone is or what they're working on, when you learn a durable fact worth keeping now, or when your notebook holds stale or wrong entries you should clean up.","https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fskills-seed\u002Fmemory\u002FSKILL.md",[],[]]