[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F7QV01KMTSFZ8RPF4D6H1W":3,"skill-same:01M7F7QV01KMTSFZ8RPF4D6H1W":64},{"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":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M7F7QV01KMTSFZ8RPF4D6H1W","deep-interview-planning-workflows",null,"Use for Kanban-authoritative Deep Interview fact gathering and Native Swarm handoff.","chaorenex1\u002Fhermes-home-content","chaorenex1","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23194925?v=4","01M7F5NA1D1D02R2MEMYQN2NZT","chan chan","01M7F5NA20KTHMTY2015CYM1TZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fdeep-interview-planning-workflows\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\r\nname: deep-interview-planning-workflows\r\ndescription: \"Use for Kanban-authoritative Deep Interview fact gathering and Native Swarm handoff.\"\r\nversion: 2.0.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nplatforms: [linux, macos, windows]\r\nmetadata:\r\n  hermes:\r\n    tags: [deep-interview, planning, kanban, specification, ultrawork]\r\n    related_skills: [plan, durable-agent-orchestration, deep-interview-for-memory-injection]\r\n---\r\n\r\n# Deep Interview Planning Workflows\r\n\r\n## Contract\r\n\r\nDeep Interview gathers explicit facts before implementation. `kanban.db` is the\r\nonly authority for the objective, feedback, hypotheses, decisions, future\r\ngoals, round snapshots, phase, and versions. Do not treat chat text,\r\n`kb_temp`, Dynamic Context, or a specification file as a replacement authority.\r\n\r\nThe Host projects only goal and runtime state to\r\n`kb_temp(information_type=\"deep_interview\")` in three atomic sections:\r\n`current_focus`, `current_progress`, and `future_needs`. AI may read this\r\nprojection through Dynamic Context but may not write it. The Host Projector is\r\nthe only writer.\r\n\r\n## Interview Turns\r\n\r\n1. Read the current Deep Interview block in Dynamic Context.\r\n2. Use `interview_search` when the complete Kanban fact snapshot is needed.\r\n3. Ask one concrete, falsifiable hypothesis about the current objective.\r\n4. Do not create a plan, specification, implementation graph, or approval\r\n   verdict during an interview round.\r\n5. Let the Host append the authoritative future-goals footer. Do not generate\r\n   that footer in the model response.\r\n\r\nExplicit feedback is classified by the AI Feedback Router as exactly one of:\r\n\r\n- `confirm_hypothesis`: record the confirmation and continue.\r\n- `reject_hypothesis`: record the correction and ask a revised hypothesis.\r\n- `goal_conflict`: keep the current goal and record the new goal as future work.\r\n- `stop_interview`: stop immediately and generate the final specification.\r\n\r\nThere is no independent Judge, review round, approval step, next-round approval,\r\nor stop confirmation.\r\n\r\n## Specification And Handoff\r\n\r\nOnly `stop_interview` may create a specification. The canonical location is:\r\n\r\n```text\r\nHERMES_HOME\u002Flancedb-memory\u002Fresource\u002Fspec\u002F\u003Ctitle>.md\r\n```\r\n\r\nThe specification is generated from the final Kanban fact snapshot and uses a\r\nmonotonic `spec_version`. Deep Interview does not compute a content hash or\r\ndigest.\r\n\r\nRun `hermes ultrawork plan \u003Cspec-path> [repository]` or\r\n`\u002Fultrawork plan \u003Cspec-path> [repository]` after the specification is\r\ncompleted. Plan accepts either the completed specification path or a direct\r\ngoal, but a path-like missing value must fail instead of being reinterpreted as\r\na goal.\r\n\r\n## Read-Only Tools\r\n\r\n- `interview_state`: compact operational phase and version metadata.\r\n- `interview_search`: complete session, round, all-session, or keyword-matched\r\n  Kanban fact snapshots.\r\n- `kb_temp_get(information_type=\"deep_interview\")`: projected goal\u002Fruntime\r\n  state only.\r\n\r\n`interview_search` is independent from `interview_state` and never mutates the\r\nInterview. No legacy alias is registered.\r\n\r\n## Verification Checklist\r\n\r\n- Kanban facts commit before projection or visible continuation.\r\n- The projection has exactly three sections and matches `goal_state_version`.\r\n- Short feedback still receives strict Dynamic Context injection.\r\n- Projection failure pauses the Interview and blocks the model turn.\r\n- Future goals never replace the current goal.\r\n- Every assistant response ends with the Host-generated future-goals footer.\r\n- Importing Markdown creates a Kanban fact seed, not a specification.\r\n- Only AI `stop_interview` creates the final specification.\r\n- Native handoff uses the completed specification path\u002Frevision without a Deep\r\n  Interview digest, and Execute consumes the resulting frozen plan path rather\r\n  than the interview ID.\r\n","# Deep Interview Planning Workflows\r\n\r\n## Contract\r\n\r\nDeep Interview gathers explicit facts before implementation. `kanban.db` is the\r\nonly authority for the objective, feedback, hypotheses, decisions, future\r\ngoals, round snapshots, phase, and versions. Do not treat chat text,\r\n`kb_temp`, Dynamic Context, or a specification file as a replacement authority.\r\n\r\nThe Host projects only goal and runtime state to\r\n`kb_temp(information_type=\"deep_interview\")` in three atomic sections:\r\n`current_focus`, `current_progress`, and `future_needs`. AI may read this\r\nprojection through Dynamic Context but may not write it. The Host Projector is\r\nthe only writer.\r\n\r\n## Interview Turns\r\n\r\n1. Read the current Deep Interview block in Dynamic Context.\r\n2. Use `interview_search` when the complete Kanban fact snapshot is needed.\r\n3. Ask one concrete, falsifiable hypothesis about the current objective.\r\n4. Do not create a plan, specification, implementation graph, or approval\r\n   verdict during an interview round.\r\n5. Let the Host append the authoritative future-goals footer. Do not generate\r\n   that footer in the model response.\r\n\r\nExplicit feedback is classified by the AI Feedback Router as exactly one of:\r\n\r\n- `confirm_hypothesis`: record the confirmation and continue.\r\n- `reject_hypothesis`: record the correction and ask a revised hypothesis.\r\n- `goal_conflict`: keep the current goal and record the new goal as future work.\r\n- `stop_interview`: stop immediately and generate the final specification.\r\n\r\nThere is no independent Judge, review round, approval step, next-round approval,\r\nor stop confirmation.\r\n\r\n## Specification And Handoff\r\n\r\nOnly `stop_interview` may create a specification. The canonical location is:\r\n\r\n```text\r\nHERMES_HOME\u002Flancedb-memory\u002Fresource\u002Fspec\u002F\u003Ctitle>.md\r\n```\r\n\r\nThe specification is generated from the final Kanban fact snapshot and uses a\r\nmonotonic `spec_version`. Deep Interview does not compute a content hash or\r\ndigest.\r\n\r\nRun `hermes ultrawork plan \u003Cspec-path> [repository]` or\r\n`\u002Fultrawork plan \u003Cspec-path> [repository]` after the specification is\r\ncompleted. Plan accepts either the completed specification path or a direct\r\ngoal, but a path-like missing value must fail instead of being reinterpreted as\r\na goal.\r\n\r\n## Read-Only Tools\r\n\r\n- `interview_state`: compact operational phase and version metadata.\r\n- `interview_search`: complete session, round, all-session, or keyword-matched\r\n  Kanban fact snapshots.\r\n- `kb_temp_get(information_type=\"deep_interview\")`: projected goal\u002Fruntime\r\n  state only.\r\n\r\n`interview_search` is independent from `interview_state` and never mutates the\r\nInterview. No legacy alias is registered.\r\n\r\n## Verification Checklist\r\n\r\n- Kanban facts commit before projection or visible continuation.\r\n- The projection has exactly three sections and matches `goal_state_version`.\r\n- Short feedback still receives strict Dynamic Context injection.\r\n- Projection failure pauses the Interview and blocks the model turn.\r\n- Future goals never replace the current goal.\r\n- Every assistant response ends with the Host-generated future-goals footer.\r\n- Importing Markdown creates a Kanban fact seed, not a specification.\r\n- Only AI `stop_interview` creates the final specification.\r\n- Native handoff uses the completed specification path\u002Frevision without a Deep\r\n  Interview digest, and Execute consumes the resulting frozen plan path rather\r\n  than the interview ID.\r\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":38,"description":7},"Hermes Agent","2.0.0",{"hermes":27},{"tags":28,"related_skills":34},[29,30,31,32,33],"deep-interview","planning","kanban","specification","ultrawork",[35,36,37],"plan","durable-agent-orchestration","deep-interview-for-memory-injection",[39,40,41],"linux","macos","windows","main","a3f3199bb87ec3c91248f68a39d88527e1847ae9","skills\u002Fsoftware-development\u002Fdeep-interview-planning-workflows","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content","https:\u002F\u002Fgithub.com\u002Fchaorenex1","https:\u002F\u002Fblog.aduib.com","A programmer whose only hobby in life is coding","2026-10-20 00:34:32",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add chaorenex1\u002Fhermes-home-content --skill deep-interview-planning-workflows",{"tool":56,"command":57},"bunx","bunx skills add chaorenex1\u002Fhermes-home-content --skill deep-interview-planning-workflows",{"tool":59,"command":60},"pnpm","pnpm dlx skills add chaorenex1\u002Fhermes-home-content --skill deep-interview-planning-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fdeep-interview-planning-workflows\u002FSKILL.md",true,[],[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7F8GF32YD5MBQW2TGSRH1YP","web-retrieval-resilience","Web tools fail or search rules break: repair or fall back.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fweb-retrieval-resilience\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7F8FP46QESQMCZ1KBT3TW3R","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7F8ER6VXHBNVRQBZS7X08SE","verification-loop","Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS\u002FFAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7F8E4BQJ38KVQVM3MT20PYV","unreal-world-builder","开放世界与环境专家——精通 UE5 World Partition、Landscape、程序化植被、HLOD 和大规模关卡流式加载，打造无缝开放世界体验","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-world-builder\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7F8D747SQW2FTP7GBSX38BR","unreal-technical-artist","Unreal Engine 视觉管线专家——精通材质编辑器、Niagara 特效、程序化内容生成和 UE5 项目的美术到引擎管线","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-technical-artist\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7F8CKHYJVZVBTN0321J88T2","unreal-systems-engineer","性能与混合架构专家——精通 C++\u002FBlueprint 边界、Nanite 几何体、Lumen GI 和 Gameplay Ability System，面向 AAA 级 Unreal Engine 项目","https:\u002F\u002Fgithub.com\u002Fchaorenex1\u002Fhermes-home-content\u002Fblob\u002Fmain\u002Fskills\u002Funreal-engine\u002Funreal-systems-engineer\u002FSKILL.md",[],[]]