[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R99EE17S3DR065JATR211C":3,"skill-same:01M6R99EE17S3DR065JATR211C":67},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6R99EE17S3DR065JATR211C","issue-triage",null,"Run either a conversational QA session for multiple issues or a deep-dive triage of one reported problem, then create GitHub issues or local issue drafts with durable behavior descriptions and TDD fix plans as needed. Use when the user wants to report bugs, do QA, file issues conversationally, triage an issue, or investigate and plan a fix.","Nairon-AI\u002Fagentic-starter-pack","Nairon-AI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260662138?v=4","01M6R8PZ1Y8CSQGFN61VACZGTH","Nairon AI","01M6R8PZ6184VR3BA88YZFBC3N",4,"MIT","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fengineering\u002Fissue-triage\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"issue triage","triage","issue","when","bugs","for","with","problem","as","plans","deep","local","either","do","use","session","fix","file","qa","issues","2026-11-10 10:12:30",false,"---\nname: issue-triage\ndescription: Run either a conversational QA session for multiple issues or a deep-dive triage of one reported problem, then create GitHub issues or local issue drafts with durable behavior descriptions and TDD fix plans as needed. Use when the user wants to report bugs, do QA, file issues conversationally, triage an issue, or investigate and plan a fix.\n---\n\n# Issue Triage\n\nHandle issue intake in one of two modes:\n\n- **QA session mode** for multiple reported issues or conversational bug intake\n- **Deep-dive mode** for one specific issue that needs diagnosis, root cause analysis, and a TDD fix plan\n\nIf the user says \"QA session\", reports several issues, or is clearly doing issue intake, use QA session mode.\n\nIf the user asks to \"triage\" one issue, wants root cause analysis, or needs a fix plan, use deep-dive mode.\n\nIf the repo is not on GitHub or `gh` is unavailable, write local Markdown issues under `.\u002Fissues\u002F` instead.\n\n## QA session mode\n\n### 1. Listen and lightly clarify\n\nAsk at most 2-3 short questions:\n\n- what they expected\n- what actually happened\n- how to reproduce\n\nDo not over-interview.\n\n### 2. Explore the codebase in the background\n\nLearn the relevant domain language and behavior boundary, but do not turn the issue into a file-path dump.\n\n### 3. Decide whether to split\n\nBreak one report into multiple issues only when there are clearly independent failure modes or parallelizable slices.\n\n### 4. File durable issue(s)\n\nDescribe behavior from the user's perspective.\n\nAlways include:\n\n- what happened\n- what was expected\n- reproduction steps\n- concise additional context\n\nDo not include stale details like file paths or line numbers.\n\n## Deep-dive mode\n\n### 1. Capture the problem\n\nIf needed, ask one question: \"What's the problem you're seeing?\"\n\nThen investigate immediately.\n\n### 2. Diagnose\n\nTrace:\n\n- where the bug manifests\n- what code path is involved\n- why it fails\n- what adjacent tests and patterns exist\n\n### 3. Identify the fix approach\n\nDetermine:\n\n- the minimal durable fix\n- affected modules or interfaces\n- behaviors that need tests\n\n### 4. Write the TDD fix plan\n\nCreate ordered RED-GREEN cycles:\n\n1. **RED**: a behavior-focused failing test\n2. **GREEN**: the minimal change that makes it pass\n\nInclude a final refactor step if needed.\n\n### 5. File the issue\n\nUse a durable issue body with:\n\n- problem statement\n- expected behavior\n- reproduction\n- root cause analysis\n- TDD fix plan\n- acceptance criteria\n\n## Output rules\n\n- Prefer GitHub issues when available.\n- Otherwise create `.\u002Fissues\u002F\u003Cslug>.md`.\n- Use the repo's domain language.\n- Keep issue bodies durable across refactors.\n- Print the created issue URL or file path at the end.\n\n## Gotchas\n\n- QA session mode is about intake and durable issue writing, not immediate root-cause analysis for every report.\n- Deep-dive mode is for one issue at a time.\n- Do not collapse several independent bugs into one thick issue just because the user mentioned them together.\n","# Issue Triage\n\nHandle issue intake in one of two modes:\n\n- **QA session mode** for multiple reported issues or conversational bug intake\n- **Deep-dive mode** for one specific issue that needs diagnosis, root cause analysis, and a TDD fix plan\n\nIf the user says \"QA session\", reports several issues, or is clearly doing issue intake, use QA session mode.\n\nIf the user asks to \"triage\" one issue, wants root cause analysis, or needs a fix plan, use deep-dive mode.\n\nIf the repo is not on GitHub or `gh` is unavailable, write local Markdown issues under `.\u002Fissues\u002F` instead.\n\n## QA session mode\n\n### 1. Listen and lightly clarify\n\nAsk at most 2-3 short questions:\n\n- what they expected\n- what actually happened\n- how to reproduce\n\nDo not over-interview.\n\n### 2. Explore the codebase in the background\n\nLearn the relevant domain language and behavior boundary, but do not turn the issue into a file-path dump.\n\n### 3. Decide whether to split\n\nBreak one report into multiple issues only when there are clearly independent failure modes or parallelizable slices.\n\n### 4. File durable issue(s)\n\nDescribe behavior from the user's perspective.\n\nAlways include:\n\n- what happened\n- what was expected\n- reproduction steps\n- concise additional context\n\nDo not include stale details like file paths or line numbers.\n\n## Deep-dive mode\n\n### 1. Capture the problem\n\nIf needed, ask one question: \"What's the problem you're seeing?\"\n\nThen investigate immediately.\n\n### 2. Diagnose\n\nTrace:\n\n- where the bug manifests\n- what code path is involved\n- why it fails\n- what adjacent tests and patterns exist\n\n### 3. Identify the fix approach\n\nDetermine:\n\n- the minimal durable fix\n- affected modules or interfaces\n- behaviors that need tests\n\n### 4. Write the TDD fix plan\n\nCreate ordered RED-GREEN cycles:\n\n1. **RED**: a behavior-focused failing test\n2. **GREEN**: the minimal change that makes it pass\n\nInclude a final refactor step if needed.\n\n### 5. File the issue\n\nUse a durable issue body with:\n\n- problem statement\n- expected behavior\n- reproduction\n- root cause analysis\n- TDD fix plan\n- acceptance criteria\n\n## Output rules\n\n- Prefer GitHub issues when available.\n- Otherwise create `.\u002Fissues\u002F\u003Cslug>.md`.\n- Use the repo's domain language.\n- Keep issue bodies durable across refactors.\n- Print the created issue URL or file path at the end.\n\n## Gotchas\n\n- QA session mode is about intake and durable issue writing, not immediate root-cause analysis for every report.\n- Deep-dive mode is for one issue at a time.\n- Do not collapse several independent bugs into one thick issue just because the user mentioned them together.\n",{"name":5,"description":7},"main","c9d0c408715983e993b2f9ebffdbfa7f10153bcb","engineering\u002Fissue-triage",0,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack","https:\u002F\u002Fgithub.com\u002FNairon-AI","https:\u002F\u002Fwww.naironai.com\u002F","Building the future of Work","2026-09-20 17:40:05",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Nairon-AI\u002Fagentic-starter-pack --skill issue-triage",{"tool":59,"command":60},"bunx","bunx skills add Nairon-AI\u002Fagentic-starter-pack --skill issue-triage",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Nairon-AI\u002Fagentic-starter-pack --skill issue-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fengineering\u002Fissue-triage\u002FSKILL.md",true,[],[68,101,121,142,162,184],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":84,"publishedAt":39},"01M6RBCG630Y8X99XWR9Q4GYNY","writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-shape\u002FSKILL.md",[74,79],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[85,86,87,88,89,36,90,91,34,33,92,93,94,95,96,97,98,99,100,22],"writing","writing shape","shape","notes","help","markdown","format","take","draft","article","material","it","about","quotes","at","candidate",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":109,"publishedAt":39},"01M6RBCCCB1KMF01P5SYGFWBSW","writing-fragments","Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions \"fragments\", \"ideate\", or \"raw material\" for writing.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-fragments\u002FSKILL.md",[107,108],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[85,110,111,112,113,114,34,33,115,116,117,94,27,95,118,119,24,120,22],"writing fragments","grilling","ideate","develop","user","document","structure","ideas","sharp","claims","single",{"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":6,"sourceHtmlUrl":125,"categories":126,"keywords":129,"publishedAt":39},"01M6RBC8V7NHHKMTAZB4BPXVYQ","writing-beats","Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-beats\u002FSKILL.md",[127,128],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[85,130,131,132,33,133,134,87,135,136,137,94,138,27,139,95,140,141,24,22],"writing beats","choose","write","assemble","only","journey","next","options","end","style","narrative","argument",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":150,"publishedAt":39},"01M6RBC58SG5Y5SC4ZV4ZNEFHC","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fstop-slop\u002FSKILL.md",[148,149],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[151,152,153,85,154,155,156,157,158,33,159,160,161,24,22],"stop","stop slop","slop","content","https","text","editing","remove","prose","patterns","drafts",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":170,"publishedAt":39},"01M6RBBJTTCJ7KZCP16G9JDFZH","humanizer","Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, passive\nvoice, negative parallelisms, and filler phrases.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fhumanizer\u002FSKILL.md",[168,169],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[164,85,171,172,156,173,132,174,175,158,176,177,160,178,179,180,181,182,183,22],"code","em dash","read","edit","generated","guide","opencode","three","human","make","wikipedia","vague","dash",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":39},"01M6RBBEQKJ5HRH8AV9J85QB1T","feedback","Prepare, deliver, and debrief timely interpersonal feedback using a question-first coaching flow, observable behavior, owned experience, and concrete impact. Use when drafting feedback, coaching managers, rehearsing a feedback conversation, praising specific behavior, or reviewing whether feedback landed.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Ffeedback\u002FSKILL.md",[],[186,191,192,193,194,195,33,196,197,198,199,200,22,201],"prepare","flow","first","question","behavior","conversation","coaching","debrief","impact","managers","deliver"]