[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R8QPZRTXZP0D2HE78XEVSH":3,"skill-same:01M6R8QPZRTXZP0D2HE78XEVSH":72},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6R8QPZRTXZP0D2HE78XEVSH","blindspot-pass",null,"Discover unknowns before expensive work. Use before ambiguous or risky product, architecture, UX, operations, billing, onboarding, data, migration, launch, or go-to-market work; when the user asks for a blindspot pass, unknown unknowns, ambiguity review, assumption check, or better agent prompt; or when an agent needs to clarify assumptions before implementation.","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\u002F.agents\u002Fskills\u002Fblindspot-pass\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"blindspot pass","use","when","unknown","for","billing","go-to-market","discover","Market","migration","review","operations","check","prompt","clarify","work","ux","product","architecture","launch","2026-11-10 10:12:30",false,"---\nname: blindspot-pass\ndescription: Discover unknowns before expensive work. Use before ambiguous or risky product, architecture, UX, operations, billing, onboarding, data, migration, launch, or go-to-market work; when the user asks for a blindspot pass, unknown unknowns, ambiguity review, assumption check, or better agent prompt; or when an agent needs to clarify assumptions before implementation.\n---\n\n# Blindspot Pass\n\nUse this skill to shrink ambiguity before code, plans, PRDs, launches, migrations, or operator\u002Fuser-facing changes. The goal is not to ask every possible question. The goal is to find the few unknowns that would make the current path wrong.\n\n## Rules\n\n- Read the territory before theorizing: repo docs, code, tests, notes, business context, and current behavior where relevant.\n- Prefer evidence over generic best practice.\n- Do not edit product code during a blindspot pass unless the user explicitly asks you to continue into implementation.\n- Ask only questions the repo\u002Fcontext cannot answer and where the answer changes scope, architecture, UX, sequencing, risk, or success criteria.\n- Include a recommended default with each question.\n- Split independent surfaces across subagents when the work is large and subagents are available.\n- Keep output concise. This is a decision aid, not a research report.\n\n## Context Anchors\n\nCheck these sources before making recommendations when they exist:\n\n- Repo operating docs: `AGENTS.md`, `README.md`, `SKILLS.md`, nearest area docs.\n- Persistent context: `brain\u002Findex.md`, `memory\u002F`, `docs\u002F`, ADRs, specs, PRDs, plans, runbooks.\n- Product\u002FUX context: personas, user-model docs, onboarding docs, admin\u002Foperator docs, analytics definitions.\n- Code context: affected flows, tests, migrations, schemas, feature flags, provider integrations.\n- External constraints only when necessary: vendor docs, legal\u002Fsecurity rules, platform limits, pricing, dates.\n\nUse repo-specific assumptions only when backed by docs or prior context. Otherwise mark them as assumptions.\n\n## Workflow\n\n1. **Re-anchor**\n   - Restate the goal and success criteria in one or two lines.\n   - Name the surface: product, code, UX, ops, GTM, data, migration, personal workflow, or mixed.\n   - Identify which docs\u002Fcode\u002Fcontext you will inspect.\n\n2. **Map the territory**\n   - Inspect current files, flows, docs, tests, metrics definitions, provider constraints, or operating process.\n   - Note facts with file paths or source names where possible.\n   - Separate current behavior from intended behavior.\n\n3. **Classify unknowns**\n   - **Known knowns:** Prompt or repo clearly says this.\n   - **Known unknowns:** Open decisions already visible.\n   - **Unknown knowns:** Implicit expectations the user may recognize only when shown, especially taste, ops habits, customer language, launch posture, or \"obvious\" assumptions.\n   - **Unknown unknowns:** Likely hidden risks, missing constraints, edge cases, stale docs, untested paths, or places an agent would probably guess wrong.\n\n4. **Rank by decision impact**\n   - **High:** changes architecture, data model, migration lane, entitlement behavior, checkout, provider integration, security\u002Fprivacy, ops workflow, or customer-facing promise.\n   - **Medium:** changes UX flow, copy, instrumentation, test strategy, sequencing, rollout, or support burden.\n   - **Low:** can be handled conservatively during implementation.\n\n5. **Recommend next move**\n   - **Proceed:** enough clarity; give a small implementation plan.\n   - **Prototype:** create a cheap mock\u002Fprobe before real wiring.\n   - **Investigate:** send agents into specific files\u002Fflows\u002Ftests.\n   - **Interview:** ask the smallest set of high-impact questions.\n   - **De-scope:** narrow the task before implementation.\n\n## Output Shape\n\n```markdown\n**Blindspot Pass**\nGoal: ...\nSurface: ...\n\n**What I Verified**\n- ...\n\n**Unknowns**\n- High: ...\n- Medium: ...\n- Low: ...\n\n**Questions That Change The Work**\n1. ... Recommended default: ...\n\n**Recommended Next Move**\n...\n\n**Agent Prompts**\n- ...\n```\n\n## During Implementation\n\nIf the user asks you to continue after the blindspot pass, keep brief notes for non-trivial work in the repo's scratch\u002Fcontext area, such as `.context\u002Fimplementation-notes.md`, when available. Log only meaningful assumptions, deviations, and follow-ups. Do not turn it into a narrative diary.\n","# Blindspot Pass\n\nUse this skill to shrink ambiguity before code, plans, PRDs, launches, migrations, or operator\u002Fuser-facing changes. The goal is not to ask every possible question. The goal is to find the few unknowns that would make the current path wrong.\n\n## Rules\n\n- Read the territory before theorizing: repo docs, code, tests, notes, business context, and current behavior where relevant.\n- Prefer evidence over generic best practice.\n- Do not edit product code during a blindspot pass unless the user explicitly asks you to continue into implementation.\n- Ask only questions the repo\u002Fcontext cannot answer and where the answer changes scope, architecture, UX, sequencing, risk, or success criteria.\n- Include a recommended default with each question.\n- Split independent surfaces across subagents when the work is large and subagents are available.\n- Keep output concise. This is a decision aid, not a research report.\n\n## Context Anchors\n\nCheck these sources before making recommendations when they exist:\n\n- Repo operating docs: `AGENTS.md`, `README.md`, `SKILLS.md`, nearest area docs.\n- Persistent context: `brain\u002Findex.md`, `memory\u002F`, `docs\u002F`, ADRs, specs, PRDs, plans, runbooks.\n- Product\u002FUX context: personas, user-model docs, onboarding docs, admin\u002Foperator docs, analytics definitions.\n- Code context: affected flows, tests, migrations, schemas, feature flags, provider integrations.\n- External constraints only when necessary: vendor docs, legal\u002Fsecurity rules, platform limits, pricing, dates.\n\nUse repo-specific assumptions only when backed by docs or prior context. Otherwise mark them as assumptions.\n\n## Workflow\n\n1. **Re-anchor**\n   - Restate the goal and success criteria in one or two lines.\n   - Name the surface: product, code, UX, ops, GTM, data, migration, personal workflow, or mixed.\n   - Identify which docs\u002Fcode\u002Fcontext you will inspect.\n\n2. **Map the territory**\n   - Inspect current files, flows, docs, tests, metrics definitions, provider constraints, or operating process.\n   - Note facts with file paths or source names where possible.\n   - Separate current behavior from intended behavior.\n\n3. **Classify unknowns**\n   - **Known knowns:** Prompt or repo clearly says this.\n   - **Known unknowns:** Open decisions already visible.\n   - **Unknown knowns:** Implicit expectations the user may recognize only when shown, especially taste, ops habits, customer language, launch posture, or \"obvious\" assumptions.\n   - **Unknown unknowns:** Likely hidden risks, missing constraints, edge cases, stale docs, untested paths, or places an agent would probably guess wrong.\n\n4. **Rank by decision impact**\n   - **High:** changes architecture, data model, migration lane, entitlement behavior, checkout, provider integration, security\u002Fprivacy, ops workflow, or customer-facing promise.\n   - **Medium:** changes UX flow, copy, instrumentation, test strategy, sequencing, rollout, or support burden.\n   - **Low:** can be handled conservatively during implementation.\n\n5. **Recommend next move**\n   - **Proceed:** enough clarity; give a small implementation plan.\n   - **Prototype:** create a cheap mock\u002Fprobe before real wiring.\n   - **Investigate:** send agents into specific files\u002Fflows\u002Ftests.\n   - **Interview:** ask the smallest set of high-impact questions.\n   - **De-scope:** narrow the task before implementation.\n\n## Output Shape\n\n```markdown\n**Blindspot Pass**\nGoal: ...\nSurface: ...\n\n**What I Verified**\n- ...\n\n**Unknowns**\n- High: ...\n- Medium: ...\n- Low: ...\n\n**Questions That Change The Work**\n1. ... Recommended default: ...\n\n**Recommended Next Move**\n...\n\n**Agent Prompts**\n- ...\n```\n\n## During Implementation\n\nIf the user asks you to continue after the blindspot pass, keep brief notes for non-trivial work in the repo's scratch\u002Fcontext area, such as `.context\u002Fimplementation-notes.md`, when available. Log only meaningful assumptions, deviations, and follow-ups. Do not turn it into a narrative diary.\n",{"name":5,"description":7},"main","c9d0c408715983e993b2f9ebffdbfa7f10153bcb",".agents\u002Fskills\u002Fblindspot-pass",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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Nairon-AI\u002Fagentic-starter-pack --skill blindspot-pass",{"tool":64,"command":65},"bunx","bunx skills add Nairon-AI\u002Fagentic-starter-pack --skill blindspot-pass",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Nairon-AI\u002Fagentic-starter-pack --skill blindspot-pass","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fblindspot-pass\u002FSKILL.md",true,[],[73,106,127,148,168,190],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":87,"publishedAt":44},"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",[79,82],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[88,89,90,91,92,93,94,95,96,25,97,98,99,100,101,102,103,104,105,26],"writing","writing shape","shape","notes","help","file","markdown","format","session","take","draft","article","material","it","about","quotes","at","candidate",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":114,"publishedAt":44},"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",[112,113],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},[88,115,116,117,118,119,96,25,120,121,122,99,123,100,124,125,28,126,26],"writing fragments","grilling","ideate","develop","user","document","structure","ideas","as","sharp","claims","single",{"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":135,"publishedAt":44},"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",[133,134],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},[88,136,137,138,25,139,140,90,141,142,143,99,144,123,145,100,146,147,28,26],"writing beats","choose","write","assemble","only","journey","next","options","end","style","narrative","argument",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":156,"publishedAt":44},"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",[154,155],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},[157,158,159,88,160,161,162,163,164,25,165,166,167,28,26],"stop","stop slop","slop","content","https","text","editing","remove","prose","patterns","drafts",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":176,"publishedAt":44},"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",[174,175],{"categoryNo":80,"categoryName":81,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":83,"categoryName":84,"taxonomyType":85,"taxonomyTypeDesc":86},[170,88,177,178,162,179,138,180,181,164,182,183,166,184,185,186,187,188,189,26],"code","em dash","read","edit","generated","guide","opencode","three","human","make","wikipedia","vague","dash",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":44},"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",[],[192,197,198,199,200,201,25,202,203,204,205,206,26,207],"prepare","flow","first","question","behavior","conversation","coaching","debrief","impact","managers","deliver"]