[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A3F8ESV53AZNWFDFK7T2H7":3,"skill-same:01M7A3F8ESV53AZNWFDFK7T2H7":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},"01M7A3F8ESV53AZNWFDFK7T2H7","paper-deep-read",null,"Explain one difficult paper at the student's level — its objective, its method step by step, its mathematics, its hidden assumptions and what is reproducible. Use when the student asks what a paper did, how a method works, why it is hard, or says they do not understand an article.","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\u002Fpaper-deep-read\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: paper-deep-read\ndescription: Explain one difficult paper at the student's level — its objective, its method step by step, its mathematics, its hidden assumptions and what is reproducible. Use when the student asks what a paper did, how a method works, why it is hard, or says they do not understand an article.\n---\n\n# paper-deep-read — make one hard paper genuinely understood\n\nThe student is not asking for a summary. They are asking to be brought to the\npoint where they could explain the paper to their supervisor, or build on it.\nThose are different outputs, and only one of them is worth their time.\n\n## Get the text first\n\nYou cannot deep-read a paper you have not read. Check grounding before starting:\n\n```bash\nsuniv-search --doi \u003Cdoi>                      # is there an open-access copy?\nsuniv-lib search \"\u003Ctitle words>\"              # does the student already hold it?\nsuniv-lib sections --file \u003Cpath>              # the structure, with page numbers\nsuniv-lib text --file \u003Cpath> --page 4         # one page at a time\n```\n\nIf only the abstract exists, say so and offer what an abstract can support: the\nquestion, the claimed contribution, the venue. Do not walk through a method you\nhave not seen. If nothing but metadata exists, this skill does not apply yet —\nhelp the student obtain the text.\n\n## Calibrate to the person\n\nAsk what they already have, or infer it from how they asked. A first-year\nmaster's student meeting variational inference and a doctoral student who knows\nit but not this variant need different explanations, and giving the wrong one\nwastes the session. When unsure, start one level below where you think they are\nand move fast — being briefly over-explained costs seconds, being lost costs the\nafternoon.\n\n## The order that works\n\n1. **The problem, before the solution.** What was broken or unknown, and why did\n   existing approaches not settle it? A method makes no sense until the student\n   feels the difficulty it answers.\n2. **The idea in one sentence,** in plain language, no notation.\n3. **The method, step by step.** What goes in, what happens to it, what comes\n   out. Name each step's purpose before its mechanics.\n4. **The mathematics, once the shape is clear.** Define every symbol on first\n   use. Say what each equation _does_ — this term penalises that, this\n   expectation is over that distribution. An equation restated in words is not\n   an explanation; an equation whose role is explained is.\n5. **The evaluation.** What is compared to what, on which data, and does the\n   comparison actually support the claim? This is where papers are weakest and\n   where a student learns to read critically.\n6. **Assumptions and limits.** What must be true for this to work? What do the\n   authors concede, and what do they pass over quietly? Distinguish the two —\n   only the first is on the record.\n7. **Reproducibility.** Is there code, data, hyperparameters, compute? What\n   would the student need to run it themselves?\n\n## Attribute everything\n\nEvery claim about the paper points to where it is: a section heading, a page, an\nequation number. \"§3.2 defines attention as…\" lets the student check you and\nfind it again. \"The paper says…\" does not, and is where a misreading becomes\ntheirs.\n\nWhen you are inferring rather than reporting — reading between the lines,\nconnecting to something the paper does not say — mark it as your reading. That\ndistinction is the difference between teaching and misleading.\n\n## Close usefully\n\n- what the student should now be able to do that they could not before;\n- the two or three papers this one rests on, if they need the foundation —\n  retrieve them with `suniv-search`, do not name them from memory;\n- the honest verdict on quality: what this paper establishes, and what it only\n  suggests.\n\nThen offer to file the notes into Zotero against the item, so the reading\nsurvives the conversation.\n","# paper-deep-read — make one hard paper genuinely understood\n\nThe student is not asking for a summary. They are asking to be brought to the\npoint where they could explain the paper to their supervisor, or build on it.\nThose are different outputs, and only one of them is worth their time.\n\n## Get the text first\n\nYou cannot deep-read a paper you have not read. Check grounding before starting:\n\n```bash\nsuniv-search --doi \u003Cdoi>                      # is there an open-access copy?\nsuniv-lib search \"\u003Ctitle words>\"              # does the student already hold it?\nsuniv-lib sections --file \u003Cpath>              # the structure, with page numbers\nsuniv-lib text --file \u003Cpath> --page 4         # one page at a time\n```\n\nIf only the abstract exists, say so and offer what an abstract can support: the\nquestion, the claimed contribution, the venue. Do not walk through a method you\nhave not seen. If nothing but metadata exists, this skill does not apply yet —\nhelp the student obtain the text.\n\n## Calibrate to the person\n\nAsk what they already have, or infer it from how they asked. A first-year\nmaster's student meeting variational inference and a doctoral student who knows\nit but not this variant need different explanations, and giving the wrong one\nwastes the session. When unsure, start one level below where you think they are\nand move fast — being briefly over-explained costs seconds, being lost costs the\nafternoon.\n\n## The order that works\n\n1. **The problem, before the solution.** What was broken or unknown, and why did\n   existing approaches not settle it? A method makes no sense until the student\n   feels the difficulty it answers.\n2. **The idea in one sentence,** in plain language, no notation.\n3. **The method, step by step.** What goes in, what happens to it, what comes\n   out. Name each step's purpose before its mechanics.\n4. **The mathematics, once the shape is clear.** Define every symbol on first\n   use. Say what each equation _does_ — this term penalises that, this\n   expectation is over that distribution. An equation restated in words is not\n   an explanation; an equation whose role is explained is.\n5. **The evaluation.** What is compared to what, on which data, and does the\n   comparison actually support the claim? This is where papers are weakest and\n   where a student learns to read critically.\n6. **Assumptions and limits.** What must be true for this to work? What do the\n   authors concede, and what do they pass over quietly? Distinguish the two —\n   only the first is on the record.\n7. **Reproducibility.** Is there code, data, hyperparameters, compute? What\n   would the student need to run it themselves?\n\n## Attribute everything\n\nEvery claim about the paper points to where it is: a section heading, a page, an\nequation number. \"§3.2 defines attention as…\" lets the student check you and\nfind it again. \"The paper says…\" does not, and is where a misreading becomes\ntheirs.\n\nWhen you are inferring rather than reporting — reading between the lines,\nconnecting to something the paper does not say — mark it as your reading. That\ndistinction is the difference between teaching and misleading.\n\n## Close usefully\n\n- what the student should now be able to do that they could not before;\n- the two or three papers this one rests on, if they need the foundation —\n  retrieve them with `suniv-search`, do not name them from memory;\n- the honest verdict on quality: what this paper establishes, and what it only\n  suggests.\n\nThen offer to file the notes into Zotero against the item, so the reading\nsurvives the conversation.\n",{"name":5,"description":7},"main","0ec1548c4ee09bdd34556c95adba28e98014fe13","deploy\u002Flayers\u002Fsuniv\u002Fsandbox\u002Fskills\u002Fpaper-deep-read",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 paper-deep-read",{"tool":37,"command":38},"bunx","bunx skills add LNdme\u002FSUniv --skill paper-deep-read",{"tool":40,"command":41},"pnpm","pnpm dlx skills add LNdme\u002FSUniv --skill paper-deep-read","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLNdme\u002FSUniv\u002Fblob\u002Fmain\u002Fdeploy\u002Flayers\u002Fsuniv\u002Fsandbox\u002Fskills\u002Fpaper-deep-read\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",[],[]]