[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B8KWG5P528FTSS7FT2PMWH":3,"skill-same:01M7B8KWG5P528FTSS7FT2PMWH":96},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7B8KWG5P528FTSS7FT2PMWH","ac-low-level-io-and-syscalls",null,"The boundary between a program and the kernel: syscall cost and batching, buffered versus direct I\u002FO, memory-mapped files and when they beat read, epoll and readiness-based event loops, io_uring and submission queues, vectored I\u002FO, blocking versus non-blocking sockets, and the written I\u002FO record. It explains what crossing the kernel boundary costs and how to cross it fewer times; it never recommends a framework and never promises a throughput. Use when asking \"syscall overhead\", \"read vs mmap\", \"direct I\u002FO\", \"epoll\", \"io_uring\", \"zero copy\", \"sendfile\", \"vectored I\u002FO\", \"blocking versus non-blocking\", \"why is reading this file slow\", \"batching syscalls\". Not for application caching (ac-caching-and-invalidation), not for distributed replication (ac-distributed-state-and-replication), not for file format layout (ac-binary-formats).","jiayaoqijia\u002Fcryptoskill","jiayaoqijia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1453879?v=4","01M6GMYTX7Q7S504VC6E756ENR","YQ","01M6GMYV1QKJ1CC75MTTGT9PR0",81,"MIT","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ac-low-level-io-and-syscalls\ndescription: \"The boundary between a program and the kernel: syscall cost and batching, buffered versus direct I\u002FO, memory-mapped files and when they beat read, epoll and readiness-based event loops, io_uring and submission queues, vectored I\u002FO, blocking versus non-blocking sockets, and the written I\u002FO record. It explains what crossing the kernel boundary costs and how to cross it fewer times; it never recommends a framework and never promises a throughput. Use when asking \\\"syscall overhead\\\", \\\"read vs mmap\\\", \\\"direct I\u002FO\\\", \\\"epoll\\\", \\\"io_uring\\\", \\\"zero copy\\\", \\\"sendfile\\\", \\\"vectored I\u002FO\\\", \\\"blocking versus non-blocking\\\", \\\"why is reading this file slow\\\", \\\"batching syscalls\\\". Not for application caching (ac-caching-and-invalidation), not for distributed replication (ac-distributed-state-and-replication), not for file format layout (ac-binary-formats).\"\nlicense: MIT\nmetadata:\n  domain: software-engineering\nstatus: seedling\n---\n\n# Low-level I\u002FO and syscalls\n\n## Overview\n\nEvery read, write, or socket operation crosses a boundary: the kernel mediates access to files, devices, and the network, and each crossing has a fixed cost independent of the bytes moved. A program that reads a file in one-megabyte chunks pays the same number of crossings as one reading in four-kilobyte chunks, at a fraction of the boundary overhead — and a program that reads byte-by-byte through a buffered wrapper may pay no boundary at all, at the cost of an extra copy.\n\nThis skill covers the boundary's mechanics: what a syscall costs, when direct I\u002FO avoids the page cache, what mmap buys and what it gives up, how readiness-driven event loops work, what submission-queue interfaces change, and why vectored and zero-copy interfaces exist. The buffer cache and the syscall boundary are design surfaces; the application-level cache is a different skill.\n\nPrimary sources: \u003Chttps:\u002F\u002Fman7.org\u002Flinux\u002Fman-pages\u002Fman2\u002Fmmap.2.html> and \u003Chttps:\u002F\u002Fman7.org\u002Flinux\u002Fman-pages\u002Fman7\u002Fepoll.7.html>.\n\n## When to use\n\n- When a workload is I\u002FO-bound and the crossing count, not the byte count, is the bottleneck.\n- When choosing between read, mmap, and direct I\u002FO for a large dataset.\n- When an event loop's readiness model matters to correctness or latency.\n- When zero-copy or vectored interfaces are under consideration.\n\n## When NOT to use\n\n- For application-level caching and invalidation (use ac-caching-and-invalidation).\n- For replication and consistency across machines (use ac-distributed-state-and-replication).\n- For the byte-level layout of the data itself (use ac-binary-formats).\n\n## Subskill Index\n\n| Leaf | Domain segment | Scope (one line) |\n|---|---|---|\n| `subskills\u002Fsyscall-cost-and-batching.md` | `software-engineering\u002Fsyscall-cost-and-batching` | The fixed cost of the boundary and amortizing it. |\n| `subskills\u002Fpage-cache-and-direct-io.md` | `software-engineering\u002Fpage-cache-and-direct-io` | The buffer cache, its sharing, and paying to skip it. |\n| `subskills\u002Fmmap-versus-read.md` | `software-engineering\u002Fmmap-versus-read` | Mapping a file versus reading it, and each one's failure mode. |\n| `subskills\u002Freadiness-and-event-loops.md` | `software-engineering\u002Freadiness-and-event-loops` | epoll, edge versus level triggering, and the thundering herd. |\n| `subskills\u002Fsubmission-queues.md` | `software-engineering\u002Fsubmission-queues` | io_uring-style submission and completion for dense I\u002FO. |\n| `subskills\u002Fvectored-and-zero-copy.md` | `software-engineering\u002Fvectored-and-zero-copy` | Scatter-gather and the copies an interface can avoid. |\n| `subskills\u002Fblocking-and-nonblocking.md` | `software-engineering\u002Fblocking-and-nonblocking` | What blocking promises, and what non-blocking requires in exchange. |\n| `subskills\u002Fio-record.md` | `software-engineering\u002Fio-record` | The written record: I\u002FO model choices and their measurements. |\n\n## Status and honest limits\n\nSyscall costs and cache behaviour are kernel- and hardware-specific, and interfaces differ across platforms — what is a submission queue on one system is an async handle on another, with different semantics for cancellation and ordering. The page cache is shared state the program does not control, so measurements of cached I\u002FO are measurements of a warm machine. Nothing here recommends a specific interface, and any I\u002FO-model decision carries its platform and kernel version in the record, because the numbers that justify it do not transfer.\n","# Low-level I\u002FO and syscalls\n\n## Overview\n\nEvery read, write, or socket operation crosses a boundary: the kernel mediates access to files, devices, and the network, and each crossing has a fixed cost independent of the bytes moved. A program that reads a file in one-megabyte chunks pays the same number of crossings as one reading in four-kilobyte chunks, at a fraction of the boundary overhead — and a program that reads byte-by-byte through a buffered wrapper may pay no boundary at all, at the cost of an extra copy.\n\nThis skill covers the boundary's mechanics: what a syscall costs, when direct I\u002FO avoids the page cache, what mmap buys and what it gives up, how readiness-driven event loops work, what submission-queue interfaces change, and why vectored and zero-copy interfaces exist. The buffer cache and the syscall boundary are design surfaces; the application-level cache is a different skill.\n\nPrimary sources: \u003Chttps:\u002F\u002Fman7.org\u002Flinux\u002Fman-pages\u002Fman2\u002Fmmap.2.html> and \u003Chttps:\u002F\u002Fman7.org\u002Flinux\u002Fman-pages\u002Fman7\u002Fepoll.7.html>.\n\n## When to use\n\n- When a workload is I\u002FO-bound and the crossing count, not the byte count, is the bottleneck.\n- When choosing between read, mmap, and direct I\u002FO for a large dataset.\n- When an event loop's readiness model matters to correctness or latency.\n- When zero-copy or vectored interfaces are under consideration.\n\n## When NOT to use\n\n- For application-level caching and invalidation (use ac-caching-and-invalidation).\n- For replication and consistency across machines (use ac-distributed-state-and-replication).\n- For the byte-level layout of the data itself (use ac-binary-formats).\n\n## Subskill Index\n\n| Leaf | Domain segment | Scope (one line) |\n|---|---|---|\n| `subskills\u002Fsyscall-cost-and-batching.md` | `software-engineering\u002Fsyscall-cost-and-batching` | The fixed cost of the boundary and amortizing it. |\n| `subskills\u002Fpage-cache-and-direct-io.md` | `software-engineering\u002Fpage-cache-and-direct-io` | The buffer cache, its sharing, and paying to skip it. |\n| `subskills\u002Fmmap-versus-read.md` | `software-engineering\u002Fmmap-versus-read` | Mapping a file versus reading it, and each one's failure mode. |\n| `subskills\u002Freadiness-and-event-loops.md` | `software-engineering\u002Freadiness-and-event-loops` | epoll, edge versus level triggering, and the thundering herd. |\n| `subskills\u002Fsubmission-queues.md` | `software-engineering\u002Fsubmission-queues` | io_uring-style submission and completion for dense I\u002FO. |\n| `subskills\u002Fvectored-and-zero-copy.md` | `software-engineering\u002Fvectored-and-zero-copy` | Scatter-gather and the copies an interface can avoid. |\n| `subskills\u002Fblocking-and-nonblocking.md` | `software-engineering\u002Fblocking-and-nonblocking` | What blocking promises, and what non-blocking requires in exchange. |\n| `subskills\u002Fio-record.md` | `software-engineering\u002Fio-record` | The written record: I\u002FO model choices and their measurements. |\n\n## Status and honest limits\n\nSyscall costs and cache behaviour are kernel- and hardware-specific, and interfaces differ across platforms — what is a submission queue on one system is an async handle on another, with different semantics for cancellation and ordering. The page cache is shared state the program does not control, so measurements of cached I\u002FO are measurements of a warm machine. Nothing here recommends a specific interface, and any I\u002FO-model decision carries its platform and kernel version in the record, because the numbers that justify it do not transfer.\n",{"name":5,"status":25,"license":15,"metadata":26,"description":7},"seedling",{"domain":27},"software-engineering","main","4aff87e77e63c1886a978b82902814d015f55a4f","skills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls",17,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia","https:\u002F\u002Feth2030.com","Hardcore infra. Building @alt-research and applied cryptography.","2026-11-15 02:28:10",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add jiayaoqijia\u002Fcryptoskill --skill ac-low-level-io-and-syscalls",{"tool":43,"command":44},"bunx","bunx skills add jiayaoqijia\u002Fcryptoskill --skill ac-low-level-io-and-syscalls",{"tool":46,"command":47},"pnpm","pnpm dlx skills add jiayaoqijia\u002Fcryptoskill --skill ac-low-level-io-and-syscalls","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002FSKILL.md",true,[51,55,61,65,69,73,77,80,84,88,92],{"path":52,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":16},"LICENSE","许可证",1068,{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"SOURCE.md","REFERENCE","参考文档",384,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002FSOURCE.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"subskills\u002Fblocking-and-nonblocking.md",3448,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fblocking-and-nonblocking.md",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"subskills\u002Fio-record.md",3162,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fio-record.md",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"subskills\u002Fmmap-versus-read.md",3271,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fmmap-versus-read.md",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"subskills\u002Fpage-cache-and-direct-io.md",3397,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fpage-cache-and-direct-io.md",{"path":78,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":79},"subskills\u002Freadiness-and-event-loops.md","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Freadiness-and-event-loops.md",{"path":81,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":82,"sourceHtmlUrl":83},"subskills\u002Fsubmission-queues.md",3368,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fsubmission-queues.md",{"path":85,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":86,"sourceHtmlUrl":87},"subskills\u002Fsyscall-cost-and-batching.md",3233,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fsyscall-cost-and-batching.md",{"path":89,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":90,"sourceHtmlUrl":91},"subskills\u002Fvectored-and-zero-copy.md",3375,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002Fsubskills\u002Fvectored-and-zero-copy.md",{"path":93,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":94,"sourceHtmlUrl":95},"TRUST.auto.yaml",2217,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fexchanges\u002Fanoscranel-ac-low-level-io-and-syscalls\u002FTRUST.auto.yaml",[97,105,113,121,129,137],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":20},"01M7DTKCERMV0RNX3HZJP4CZ26","troves","Deposit and withdraw from Troves DeFi yield vault strategies on Starknet. View available strategies, check positions, and manage vault deposits. Use this skill when the user mentions Troves, vault, yield vault, DeFi vault, strategy, yield farming, vault deposit, vault withdraw, earning yield through vaults, passive yield strategies, or wants to deposit into or withdraw from a yield strategy — even if they don't say \"Troves\" explicitly.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-troves\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-troves\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":20},"01M7DTK6CJSMGC8KCQHGNYFZBD","trade","Swap tokens on Starknet via Fibrous DEX aggregator. Supports per-provider selection (avnu, ekubo, or auto to race all). Use this skill when the user wants to swap, exchange, trade, convert, buy, or sell one token for another on Starknet. Also use when the user asks about token prices, exchange rates, DEX routing, best swap route, or wants to check how much they would receive for a given amount — even if they don't explicitly say \"swap\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-trade\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-trade\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":20},"01M7DTJZ6A0X4PAW3Y8W4J9K64","staking","Stake, unstake, claim, and compound rewards for STRK, WBTC, tBTC, SolvBTC, and LBTC on Starknet. View validators, pools, and staking positions. Use this skill when the user mentions staking, delegating, validators, staking pools, rewards, compounding, unstaking, earning yield, passive income on crypto, or wants to earn on their STRK or BTC tokens — even if they don't say \"stake\" explicitly.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-staking\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-staking\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":20},"01M7DTJSDZJKCDMW7GHRF4BRH5","send","Send STRK, ETH, or any ERC-20 token to a Starknet address. Supports simulation (dry-run) before execution. Use this skill when the user wants to send, transfer, pay, tip, or move tokens to another wallet address on Starknet. Also trigger when the user mentions sending funds to someone, making a payment, transferring assets, or moving crypto to a specific address — even if they just say \"pay 10 STRK to 0x...\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-send\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-send\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":133,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":20},"01M7DTJG1E480D51ZQ7WKDQ26K","portfolio","View a comprehensive DeFi portfolio dashboard and optimize portfolio allocation via automated rebalancing. Use this skill when the user wants an overview, summary, dashboard, total value, net worth, portfolio rebalancing, target allocation, or wants to see all their DeFi positions across Starknet at once. Also trigger when the user asks \"what do I have\", \"show me everything\", \"how much am I worth\", \"my positions\", \"my investments\", \"rebalance my portfolio\", \"I want 50% ETH\", \"optimize my holdings\", or any request for a holistic view of their Starknet holdings — even if they don't explicitly say \"portfolio\".","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-portfolio\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-portfolio\u002FSKILL.md",[],[],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":141,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":20},"01M7DTJ7M8TE9R2N36HFBZDGVD","multi-swap","Execute multiple token swaps in a single Starknet transaction via Fibrous (default). Supports per-provider selection (avnu, ekubo, or auto to race all). Supports 2-3 swap pairs bundled into one multicall. Use this skill when the user wants to swap multiple token pairs at once, do batch swaps, execute several trades simultaneously, perform parallel swaps, or do bulk trading in one transaction. Also trigger when the user mentions \"two swaps\", \"three swaps\", \"swap X and Y at the same time\", or wants to convert multiple tokens in a single call.","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-multi-swap\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fmcp-servers\u002Fahmetenesdur-multi-swap\u002FSKILL.md",[],[]]