[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CZKBXB4B34EX95EEAT0RDJ":3,"skill-same:01M7CZKBXB4B34EX95EEAT0RDJ":46},{"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":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7CZKBXB4B34EX95EEAT0RDJ","solving-together",null,"How to work with the other agents on the same theorem — read it at the start.","Infini-AI-Lab\u002Fhermit","Infini-AI-Lab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F149595684?v=4","01M7CZJ2B2FWAKCN12205RA5YT","01M7CZJ2BNJ2V36H0YNVDF7MD9",522,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fexamples\u002Flean_swarm\u002Fadapter\u002Fskills\u002Fsolving-together\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: solving-together\ndescription: How to work with the other agents on the same theorem — read it at the start.\n---\n\n# Solving together\n\nSeveral of you work on the same problem; the channel (`say`) is how you think together.\nWhat the team shares best is checked work: verified lemmas others can pull, not prose.\n\n**Pull, don't re-prove.** You do not need to build the whole proof yourself: pull your\nteammates' verified lemmas instead of proving them again, and spend your effort on a\npiece nobody has.\n\n**Post a finding the moment it checks.** A key fact or construction that survives a\nnumerical check goes to the channel at once, before you formalize it; its definitions\ngo into the library as compiled lemmas others can pull.\n\n**Look before you build.** Read the new posts and the library before you begin a step\nor define anything: if the concept or the lemma is already there, build on it. When a\nteammate's verified lemma or construction covers your plan, adopt it, name what it\nstill lacks, build that piece, and drop your own copy. Before you write a long block,\nsearch the library for it.\n\n**Read the whole library.** `library\u002Flemmas.md` lists everything the team has verified,\none line each. It is long, keeps growing, and a long output gets cut: read all of it, in\nseveral pieces until you reach the end. The lemma you are about to write may already be\nthere, under a name you would not guess; searching for a name finds only the names you\nguess, so read the list itself.\n\n**Say what you are about to do.** Before a long computation or a big piece of Lean,\npost it in one line — what, and roughly how long. If it is already being done, do\nsomething else.\n\n**Join the plan.** Once a map is registered, work on its parts, or split the largest\nheld part, rather than on a whole proof of your own (a part marked hard welcomes a\nparallel attempt with a different approach).\n\n**Take one part, then state it.** Hold one part at a time. When you take it, state it as\na `sorry` lemma in your Problem.lean at once — the team sees who is on what from the\nfiles — and develop its proof in a scratch file; move the proof over once it compiles.\n\n**Keep in touch while you work.** During a long computation or a long stretch of\nthought, look at what changed in the team now and then (any team tool reply shows it);\nafter your context is summarized, reread the posts addressed to you.\n\n**Share what you learn, especially failures.** A route that fails, and why, saves the\nothers the same hour. One agent re-checks a teammate's construction; the others build\non it.\n\n**Close the last gap together.** When one step remains, name it exactly and leave it\nto the agent holding the closest lemmas; the others pull the result or keep working on\nopen parts rather than repeating the same step.\n\n**Hand over what you finish.** When a lemma lands, post its name and what it gives; pull\nothers' lemmas instead of proving them again.\n","# Solving together\n\nSeveral of you work on the same problem; the channel (`say`) is how you think together.\nWhat the team shares best is checked work: verified lemmas others can pull, not prose.\n\n**Pull, don't re-prove.** You do not need to build the whole proof yourself: pull your\nteammates' verified lemmas instead of proving them again, and spend your effort on a\npiece nobody has.\n\n**Post a finding the moment it checks.** A key fact or construction that survives a\nnumerical check goes to the channel at once, before you formalize it; its definitions\ngo into the library as compiled lemmas others can pull.\n\n**Look before you build.** Read the new posts and the library before you begin a step\nor define anything: if the concept or the lemma is already there, build on it. When a\nteammate's verified lemma or construction covers your plan, adopt it, name what it\nstill lacks, build that piece, and drop your own copy. Before you write a long block,\nsearch the library for it.\n\n**Read the whole library.** `library\u002Flemmas.md` lists everything the team has verified,\none line each. It is long, keeps growing, and a long output gets cut: read all of it, in\nseveral pieces until you reach the end. The lemma you are about to write may already be\nthere, under a name you would not guess; searching for a name finds only the names you\nguess, so read the list itself.\n\n**Say what you are about to do.** Before a long computation or a big piece of Lean,\npost it in one line — what, and roughly how long. If it is already being done, do\nsomething else.\n\n**Join the plan.** Once a map is registered, work on its parts, or split the largest\nheld part, rather than on a whole proof of your own (a part marked hard welcomes a\nparallel attempt with a different approach).\n\n**Take one part, then state it.** Hold one part at a time. When you take it, state it as\na `sorry` lemma in your Problem.lean at once — the team sees who is on what from the\nfiles — and develop its proof in a scratch file; move the proof over once it compiles.\n\n**Keep in touch while you work.** During a long computation or a long stretch of\nthought, look at what changed in the team now and then (any team tool reply shows it);\nafter your context is summarized, reread the posts addressed to you.\n\n**Share what you learn, especially failures.** A route that fails, and why, saves the\nothers the same hour. One agent re-checks a teammate's construction; the others build\non it.\n\n**Close the last gap together.** When one step remains, name it exactly and leave it\nto the agent holding the closest lemmas; the others pull the result or keep working on\nopen parts rather than repeating the same step.\n\n**Hand over what you finish.** When a lemma lands, post its name and what it gives; pull\nothers' lemmas instead of proving them again.\n",{"name":5,"description":7},"main","e81353897a1b5174178fe9fdf537f68862cc18ee","examples\u002Flean_swarm\u002Fadapter\u002Fskills\u002Fsolving-together",46,"https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit","https:\u002F\u002Finfini-ai-lab.github.io\u002Fhermit\u002F","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab","Next Generation AI algorithms and systems","2026-11-13 10:07:23",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Infini-AI-Lab\u002Fhermit --skill solving-together",{"tool":38,"command":39},"bunx","bunx skills add Infini-AI-Lab\u002Fhermit --skill solving-together",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Infini-AI-Lab\u002Fhermit --skill solving-together","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fexamples\u002Flean_swarm\u002Fadapter\u002Fskills\u002Fsolving-together\u002FSKILL.md",true,[],[47,53,59,65,71,77],{"skillNo":48,"name":49,"nameZh":6,"description":6,"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},"01M7CZMQVA5C6BBSRD2AVFAGE5","keep-journal","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fhermit\u002Fagent\u002Fevolver\u002Fmethods\u002Fmwm\u002Fmaterials\u002Fskills\u002Fkeep-journal\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7CZMK8QC1FXQP17QNAAG94S","failure-discipline","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fhermit\u002Fagent\u002Fevolver\u002Fmethods\u002Fmwm\u002Fmaterials\u002Fskills\u002Ffailure-discipline\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M7CZMFXPFX20FV51NP1GHY6N","design-representation","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fhermit\u002Fagent\u002Fevolver\u002Fmethods\u002Fmwm\u002Fmaterials\u002Fskills\u002Fdesign-representation\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7CZMCKY8AA74JVACE7WQ2ZN","decide-executable","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fhermit\u002Fagent\u002Fevolver\u002Fmethods\u002Fmwm\u002Fmaterials\u002Fskills\u002Fdecide-executable\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M7CZMARG8WRCWPKTY6EB6MNB","curate-brief","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fhermit\u002Fagent\u002Fevolver\u002Fmethods\u002Fmwm\u002Fmaterials\u002Fskills\u002Fcurate-brief\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M7CZM6TBNYYVTZZNF0DCZK55","create-subagent","https:\u002F\u002Fgithub.com\u002FInfini-AI-Lab\u002Fhermit\u002Fblob\u002Fmain\u002Fhermit\u002Fagent\u002Fevolver\u002Fmethods\u002Fmwm\u002Fmaterials\u002Fskills\u002Fcreate-subagent\u002FSKILL.md",[],[]]