[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GVXKA78VRP0DRZXW8814MG":3,"skill-same:01M6GVXKA78VRP0DRZXW8814MG":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":13,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6GVXKA78VRP0DRZXW8814MG","skill-authoring",null,"Create or update portable Agent Skills under .agents\u002Fskills with concise SKILL.md instructions and optional scripts, references, or assets. Use when a user wants skill-creator behavior that works across Codex, Gemini, Claude Code, OpenCode, or other agents without relying on one vendor's built-in creator.","KiringYJ\u002Fagent-workbench","KiringYJ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F55372344?v=4","01M6GVWMGEWDMMMG20Q03G7K97","01M6GVWMMQZ1DZVK4MQ8WHVRN1",0,"MIT","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Fskill-authoring\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"skill authoring","authoring","vendor","creator","concise","with","scripts","across","references","opencode","use","gemini","user","behavior","instructions","assets","code","update","create","codex","2026-11-10 10:12:30",false,"---\nname: skill-authoring\ndescription: Create or update portable Agent Skills under .agents\u002Fskills with concise SKILL.md instructions and optional scripts, references, or assets. Use when a user wants skill-creator behavior that works across Codex, Gemini, Claude Code, OpenCode, or other agents without relying on one vendor's built-in creator.\n---\n\n\u003C!-- agent-workbench: managed portable-skill -->\n\n# Skill Authoring\n\n## Dispatch\n\nUse the tier, delivery boundary, and escalation rule for `skill-authoring` in `AI_AGENT_GUIDE.md`'s **Skill Model and Reasoning Routing** table, and resolve the tier through the active platform binding.\n\n## Workflow\n\n1. Read `.agents\u002Fprompts\u002Fcreate-agent-skill.md` if present.\n2. If the active environment provides a compatible built-in skill creator, prefer it while keeping the output in the standard project-local format below; otherwise run this portable workflow directly.\n3. Gather concrete trigger examples and the repeated task the skill should improve.\n4. Create `.agents\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md`.\n5. Use frontmatter with only `name` and `description` unless a target explicitly requires more.\n6. Add `scripts\u002F`, `references\u002F`, or `assets\u002F` only when they materially reduce repeated work or increase reliability.\n7. Test scripts and validate frontmatter.\n\n## Quality Bar\n\nKeep skills concise, non-obvious, reusable, project-safe, and actionable.\n","\u003C!-- agent-workbench: managed portable-skill -->\n\n# Skill Authoring\n\n## Dispatch\n\nUse the tier, delivery boundary, and escalation rule for `skill-authoring` in `AI_AGENT_GUIDE.md`'s **Skill Model and Reasoning Routing** table, and resolve the tier through the active platform binding.\n\n## Workflow\n\n1. Read `.agents\u002Fprompts\u002Fcreate-agent-skill.md` if present.\n2. If the active environment provides a compatible built-in skill creator, prefer it while keeping the output in the standard project-local format below; otherwise run this portable workflow directly.\n3. Gather concrete trigger examples and the repeated task the skill should improve.\n4. Create `.agents\u002Fskills\u002F\u003Cskill-name>\u002FSKILL.md`.\n5. Use frontmatter with only `name` and `description` unless a target explicitly requires more.\n6. Add `scripts\u002F`, `references\u002F`, or `assets\u002F` only when they materially reduce repeated work or increase reliability.\n7. Test scripts and validate frontmatter.\n\n## Quality Bar\n\nKeep skills concise, non-obvious, reusable, project-safe, and actionable.\n",{"name":5,"description":7},"main","02e688151fc5f1a2ea5e329d4826706f9689039c","skills\u002Fskill-authoring","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench","https:\u002F\u002Fgithub.com\u002FKiringYJ","2026-11-03 22:29:44",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add KiringYJ\u002Fagent-workbench --skill skill-authoring",{"tool":60,"command":61},"bunx","bunx skills add KiringYJ\u002Fagent-workbench --skill skill-authoring",{"tool":63,"command":64},"pnpm","pnpm dlx skills add KiringYJ\u002Fagent-workbench --skill skill-authoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Fskill-authoring\u002FSKILL.md",true,[],[69,80,100,128,151,177],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":76,"publishedAt":43},"01M6GVXWA15400E2124F1P4AEP","sync-agent-workbench","Synchronize the fixture workbench.","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fworkbench\u002Fskills\u002Fsync-agent-workbench\u002FSKILL.md",[75],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[77,78,79],"sync","sync agent workbench","fixture",{"skillNo":81,"name":71,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":43},"01M6GVXQP62ENH1A32Q1FZ8BJ9","Synchronize, audit, or repair composable agent-workbench policy in a project. Use when a user wants canonical AI_AGENT_GUIDE.md, thin vendor loader entrypoints, project-selected profiles, portable prompts, and standard Agent Skills without depending on a marketplace, plugin, global config, or submodule.","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Fsync-agent-workbench\u002FSKILL.md",[85],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[77,78,87,88,89,90,91,92,35,93,25,94,33,95,96,97,98,99],"policy","config","plugin","composable","audit","marketplace","global","guide","prompts","repair","project","profiles","canonical",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":109,"publishedAt":43},"01M6GVXEMTRAXEKJH91535HDSH","math-pdf-reader","Read, transcribe, summarize, or verify mathematical PDFs with high fidelity by combining rendered-page inspection, cautious text extraction, version-matched source checks, and explicit uncertainty. Use for theorem, proof, formula, notation, attribution, or bibliographic work where ordinary PDF text extraction can silently corrupt mathematical content.","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Fmath-pdf-reader\u002FSKILL.md",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理",[110,111,112,113,114,115,116,117,118,119,120,121,33,122,123,28,124,125,126,127],"PDF","reader","math","pdf reader","math pdf reader","transcribe","attribution","verify","text","page","work","read","version","formula","uncertainty","notation","can","high",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":43},"01M6GVX9TE6W6NH2NH02TBCD4X","loop-until-done","Keep working on a requested task through bounded work, root-cause diagnosis, verification, and retry iterations until explicit completion criteria are met or a maximum iteration limit is reached. Use for Ralph-style self-correction without requiring Claude plugins, Codex plugins, Gemini extensions, or hook support.","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Floop-until-done\u002FSKILL.md",[],[135,136,137,34,42,138,139,140,120,33,141,142,143,144,145,146,147,148,149,150],"loop","done","loop until done","support","verification","ralph","root-cause","task","self","iteration","diagnosis","style","keep","retry","limit","extensions",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":43},"01M6GVX60CD180RW3PX73QM86T","linus-review","Run a strict Linus-style code review focused on correctness, backward compatibility, simplicity, data structures, special cases, hardcoded values, root-cause proof, maintainability, and verification. Use when the user asks for Linus mode, Linus review, a blunt maintainer review, harsh review, kernel-style review, or an especially skeptical code review.","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Flinus-review\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000007","代码审查",[161,162,163,164,165,39,139,166,167,33,168,169,170,171,146,172,173,174,175,176],"review","linus review","code review","kernel","run","maintainer review","data","simplicity","compatibility","maintainability","data structures","proof","correctness","root","mode","values",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":43},"01M6GVX0D2EMHD0X5C65KHB167","integrate-chatgpt-conversation","Retrieve and integrate the current accessible branch of a user-supplied ChatGPT conversation mention or direct ChatGPT URL. Use when a task depends on the full live transcript, including when the user asks to synthesize, review, or update project files from it, with authenticated recovery, scope-preserving acceptance tracking, explicit completeness boundaries, bounded independent mathematical repair, durable deferred-task recording, and downstream validation.","https:\u002F\u002Fgithub.com\u002FKiringYJ\u002Fagent-workbench\u002Fblob\u002Fmain\u002Fskills\u002Fintegrate-chatgpt-conversation\u002FSKILL.md",[],[184,185,186,187,161,188,189,190,191,33,192,142,193,96,97,194,195,28,196,197],"chatgpt","integrate","conversation","integrate chatgpt conversation","transcript","acceptance","recovery","branch","files","synthesize","scope","completeness","URL","recording"]