[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718ADE9H7Q9N0MXTTBZKBYC":3,"skill-same:01M718ADE9H7Q9N0MXTTBZKBYC":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":52,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":6,"updatedAt":55,"install":56,"resources":68},"01M718ADE9H7Q9N0MXTTBZKBYC","solo",null,"Work on one hard mathematics problem in this session yourself, with no sub-agents: reason in stages, record each settled step in a notes file so that nothing written is lost if a response is cut off, and end with a self-contained proof.md. Usage: \u002Fmath-proof:solo \u003Cthe problem, stated in full, or the path of a file holding it>.","anthropics\u002Fclaude-plugins-official","anthropics","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4","01M697XGDPXJAVQ8391V2BCYTE","Anthropic","01M7188MR49TZ9N2ZKPXJ7M7HY",46906,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fmath-proof\u002Fskills\u002Fsolo\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"file","webfetch","math","cp","work","record","notes","self","with","websearch","Bash","true","mkdir","end","session","work on","problem statement","problem","usage","2026-11-10 10:12:30",false,"---\nname: solo\ndescription: \"Work on one hard mathematics problem in this session yourself, with no sub-agents: reason in stages, record each settled step in a notes file so that nothing written is lost if a response is cut off, and end with a self-contained proof.md. Usage: \u002Fmath-proof:solo \u003Cthe problem, stated in full, or the path of a file holding it>.\"\nargument-hint: \"[DIR=run-directory] \u003Cproblem statement | problem-file>\"\ndisable-model-invocation: true\ndisallowed-tools: WebSearch, WebFetch, AskUserQuestion\nallowed-tools: Read, Write, Edit, Glob, Grep, Bash(mkdir *), Bash(cp *), Bash(cmp *)\n---\n\n# math-proof: solo\n\nYou solve the problem yourself, in this session. There are no sub-agents and no rounds: just you, a notes\nfile and, at the end, proof.md.\n\n**Arguments.** The invoking message reads: $ARGUMENTS\nIt gives the problem and, optionally, the run directory. Read it this way. A token of the form DIR=path at its\nstart sets the run directory (the path quoted if it contains spaces); remove it. Any other leading token of the\nform NAME=value, where NAME is a word of two or more capital letters and underscores and value is a whole number,\nis a setting this skill does not have: tell the user in one sentence that \u002Fmath-proof:solo takes only DIR=path\nbefore the problem (round and wave settings belong to \u002Fmath-proof:siege), and that if the token is part of the\nproblem itself the problem can be given as a file path instead, and stop. If what remains is a single line\nthat, taken as a whole — surrounding whitespace and one pair of enclosing quotation marks removed,\nbackslash-escaped spaces read as spaces — is the path of an existing file (it may contain spaces; check with\nRead or Glob, not the shell), that file is the problem file; if no such file exists and what remains can only\nbe a file path — a single line ending in .md, .txt or .tex, or a single token (no spaces once the quotes are\nremoved) containing \"\u002F\" or \"\\\" — tell the user in one sentence that no file exists at the absolute path you\nlooked for (give it) and that the problem can instead be given in full as text after the command, and stop;\notherwise everything that remains, to the end of the message, IS the problem statement, verbatim — mathematics,\nline breaks and all (\"n=3\", \"N=pq\" and \"AB=AC\" are mathematics, not settings). The run directory DIR defaults to\n.\u002Fmath-proof-solo under the current directory; use DIR's absolute path everywhere below. If the message holds\nneither a readable problem file nor any problem text, say so in one sentence — with the usage,\n`\u002Fmath-proof:solo \u003Cproblem statement, or the path of a file holding it>` — and stop.\n\n**Setup.** The run's files are DIR\u002Fproblem.md (the problem), DIR\u002Fnotes.md (your notes) and DIR\u002Fproof.md (the\ndeliverable). Create DIR with `mkdir -p`. If DIR\u002Fnotes.md already exists, this problem was already being\nworked on in DIR: check that DIR\u002Fproblem.md is the same problem you were given (compare the text, ignoring\ndifferences in whitespace and line endings; for a file, `cmp`) — if it differs, say in one sentence that DIR\nholds work on a different problem and that `DIR=\u003Canother directory>` selects a fresh one, and stop; if it is\nthe same, read DIR\u002Fnotes.md, and DIR\u002Fproof.md if it exists. If they record the solution as complete (proof.md\nwritten and nothing in the notes still to do), the earlier session finished: say where proof.md is and that\n`DIR=\u003Canother directory>` starts a fresh attempt, and stop. Otherwise the earlier session ended before it\nfinished, and whatever reasoning it had not written down is lost: continue from the last point recorded there\nrather than starting over. If DIR\u002Fnotes.md does not exist yet, put the problem at DIR\u002Fproblem.md: if it came as\na file, copy that file there byte for byte with `cp`; if it came as text in the invoking message, Write\nexactly that text (nothing added, removed or reworded). Then Read DIR\u002Fproblem.md in full; it is the authoritative text of the problem. Use the shell for\nnothing but that `mkdir`, `cp` and `cmp`.\n\n**The task.** Solve the problem stated in DIR\u002Fproblem.md; the deliverable is DIR\u002Fproof.md. After reasoning,\nwrite your answer. This task runs as a conversation that can span many messages, each with a bounded output\nallowance; a message that is cut off is normally followed by a request to continue, and only what you have\nWRITTEN (not unwritten reasoning) is guaranteed to carry into the next message. So write your work product\nout as you go, in a notes file, DIR\u002Fnotes.md: whenever you settle something — a lemma and its proof, a\nreduction, a dead end and why it is dead, the precise statement you are now attempting — write it down before\nreasoning further. A partial answer is much more useful than none. Writing to the notes is not finishing —\nkeep going after each write. Important: each message's output allowance also covers your private reasoning,\nand it is far smaller than a hard problem deserves — a message spent entirely on reasoning, with nothing\nwritten, gets cut off, and unwritten reasoning should be assumed lost. So do not try to finish in one\nmessage. Work in stages: early in EVERY message, before any long derivation, write your current plan and the\nprecise statement you are attempting to DIR\u002Fnotes.md; then reason toward the next concrete intermediate\nresult, append it to the notes as soon as you have it, and continue. Many short written steps beat one long\nunwritten one. If a message of yours is cut off, re-read DIR\u002Fnotes.md and continue from the last thing\nwritten there; never start over. You have no web access and no code execution; this is a pure reasoning\ntask. When the problem is resolved, or you have taken it as far as you can, write your complete solution to\nDIR\u002Fproof.md. proof.md is read on its own by a referee who cannot open any other file (not your notes\neither), so it must be self-contained: every argument the solution relies on is written out in full there.\nWork unattended: there is no one to answer questions, so never stop to ask.\n\nWhen DIR\u002Fproof.md is written, reply briefly: where proof.md is, and whether it resolves the problem\ncompletely or, in proof.md's own words, what it leaves open.\n","# math-proof: solo\n\nYou solve the problem yourself, in this session. There are no sub-agents and no rounds: just you, a notes\nfile and, at the end, proof.md.\n\n**Arguments.** The invoking message reads: $ARGUMENTS\nIt gives the problem and, optionally, the run directory. Read it this way. A token of the form DIR=path at its\nstart sets the run directory (the path quoted if it contains spaces); remove it. Any other leading token of the\nform NAME=value, where NAME is a word of two or more capital letters and underscores and value is a whole number,\nis a setting this skill does not have: tell the user in one sentence that \u002Fmath-proof:solo takes only DIR=path\nbefore the problem (round and wave settings belong to \u002Fmath-proof:siege), and that if the token is part of the\nproblem itself the problem can be given as a file path instead, and stop. If what remains is a single line\nthat, taken as a whole — surrounding whitespace and one pair of enclosing quotation marks removed,\nbackslash-escaped spaces read as spaces — is the path of an existing file (it may contain spaces; check with\nRead or Glob, not the shell), that file is the problem file; if no such file exists and what remains can only\nbe a file path — a single line ending in .md, .txt or .tex, or a single token (no spaces once the quotes are\nremoved) containing \"\u002F\" or \"\\\" — tell the user in one sentence that no file exists at the absolute path you\nlooked for (give it) and that the problem can instead be given in full as text after the command, and stop;\notherwise everything that remains, to the end of the message, IS the problem statement, verbatim — mathematics,\nline breaks and all (\"n=3\", \"N=pq\" and \"AB=AC\" are mathematics, not settings). The run directory DIR defaults to\n.\u002Fmath-proof-solo under the current directory; use DIR's absolute path everywhere below. If the message holds\nneither a readable problem file nor any problem text, say so in one sentence — with the usage,\n`\u002Fmath-proof:solo \u003Cproblem statement, or the path of a file holding it>` — and stop.\n\n**Setup.** The run's files are DIR\u002Fproblem.md (the problem), DIR\u002Fnotes.md (your notes) and DIR\u002Fproof.md (the\ndeliverable). Create DIR with `mkdir -p`. If DIR\u002Fnotes.md already exists, this problem was already being\nworked on in DIR: check that DIR\u002Fproblem.md is the same problem you were given (compare the text, ignoring\ndifferences in whitespace and line endings; for a file, `cmp`) — if it differs, say in one sentence that DIR\nholds work on a different problem and that `DIR=\u003Canother directory>` selects a fresh one, and stop; if it is\nthe same, read DIR\u002Fnotes.md, and DIR\u002Fproof.md if it exists. If they record the solution as complete (proof.md\nwritten and nothing in the notes still to do), the earlier session finished: say where proof.md is and that\n`DIR=\u003Canother directory>` starts a fresh attempt, and stop. Otherwise the earlier session ended before it\nfinished, and whatever reasoning it had not written down is lost: continue from the last point recorded there\nrather than starting over. If DIR\u002Fnotes.md does not exist yet, put the problem at DIR\u002Fproblem.md: if it came as\na file, copy that file there byte for byte with `cp`; if it came as text in the invoking message, Write\nexactly that text (nothing added, removed or reworded). Then Read DIR\u002Fproblem.md in full; it is the authoritative text of the problem. Use the shell for\nnothing but that `mkdir`, `cp` and `cmp`.\n\n**The task.** Solve the problem stated in DIR\u002Fproblem.md; the deliverable is DIR\u002Fproof.md. After reasoning,\nwrite your answer. This task runs as a conversation that can span many messages, each with a bounded output\nallowance; a message that is cut off is normally followed by a request to continue, and only what you have\nWRITTEN (not unwritten reasoning) is guaranteed to carry into the next message. So write your work product\nout as you go, in a notes file, DIR\u002Fnotes.md: whenever you settle something — a lemma and its proof, a\nreduction, a dead end and why it is dead, the precise statement you are now attempting — write it down before\nreasoning further. A partial answer is much more useful than none. Writing to the notes is not finishing —\nkeep going after each write. Important: each message's output allowance also covers your private reasoning,\nand it is far smaller than a hard problem deserves — a message spent entirely on reasoning, with nothing\nwritten, gets cut off, and unwritten reasoning should be assumed lost. So do not try to finish in one\nmessage. Work in stages: early in EVERY message, before any long derivation, write your current plan and the\nprecise statement you are attempting to DIR\u002Fnotes.md; then reason toward the next concrete intermediate\nresult, append it to the notes as soon as you have it, and continue. Many short written steps beat one long\nunwritten one. If a message of yours is cut off, re-read DIR\u002Fnotes.md and continue from the last thing\nwritten there; never start over. You have no web access and no code execution; this is a pure reasoning\ntask. When the problem is resolved, or you have taken it as far as you can, write your complete solution to\nDIR\u002Fproof.md. proof.md is read on its own by a referee who cannot open any other file (not your notes\neither), so it must be self-contained: every argument the solution relies on is written out in full there.\nWork unattended: there is no one to answer questions, so never stop to ask.\n\nWhen DIR\u002Fproof.md is written, reply briefly: where proof.md is, and whether it resolves the problem\ncompletely or, in proof.md's own words, what it leaves open.\n",{"name":5,"description":7,"allowed-tools":43,"argument-hint":44,"disallowed-tools":45,"disable-model-invocation":46},"Read, Write, Edit, Glob, Grep, Bash(mkdir *), Bash(cp *), Bash(cmp *)","[DIR=run-directory] \u003Cproblem statement | problem-file>","WebSearch, WebFetch, AskUserQuestion",true,"main","dceb15d50832e6adf380bedc26dde03d251324b9","plugins\u002Fmath-proof\u002Fskills\u002Fsolo",4875,"https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official","https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fplugins","https:\u002F\u002Fgithub.com\u002Fanthropics","https:\u002F\u002Fanthropic.com","2026-11-12 03:40:35",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":46},[58,61,64],{"tool":59,"command":60},"npx","npx skills add anthropics\u002Fclaude-plugins-official --skill solo",{"tool":62,"command":63},"bunx","bunx skills add anthropics\u002Fclaude-plugins-official --skill solo",{"tool":65,"command":66},"pnpm","pnpm dlx skills add anthropics\u002Fclaude-plugins-official --skill solo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fmath-proof\u002Fskills\u002Fsolo\u002FSKILL.md",[],[70,103,127,151,175,196],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":82,"publishedAt":38},"01M718BVSPNAK6S5NZCYFDBG6E","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-creator\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-creator\u002Fskills\u002Fskill-creator\u002FSKILL.md",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"skill creator","creator","performance","improve","run evals","new","when","analysis","create","optimize","variance analysis","run","edit","benchmark","existing skill","evals","for","accuracy","scratch","use",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":114,"publishedAt":38},"01M718BSVAWJRFN6MRCZZ0QX4X","session-report","Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~\u002F.claude\u002Fprojects transcripts.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fsession-report\u002Fskills\u002Fsession-report\u002FSKILL.md",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[33,115,116,117,37,118,119,120,121,122,123,124,125,126],"report","session report","projects","generate","tokens","html report","transcripts","prompts","cache","code","html","subagents",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":136,"publishedAt":38},"01M718BPKHVD214FAS1T4E5XCE","receipts","Generate a personal Claude Code usage & impact report (\"receipts\") from this machine's local session transcripts — for justifying Claude Code usage\u002Fspend to a manager, self-review, or \"what have I been using this for\" check-ins. Mines ~\u002F.claude\u002Fprojects locally (no extra API calls beyond one final write-up), cross-references local git history, and writes a markdown report plus a self-contained HTML receipt to your home directory. Use when the user asks for \"receipts\", an \"impact report\", \"usage report\", wants to \"show my Claude Code activity\", \"prove the value of Claude Code\", or runs `\u002Freceipts`.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Freceipts\u002Fskills\u002Freceipts\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000030","开发工程师",[129,117,137,138,139,140,89,124,141,142,26,143,118,144,145,146,147,148,149,150],"show","up","local","impact","api","review","references","markdown","directory","write","git","activity","my","manager",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":38},"01M718BJMX0T4691FJQ62GYY5C","project-artifact","Generate and publish a project status artifact — an opinionated, tabbed status page for a project too big for one update (overview & success criteria, the workstream sequence, next steps, plus background, plan, risks & open questions, and decisions\u002FFAQ when they earn a tab) — published with the built-in Artifact tool to a default-private claude.ai page the user can share with teammates. Use when a piece of work spans several workstreams and you want a shareable overview kept current. Each artifact is backed by a small per-project config in the plugin data dir, so refreshing it re-gathers live state, redeploys the same URL, and reports only the delta. For software projects whose workstreams are PRs, also read swe.md (the X.Y PR-numbering convention; pulling PR state with gh\u002Fgit; a per-PR detail block). Needs the built-in Artifact tool (claude.ai login). Not for single-PR changes or public docs.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fproject-artifact\u002Fskills\u002Fproject-artifact\u002FSKILL.md",[],[158,159,160,161,117,162,163,164,165,166,167,89,168,169,170,171,23,172,173,174],"project","artifact","project artifact","project status","re","default","next steps","open","only","SWE","URL","you","reports","publish","plan","status page","next",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":38},"01M718BF1TTFP5CM0S5HBW64FJ","skill-development","This skill should be used when the user wants to \"create a skill\", \"add a skill to plugin\", \"write a new skill\", \"improve skill description\", \"organize skill content\", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-dev\u002Fskills\u002Fskill-development\u002FSKILL.md",[181],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},[183,184,185,86,88,186,89,124,91,187,146,188,189,190,191,99,192,193,194,195],"development","skill development","skill to plugin","improve skill","structure","organize","new skill","claude code plugins","add","progressive","best practices","progressive disclosure","plugin",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":203,"publishedAt":38},"01M718BCARZ2J4PW0X3AJCZ8MZ","plugin-structure","This skill should be used when the user asks to \"create a plugin\", \"scaffold a plugin\", \"understand plugin structure\", \"organize plugin components\", \"set up plugin.json\", \"use ${CLAUDE_PLUGIN_ROOT}\", \"add commands\u002Fagents\u002Fskills\u002Fhooks\", \"configure auto-discovery\", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-dev\u002Fskills\u002Fplugin-structure\u002FSKILL.md",[202],{"categoryNo":78,"categoryName":79,"taxonomyType":80,"taxonomyTypeDesc":81},[187,204,195,205,206,207,138,208,209,89,210,124,211,212,91,213,214,215,145,216],"Plugin Structure","SET","plugin architecture","hooks","auto-discovery","auto","configure","components","architecture","component","layout","organization","commands"]