[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77KBPDNKYVMRWG1N1FDPSS7":3,"skill-same:01M77KBPDNKYVMRWG1N1FDPSS7":45},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M77KBPDNKYVMRWG1N1FDPSS7","implement",null,"Use when agreed work is to be written into code.","dveyarangi\u002Fmeteoscape","dveyarangi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F693404?v=4","01M77KAGWZ8X0CNA092ZDNEF6T","Fima Rotter","01M77KAGXT8AD0B9SZCNM5807F",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimplement\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: implement\ndescription: Use when agreed work is to be written into code.\n---\n\nMechanism: not yet\n\nImplement the work described by the relevant architecture decisions (spec,\nticket, RFC, prior discussion).\n\nPick entity names in vibe with the project glossary.\nDo not use implementation-shaped names or parameters; orient them at the\nfunction's meaning toward the client.\n\nUse `\u002Ftdd` where possible, at pre-agreed seams. Make sure implementation, even\nin dummy\u002Fdegenerate form, fully follows contract surfaces in the docs.\n\nMake methods behind main architectural boundaries clear — they should read\nalmost as a story explaining the boundary logic, with separate concerns\nextracted to properly named sub-methods. Prefer to split submethods by\nresponsibility.\n\nThe code should read as a story. Make sure the main process appears first in\nthe file, where possible, and main boundaries' implementation reads through\nentities, interfaces and submethods used as nouns, adjectives and verbs.\n\nMark code an open question's answer will change with a comment line beginning\n`TODO` that names the question, per the entry file's straw-dog rule, and say so\nin the docstring.\n\nWhere the code you write follows a rule that a load-bearing record of the project states — its\narchitecture or an ADR — name each such rule at the end of the comment phrase it backs, as\n`(\u003Cpath from the tree's root>: \"\u003Cthe rule's name>\")`, whole on one line — wrap the comment before\nit, never inside it — the name being the rule's heading or the bold lead of its paragraph, word for\nword. A rule with no such name gets one in its record first. Code no such rule governs carries no\npointer.\n\nMake sure the errors follow error rules.\n\nMake sure to read and follow `\u002Fimprove-comments` rules. Mark other pending\nactions — hotpaths that may need optimization, work with no named successor —\nas `TODO` too; without a ticket they are notes, and the listing script reports\nthem as guesses.\n\nDuring the work, run the checks in the project's verification set, as\n[`\u002Fverify`](..\u002Fverify\u002FSKILL.md#the-verification-set) defines it. `\u002Fverify` is the\nverification of landed work; a local run of a subset is not that pass.\n\nOnce done, and unless you need to take a break, use `\u002Fverify`.\n\nRead `commit` from `AGENTS.md`. Do not commit until that switch allows it.\nRepair during the work follows the `repair` switch; it is not a substitute\nfor `\u002Fverify`.\n\n\u003Cinstalled by=\"local\">\n**L3** The verification set: the project's CI and the harness's record checks, every one green.\n\n```\nuv run ruff check .\nuv run ruff format --check .\nuv run pyright\nuv run pytest\n```\n\n```\nuv run python .agents\u002Fscripts\u002Fgw\u002Ftickets.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fedges.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fquestions.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fproduct.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fmaintain.py --check\n```\n\u003C\u002Finstalled>\n","Mechanism: not yet\n\nImplement the work described by the relevant architecture decisions (spec,\nticket, RFC, prior discussion).\n\nPick entity names in vibe with the project glossary.\nDo not use implementation-shaped names or parameters; orient them at the\nfunction's meaning toward the client.\n\nUse `\u002Ftdd` where possible, at pre-agreed seams. Make sure implementation, even\nin dummy\u002Fdegenerate form, fully follows contract surfaces in the docs.\n\nMake methods behind main architectural boundaries clear — they should read\nalmost as a story explaining the boundary logic, with separate concerns\nextracted to properly named sub-methods. Prefer to split submethods by\nresponsibility.\n\nThe code should read as a story. Make sure the main process appears first in\nthe file, where possible, and main boundaries' implementation reads through\nentities, interfaces and submethods used as nouns, adjectives and verbs.\n\nMark code an open question's answer will change with a comment line beginning\n`TODO` that names the question, per the entry file's straw-dog rule, and say so\nin the docstring.\n\nWhere the code you write follows a rule that a load-bearing record of the project states — its\narchitecture or an ADR — name each such rule at the end of the comment phrase it backs, as\n`(\u003Cpath from the tree's root>: \"\u003Cthe rule's name>\")`, whole on one line — wrap the comment before\nit, never inside it — the name being the rule's heading or the bold lead of its paragraph, word for\nword. A rule with no such name gets one in its record first. Code no such rule governs carries no\npointer.\n\nMake sure the errors follow error rules.\n\nMake sure to read and follow `\u002Fimprove-comments` rules. Mark other pending\nactions — hotpaths that may need optimization, work with no named successor —\nas `TODO` too; without a ticket they are notes, and the listing script reports\nthem as guesses.\n\nDuring the work, run the checks in the project's verification set, as\n[`\u002Fverify`](..\u002Fverify\u002FSKILL.md#the-verification-set) defines it. `\u002Fverify` is the\nverification of landed work; a local run of a subset is not that pass.\n\nOnce done, and unless you need to take a break, use `\u002Fverify`.\n\nRead `commit` from `AGENTS.md`. Do not commit until that switch allows it.\nRepair during the work follows the `repair` switch; it is not a substitute\nfor `\u002Fverify`.\n\n\u003Cinstalled by=\"local\">\n**L3** The verification set: the project's CI and the harness's record checks, every one green.\n\n```\nuv run ruff check .\nuv run ruff format --check .\nuv run pyright\nuv run pytest\n```\n\n```\nuv run python .agents\u002Fscripts\u002Fgw\u002Ftickets.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fedges.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fquestions.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fproduct.py --check\nuv run python .agents\u002Fscripts\u002Fgw\u002Fmaintain.py --check\n```\n\u003C\u002Finstalled>\n",{"name":5,"description":7},"main","d2bf1c688554a199b2433460c08378a28c368373",".agents\u002Fskills\u002Fimplement","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape","https:\u002F\u002Fgithub.com\u002Fdveyarangi","http:\u002F\u002Fdveyarangi.blogspot.com\u002F","2026-10-14 08:50:21",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add dveyarangi\u002Fmeteoscape --skill implement",{"tool":37,"command":38},"bunx","bunx skills add dveyarangi\u002Fmeteoscape --skill implement",{"tool":40,"command":41},"pnpm","pnpm dlx skills add dveyarangi\u002Fmeteoscape --skill implement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimplement\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M77KD67QK512NQZZ0KG710E7","verify","Use after an implementation pass, or to verify a landed slice before close. Whole verification of landed work: ticket, RFC, governing docs, and the project's verification set. Repair-and-report where that policy holds.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M77KD3YKE65N7D472BJAQAGW","ticket","Use to decompose a parent work into independently-workable child tickets. Use to mint ticket(s), possibly a single one, when planning implementation without one.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fticket\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M77KCZCEZJVQ8YV739MHA5YB","tdd","Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions \"red-green-refactor\", wants integration tests, or asks for test-first development.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftdd\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M77KCW8EYKHZ0HWCGN9FTQP3","spec","Use to develop a spec for substantial work through \u002Falign, then hand off to \u002Fticket. Use when a change needs agreed scope, behavior, boundaries and testing before decomposition. An existing spec for the work is developed in place.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspec\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M77KCRGB1CFTZJ39P7RGSKQ8","skill-up","Aid agent skill creation or modification. Use when creating a new skill or changing an existing one. Use whenever writing any agent instructions, whether to a file or directly in a reply.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-up\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M77KCK8PEVY9Z2PJ38ERGZQH","setup-devops","Set up the project's engineering scaffolding, from toolchain to CICD and observability. Use when initializing a repo or filling a setup gap.","https:\u002F\u002Fgithub.com\u002Fdveyarangi\u002Fmeteoscape\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsetup-devops\u002FSKILL.md",[],[]]