[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7801RBXST6CHGJS8N7W622C":3,"skill-same:01M7801RBXST6CHGJS8N7W622C":80},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7801RBXST6CHGJS8N7W622C","cxc-interview",null,"Use for requirements interviews. Triggers: interview, ambiguity, contradiction scan, ask me questions, I phase, 인터뷰.","lidge-jun\u002Fcodexclaw","lidge-jun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F243035832?v=4","01M77ZYSKV8Z3ATX74SGTVT60X","JUN","01M77ZYSMFY8RQFKCVFHFBPQA9",54,"MIT","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cxc-interview\ndescription: \"Use for requirements interviews. Triggers: interview, ambiguity, contradiction scan, ask me questions, I phase, 인터뷰.\"\nmetadata:\n  short-description: \"Persistent I-phase clarification with contradiction tracking.\"\n---\n\n# cxc-interview\n\nUse this skill for Interview work within the user's scope. Loading it or receiving\na natural-language I hint does not enter the phase. Actual entry uses an explicit\nuser command or authorized `cxc orchestrate I --session \u003Cid>` with the current\nSessionStart binding. No-FSM requests remain advisory without a transition.\n\n## Contract\n\n- Interview questions use synchronous `request_user_input`, subject to the host's\n  rules. Do not use `request_user_input_async` or a legacy async variant for\n  Interview rounds: this workflow needs returned answers and ledger-backed readiness.\n  General mid-work questions follow [Async user questions](..\u002Fdev\u002Freferences\u002Fasync-questions.md).\n- The main session owns questions, user answers, tracker updates, and devlog\n  records.\n- Subagents may search for contradictions and propose question candidates, but\n  they do not ask the user directly.\n- Ask across four dimensions: Goal, Constraint, Success criteria, Ontology.\n- Re-scan contradictions after every user answer.\n- Do not advance to Plan while a high contradiction or pending question remains.\n- Record medium\u002Flow unresolved items as OPEN ASSUMPTIONS before leaving Interview,\n  with the provenance fields of INTERVIEW-ASSUME-01.\n- When Interview reveals work that will span 2+ PABCD cycles, flag the unit as\n  multi-cycle so that the first work-phase enters as a docs-only roadmap cycle\n  (LOOP-DOCS-FIRST-01, `cxc-loop`). Interview settles unit residence\n  (UNIT-RESIDENCE-01) but does not write decade docs — that is the roadmap\n  cycle's job.\n\n## Question quality (INTERVIEW-Q-01)\n\n- Target the weakest dimension first and name why it is the current bottleneck.\n- Ask focused questions that expose an ASSUMPTION or boundary — not a feature-list roundup.\n  Bundle several only when they are INDEPENDENT: never batch two questions where one\n  answer changes the other (INTERVIEW-INDEPENDENT-01). Independence governs, not a count.\n  Note the transport limit: `request_user_input` accepts at most three questions per call,\n  so a larger independent batch has to be split across calls.\n- High-impact `proposed` assumptions (INTERVIEW-ASSUME-01) are candidates for the\n  next relevant question round. Low-impact ones may stay `proposed`; closeout lists them.\n- Prefer repo-grounded confirmation (\"the code does X — is that intended?\") over re-asking what\n  the codebase already answers.\n- Treat every answer as a claim to pressure-test: vague or hedged answers do not raise a\n  dimension's readiness; they keep or deepen the gap.\n\n## Show the state before asking (INTERVIEW-RENDER-01)\n\nEmit a short status block immediately before `request_user_input`: what is now known, which\ndimension is weakest and why it is the current bottleneck, and what the answer will change.\nThe runtime cannot force this — hooks only inject text — so it is the main session's job.\nWithout it a well-grounded question still reads as context-blind, because the user cannot see\nthe reasoning that produced it.\n\n## Conditional References\n\n| Condition | Reference |\n| --- | --- |\n| Inferring, deferring or confirming assumptions; handing off to Plan | [Assumption provenance](references\u002Fassumption-provenance.md) (INTERVIEW-ASSUME-01) |\n| Before another question round or recording readiness evidence | [Ledger grounding](references\u002Fledger-grounding.md) (INTERVIEW-GROUND-01) |\n| Vague domain, catalog discovery, configurator or option-set design | [Catalog and configurator](references\u002Fcatalog-configurator.md) |\n| Rescan, loop classification, proceed\u002Fpause decision or I → P transition | [Readiness and closeout](references\u002Freadiness-closeout.md) |\n| Runtime hooks, goal firewall or authorized Mind dispatch | [Runtime status](references\u002Fruntime-status.md); before Mind dispatch read [Mind dispatch](references\u002Fmind-dispatch.md) completely |\n","# cxc-interview\n\nUse this skill for Interview work within the user's scope. Loading it or receiving\na natural-language I hint does not enter the phase. Actual entry uses an explicit\nuser command or authorized `cxc orchestrate I --session \u003Cid>` with the current\nSessionStart binding. No-FSM requests remain advisory without a transition.\n\n## Contract\n\n- Interview questions use synchronous `request_user_input`, subject to the host's\n  rules. Do not use `request_user_input_async` or a legacy async variant for\n  Interview rounds: this workflow needs returned answers and ledger-backed readiness.\n  General mid-work questions follow [Async user questions](..\u002Fdev\u002Freferences\u002Fasync-questions.md).\n- The main session owns questions, user answers, tracker updates, and devlog\n  records.\n- Subagents may search for contradictions and propose question candidates, but\n  they do not ask the user directly.\n- Ask across four dimensions: Goal, Constraint, Success criteria, Ontology.\n- Re-scan contradictions after every user answer.\n- Do not advance to Plan while a high contradiction or pending question remains.\n- Record medium\u002Flow unresolved items as OPEN ASSUMPTIONS before leaving Interview,\n  with the provenance fields of INTERVIEW-ASSUME-01.\n- When Interview reveals work that will span 2+ PABCD cycles, flag the unit as\n  multi-cycle so that the first work-phase enters as a docs-only roadmap cycle\n  (LOOP-DOCS-FIRST-01, `cxc-loop`). Interview settles unit residence\n  (UNIT-RESIDENCE-01) but does not write decade docs — that is the roadmap\n  cycle's job.\n\n## Question quality (INTERVIEW-Q-01)\n\n- Target the weakest dimension first and name why it is the current bottleneck.\n- Ask focused questions that expose an ASSUMPTION or boundary — not a feature-list roundup.\n  Bundle several only when they are INDEPENDENT: never batch two questions where one\n  answer changes the other (INTERVIEW-INDEPENDENT-01). Independence governs, not a count.\n  Note the transport limit: `request_user_input` accepts at most three questions per call,\n  so a larger independent batch has to be split across calls.\n- High-impact `proposed` assumptions (INTERVIEW-ASSUME-01) are candidates for the\n  next relevant question round. Low-impact ones may stay `proposed`; closeout lists them.\n- Prefer repo-grounded confirmation (\"the code does X — is that intended?\") over re-asking what\n  the codebase already answers.\n- Treat every answer as a claim to pressure-test: vague or hedged answers do not raise a\n  dimension's readiness; they keep or deepen the gap.\n\n## Show the state before asking (INTERVIEW-RENDER-01)\n\nEmit a short status block immediately before `request_user_input`: what is now known, which\ndimension is weakest and why it is the current bottleneck, and what the answer will change.\nThe runtime cannot force this — hooks only inject text — so it is the main session's job.\nWithout it a well-grounded question still reads as context-blind, because the user cannot see\nthe reasoning that produced it.\n\n## Conditional References\n\n| Condition | Reference |\n| --- | --- |\n| Inferring, deferring or confirming assumptions; handing off to Plan | [Assumption provenance](references\u002Fassumption-provenance.md) (INTERVIEW-ASSUME-01) |\n| Before another question round or recording readiness evidence | [Ledger grounding](references\u002Fledger-grounding.md) (INTERVIEW-GROUND-01) |\n| Vague domain, catalog discovery, configurator or option-set design | [Catalog and configurator](references\u002Fcatalog-configurator.md) |\n| Rescan, loop classification, proceed\u002Fpause decision or I → P transition | [Readiness and closeout](references\u002Freadiness-closeout.md) |\n| Runtime hooks, goal firewall or authorized Mind dispatch | [Runtime status](references\u002Fruntime-status.md); before Mind dispatch read [Mind dispatch](references\u002Fmind-dispatch.md) completely |\n",{"name":5,"metadata":24,"description":7},{"short-description":25},"Persistent I-phase clarification with contradiction tracking.","main","e413b144ffa0617093d158a0dde101601bcadee9","plugins\u002Fcodexclaw\u002Fskills\u002Finterview",11,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw","https:\u002F\u002Flidge-jun.github.io\u002Fcodexclaw\u002F","https:\u002F\u002Fgithub.com\u002Flidge-jun","https:\u002F\u002Ftrygoat.ai","Building GOAT (trygoat.ai): run coding agents on any model, any machine. Creator of OpenCodex (18K★). Korea University.","2026-11-09 12:57:23",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lidge-jun\u002Fcodexclaw --skill cxc-interview",{"tool":42,"command":43},"bunx","bunx skills add lidge-jun\u002Fcodexclaw --skill cxc-interview",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lidge-jun\u002Fcodexclaw --skill cxc-interview","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002FSKILL.md",true,[50,56,60,64,68,72,76],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"agents\u002Fopenai.yaml","REFERENCE","参考文档",168,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Fagents\u002Fopenai.yaml",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fassumption-provenance.md",2707,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Freferences\u002Fassumption-provenance.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fcatalog-configurator.md",2734,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Freferences\u002Fcatalog-configurator.md",{"path":65,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fledger-grounding.md",2611,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Freferences\u002Fledger-grounding.md",{"path":69,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fmind-dispatch.md",3128,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Freferences\u002Fmind-dispatch.md",{"path":73,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Freadiness-closeout.md",3530,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Freferences\u002Freadiness-closeout.md",{"path":77,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fruntime-status.md",2506,"https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Finterview\u002Freferences\u002Fruntime-status.md",[81,88,95,102,109,116],{"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},"01M78033YWB99B1Y92JY0CFTV1","cxc-worktree-guardian","Use for Codex-app worktrees. Triggers: worktree, rename worktree, detached HEAD, ~\u002F.codex\u002Fworktrees, 워크트리, 워크트리 이름, 새 워크트리, 브랜치랑 워크트리.","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Fworktree-guardian\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M780318BPTTTEVJ9XJMH52N9","cxc-skill-hub","Deprecated alias. Use cxc-dev.","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Fskill-hub\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7802WKVM3GWAS4P92YZBMKF","cxc-search","Use for web\u002Fcurrent lookups. Triggers: search, look up, latest, news, prices, docs, status, X\u002FTwitter, deep research, 검색, 검색해, 찾아봐, 찾아줘, 알아봐, 웹검색, 딥리서치, 심층 조사.","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Fsearch\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7802RE0M30FANF56N0SZRY3","cxc-repo-map","Use for repo structure and symbol maps. Triggers: repo map, codebase overview, architecture map, 와꾸.","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Frepo-map\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7802MXVMFKWM5742TNYW6WJ","cxc-remote","Use for Telegram\u002FDiscord bridge setup. Triggers: remote, messenger, pairing, tokens, webhooks, 텔레그램 연결, 디스코드 연결, 메신저 연결, 봇 연결, 원격, 페어링.","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Fremote\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M7802HB0C7HMRE4JSP9KXCR7","cxc-recall","Use for past-session context recovery. Triggers: recall, last time, previous session, chat search, memory search, 그때, 지난번, 저번 세션, 예전에 했던, 기억나?, 리콜, 지난 세션, 이전 작업, 뭐였지, 어떻게 했었지.","https:\u002F\u002Fgithub.com\u002Flidge-jun\u002Fcodexclaw\u002Fblob\u002Fmain\u002Fplugins\u002Fcodexclaw\u002Fskills\u002Frecall\u002FSKILL.md",[],[]]