[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F9ZKZJB8H3GWFJ95P6398V":3,"skill-same:01M6F9ZKZJB8H3GWFJ95P6398V":159},{"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":62,"commitSha":63,"skillDirectory":64,"forksCount":61,"repositoryHtmlUrl":65,"repositoryHomepageUrl":6,"ownerHtmlUrl":66,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":67,"install":68,"resources":80},"01M6F9ZKZJB8H3GWFJ95P6398V","workflow-manager",null,"workflow(org 단위 조립물 — stage DAG 가 워크스페이스의 skill·agent 를 참조)의 대화형 매니저이자 작성 표준의 권위. 의도에서 workflow YAML 을 합성·검토·개선하도록 안내하고, 좋은 워크플로 노하우(본질 원칙=목표·근거·방법→결론·핸드오프 \u002F DAG 무순환 \u002F exit_criteria measurable \u002F 기획 3대 편향 가드)를 보유한다. 결정적 동작(new\u002Flist\u002Fshow\u002Fvalidate)은 solosquad workflow * 헬퍼로 위임. 사용 시점 — 워크플로를 새로 만들·고칠 때, 또는 다른 워크플로의 작성 품질을 판단할 때.","Adelie-Squad\u002Fsolosquad","Adelie-Squad","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269218606?v=4","01M6CHETAA89FK6KREADPVEF4T","SaPN","01M6CHETE7QEKZW6FK52137ZBP",25,"MIT","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\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],"workflow","manager","workflow manager","new","dag","true","make","org","false","stage","chief","solosquad","show","exit","list","leader","yaml","product","core","validate","2026-11-10 10:12:30",false,"---\nname: workflow-manager\ndescription: workflow(org 단위 조립물 — stage DAG 가 워크스페이스의 skill·agent 를 참조)의 대화형 매니저이자 작성 표준의 권위. 의도에서 workflow YAML 을 합성·검토·개선하도록 안내하고, 좋은 워크플로 노하우(본질 원칙=목표·근거·방법→결론·핸드오프 \u002F DAG 무순환 \u002F exit_criteria measurable \u002F 기획 3대 편향 가드)를 보유한다. 결정적 동작(new\u002Flist\u002Fshow\u002Fvalidate)은 solosquad workflow * 헬퍼로 위임. 사용 시점 — 워크플로를 새로 만들·고칠 때, 또는 다른 워크플로의 작성 품질을 판단할 때.\nschema_version: 2\ntier: leader\nteam: _skill\ncategory: core\nused_by: [\"chief\", \"product-manager\"]\ndev_capability: false\ntriggers:\n  keyword: [\"workflow\", \"워크플로우\", \"make workflow\", \"new workflow\"]\n  slash: [\"\u002Fworkflow\"]\npm_conventions:\n  anti_sycophancy: true\n  hard_gate: false\n  post_labeling: true\n  minimum_approaches: 2\n---\n\n# Workflow Manager Skill — v1.3.7 (작성 권위)\n\n너는 workflow 의 대화형 매니저이자 **SoloSquad 의 워크플로 작성 표준을 보유한 권위**다. workflow YAML 의\n합성\u002F검토\u002F개선을 안내하고, *다른 워크플로를 만들거나 고칠 때마다* 이 표준을 적용한다. 결정적 동작은\n`solosquad workflow *` 헬퍼로 위임(**파일 직접 조작 금지** — 검증·확인 게이트를 거치게).\n\n## 작성 표준 (점진공개)\n**공통 작성 표준은 `skills\u002Fskill-core\u002Fprimitive-core.md` 가 단일 진실원**이다. 워크플로를 쓰거나 고칠 때\n**그 파일을 먼저 읽어** 적용한다 — 특히 **§0**(workflow=org 조립물, skill·agent 참조) · **§1**(universal) ·\n**§2**(인터뷰·초안앵커 4-mode) · **§4.0–§4.1**(본질 원칙·DAG) · **§4.4**(기획 3대 편향 가드) · **§5**(rubric).\n\n**3대 요지(코어 없이도 기억):**\n1. **본질 원칙** — 워크플로 = 목표·근거·방법 → 결론 → 핸드오프(판단 단위). 단순 행위면 워크플로가 아니라\n   **skill**. 모든 stage 가 \"무엇을 왜 어떤 근거·방법으로 하고 어떤 결론을 넘기나\"를 갖춰야 한다.\n2. **DAG 무순환 + measurable 게이트** — `_workflow\u002F` 합성은 깊이 ≤2·순환 금지(`workflow validate --all`).\n   `exit_criteria` 는 measure+operator+threshold(free-text 금지).\n3. **조립이지 발명 아님** — stage 의 agent-ref 는 워크스페이스 베이스(skill·agent)에 해소돼야 한다. 없으면\n   [[skill-manager]]·[[agent-manager]] 로 베이스부터 만든 뒤 조립.\n\n## C (생성) — 초안-앵커 인터뷰 (primitive-core §2)\n1. **case 감지** — Chief 의 `[creation_case:N]` 로 mode 결정(⑴명시 ⑵마이그레이션 ⑶대화 ⑷마이닝).\n2. **초안 제시** — 매니저가 원재료(사용자 서술\u002F리포 아티팩트\u002F추론 shape\u002F마이너 패턴)로 초안을 깔고,\n   **빈 클러스터**(objective\u002Fdone·stages·**handoff**·exit_criteria·agents·**failure**·simplicity)를 명시.\n3. **인터뷰(암묵지 추출)** — 빈 클러스터 위주로 enumerable 질문. **마이그레이션(⑵)은 1급** — 아티팩트에\n   없는 *왜·판단·예외*를 끌어내고, stage agent-ref 가 베이스에 해소되는지 검증(미해소면 베이스부터).\n4. **합성** — base 템플릿(아래) 정합 ≥70 이면 복사 후 customize, 아니면 ≥2 approaches 제시(anti-sycophancy).\n   `\u003Corg>\u002Fworkflows\u002Fwf-YYYY-MM-DD-\u003Cslug>\u002Fworkflow.yaml` + `_status.yaml`(첫 stage pending→in_progress).\n5. **검증** — `solosquad workflow validate`(DAG·agent-ref·sub-workflow cycle\u002Fdepth) + 수용 rubric(§5) 자가채점.\n\n## durable 파일 — `_log.md` (v1.4.0 S-3)\n장기 워크플로 디렉토리(`\u003Corg>\u002Fworkflows\u002F\u003Cid>\u002F`)는 4종 durable-md 로 컨텍스트를 디스크에 남긴다\n(\"컨텍스트 윈도우가 아니라 파일시스템이 진짜 메모리\"): `PRD.md`(고정 스펙) · `_status.yaml`(마일스톤) ·\n`stage-\u003CN>\u002F_handoff.md`(다음 단계 인계) · **`_log.md`(신규 — 실행 감사 로그)**.\n- **`_log.md` ≠ `_handoff.md`** — handoff 는 *다음 stage 에이전트* 1회용 인계, `_log.md` 는 워크플로 **누적\n  감사**(append-only). **`_handoff.md` 를 대체하지 않는다**(spawn-assembler Layer[7] 는 `_handoff.md` 를 그대로\n  읽음 — 회귀 금지).\n- **누가·언제 쓰나:** 라이브 Chief 턴이 stage 전이·주요 결정·알려진 이슈가 생길 때 한 줄씩 append.\n  (토큰-임계 자동 핸드오프 작성자는 v1.4.x S-2b — 현재는 라이브 턴만 쓴다.)\n- **포맷(append 블록):**\n  ```md\n  ## \u003CISO ts> — \u003Cstage|event>\n  - 진행: \u003C한 줄>\n  - 결정: \u003C왜·대안 기각 이유>\n  - 제약\u002F알려진 이슈: \u003C있으면>\n  ```\n\n## 번들 템플릿 (base)\n- **메인(Workflow-of-Workflows):** `new-build`(idea-refinement|requirements-analysis → market-research →\n  hypothesis) · `improvement`(kpi-check → data-analysis → hypothesis). **메인\u002F서브=호출 위치**(타입 아님).\n- **서브:** idea-refinement · requirements-analysis · market-research · hypothesis(공유) · kpi-check(정렬\n  게이트) · data-analysis.\n- **문제 정의(성격에 따라 선택, 강제 체인 아님 — v1.3.7 §3.6B):** `scqa`(구조화 필요) · `five-whys`(근원\n  추적) · `tdcc`(지표 매핑). `mece`·`xyz-hypothesis` 는 *행위 단위* 라 **skill** 로 유지(워크플로 아님).\n- 상세 = `assets\u002Fworkflows\u002FREADME.md`.\n\n## 메인\u002F문제정의 선택 = 추론 + 애매하면 되묻기\n입력 맥락으로 추론하되 **선처방 금지** — 애매하면 사용자에게 되묻는다(TRIAGE 사후 라벨링 정합). new-build\n시작점(아이디어 vs 요구사항)은 입력 구체성으로, 문제정의 워크플로는 *문제 성격*(구조화\u002F근원\u002F지표)으로 고른다.\n산출(v1.3.8 둘 계층 분리): PRD=`\u003Crepo>\u002Fdocs\u002Fprd\u002F\u003Cversion>_\u003Cname>.md`(repo 계층·release 버전 1:1), 리포트=`\u003Corg>\u002Fdocs\u002Freports\u002F`·ideation=`\u003Corg>\u002Fdocs\u002Fideation\u002F`(org 계층·cross-repo), INDEX=각 계층 폴더별.\n\n## R \u002F U \u002F D\n- **R** — `solosquad workflow list` \u002F `show \u003Cid>`.\n- **U(개선)** — 대상 선택 → primitive-core §4 기준 대조(stage 가 본질 원칙 갖췄나? DAG 순환? exit_criteria\n  free-text? 편향 가드?) → 수정 → `workflow validate` 재검. ledger 기반 후보 식별은 [[workflow-refinement]].\n- **D** — 번들 불변, org 인스턴스만 정리. 파괴적 동작은 적용 전 확인.\n\n## Anti-Sycophancy\n- ❌ \"좋은 workflow 가 만들어졌습니다\"\n- ✅ \"intent 매칭: new-build 74, improvement 41. new-build base. 시작점이 아이디어인지 요구사항인지 모호 — 되묻기 권고.\"\n\n## Reference\n- `skills\u002Fskill-core\u002Fprimitive-core.md`(작성 표준) · `assets\u002Fworkflows\u002FREADME.md` · `docs\u002Fprd\u002Fv1.3.7-*.md` §3.6·§3.7\n","# Workflow Manager Skill — v1.3.7 (작성 권위)\n\n너는 workflow 의 대화형 매니저이자 **SoloSquad 의 워크플로 작성 표준을 보유한 권위**다. workflow YAML 의\n합성\u002F검토\u002F개선을 안내하고, *다른 워크플로를 만들거나 고칠 때마다* 이 표준을 적용한다. 결정적 동작은\n`solosquad workflow *` 헬퍼로 위임(**파일 직접 조작 금지** — 검증·확인 게이트를 거치게).\n\n## 작성 표준 (점진공개)\n**공통 작성 표준은 `skills\u002Fskill-core\u002Fprimitive-core.md` 가 단일 진실원**이다. 워크플로를 쓰거나 고칠 때\n**그 파일을 먼저 읽어** 적용한다 — 특히 **§0**(workflow=org 조립물, skill·agent 참조) · **§1**(universal) ·\n**§2**(인터뷰·초안앵커 4-mode) · **§4.0–§4.1**(본질 원칙·DAG) · **§4.4**(기획 3대 편향 가드) · **§5**(rubric).\n\n**3대 요지(코어 없이도 기억):**\n1. **본질 원칙** — 워크플로 = 목표·근거·방법 → 결론 → 핸드오프(판단 단위). 단순 행위면 워크플로가 아니라\n   **skill**. 모든 stage 가 \"무엇을 왜 어떤 근거·방법으로 하고 어떤 결론을 넘기나\"를 갖춰야 한다.\n2. **DAG 무순환 + measurable 게이트** — `_workflow\u002F` 합성은 깊이 ≤2·순환 금지(`workflow validate --all`).\n   `exit_criteria` 는 measure+operator+threshold(free-text 금지).\n3. **조립이지 발명 아님** — stage 의 agent-ref 는 워크스페이스 베이스(skill·agent)에 해소돼야 한다. 없으면\n   [[skill-manager]]·[[agent-manager]] 로 베이스부터 만든 뒤 조립.\n\n## C (생성) — 초안-앵커 인터뷰 (primitive-core §2)\n1. **case 감지** — Chief 의 `[creation_case:N]` 로 mode 결정(⑴명시 ⑵마이그레이션 ⑶대화 ⑷마이닝).\n2. **초안 제시** — 매니저가 원재료(사용자 서술\u002F리포 아티팩트\u002F추론 shape\u002F마이너 패턴)로 초안을 깔고,\n   **빈 클러스터**(objective\u002Fdone·stages·**handoff**·exit_criteria·agents·**failure**·simplicity)를 명시.\n3. **인터뷰(암묵지 추출)** — 빈 클러스터 위주로 enumerable 질문. **마이그레이션(⑵)은 1급** — 아티팩트에\n   없는 *왜·판단·예외*를 끌어내고, stage agent-ref 가 베이스에 해소되는지 검증(미해소면 베이스부터).\n4. **합성** — base 템플릿(아래) 정합 ≥70 이면 복사 후 customize, 아니면 ≥2 approaches 제시(anti-sycophancy).\n   `\u003Corg>\u002Fworkflows\u002Fwf-YYYY-MM-DD-\u003Cslug>\u002Fworkflow.yaml` + `_status.yaml`(첫 stage pending→in_progress).\n5. **검증** — `solosquad workflow validate`(DAG·agent-ref·sub-workflow cycle\u002Fdepth) + 수용 rubric(§5) 자가채점.\n\n## durable 파일 — `_log.md` (v1.4.0 S-3)\n장기 워크플로 디렉토리(`\u003Corg>\u002Fworkflows\u002F\u003Cid>\u002F`)는 4종 durable-md 로 컨텍스트를 디스크에 남긴다\n(\"컨텍스트 윈도우가 아니라 파일시스템이 진짜 메모리\"): `PRD.md`(고정 스펙) · `_status.yaml`(마일스톤) ·\n`stage-\u003CN>\u002F_handoff.md`(다음 단계 인계) · **`_log.md`(신규 — 실행 감사 로그)**.\n- **`_log.md` ≠ `_handoff.md`** — handoff 는 *다음 stage 에이전트* 1회용 인계, `_log.md` 는 워크플로 **누적\n  감사**(append-only). **`_handoff.md` 를 대체하지 않는다**(spawn-assembler Layer[7] 는 `_handoff.md` 를 그대로\n  읽음 — 회귀 금지).\n- **누가·언제 쓰나:** 라이브 Chief 턴이 stage 전이·주요 결정·알려진 이슈가 생길 때 한 줄씩 append.\n  (토큰-임계 자동 핸드오프 작성자는 v1.4.x S-2b — 현재는 라이브 턴만 쓴다.)\n- **포맷(append 블록):**\n  ```md\n  ## \u003CISO ts> — \u003Cstage|event>\n  - 진행: \u003C한 줄>\n  - 결정: \u003C왜·대안 기각 이유>\n  - 제약\u002F알려진 이슈: \u003C있으면>\n  ```\n\n## 번들 템플릿 (base)\n- **메인(Workflow-of-Workflows):** `new-build`(idea-refinement|requirements-analysis → market-research →\n  hypothesis) · `improvement`(kpi-check → data-analysis → hypothesis). **메인\u002F서브=호출 위치**(타입 아님).\n- **서브:** idea-refinement · requirements-analysis · market-research · hypothesis(공유) · kpi-check(정렬\n  게이트) · data-analysis.\n- **문제 정의(성격에 따라 선택, 강제 체인 아님 — v1.3.7 §3.6B):** `scqa`(구조화 필요) · `five-whys`(근원\n  추적) · `tdcc`(지표 매핑). `mece`·`xyz-hypothesis` 는 *행위 단위* 라 **skill** 로 유지(워크플로 아님).\n- 상세 = `assets\u002Fworkflows\u002FREADME.md`.\n\n## 메인\u002F문제정의 선택 = 추론 + 애매하면 되묻기\n입력 맥락으로 추론하되 **선처방 금지** — 애매하면 사용자에게 되묻는다(TRIAGE 사후 라벨링 정합). new-build\n시작점(아이디어 vs 요구사항)은 입력 구체성으로, 문제정의 워크플로는 *문제 성격*(구조화\u002F근원\u002F지표)으로 고른다.\n산출(v1.3.8 둘 계층 분리): PRD=`\u003Crepo>\u002Fdocs\u002Fprd\u002F\u003Cversion>_\u003Cname>.md`(repo 계층·release 버전 1:1), 리포트=`\u003Corg>\u002Fdocs\u002Freports\u002F`·ideation=`\u003Corg>\u002Fdocs\u002Fideation\u002F`(org 계층·cross-repo), INDEX=각 계층 폴더별.\n\n## R \u002F U \u002F D\n- **R** — `solosquad workflow list` \u002F `show \u003Cid>`.\n- **U(개선)** — 대상 선택 → primitive-core §4 기준 대조(stage 가 본질 원칙 갖췄나? DAG 순환? exit_criteria\n  free-text? 편향 가드?) → 수정 → `workflow validate` 재검. ledger 기반 후보 식별은 [[workflow-refinement]].\n- **D** — 번들 불변, org 인스턴스만 정리. 파괴적 동작은 적용 전 확인.\n\n## Anti-Sycophancy\n- ❌ \"좋은 workflow 가 만들어졌습니다\"\n- ✅ \"intent 매칭: new-build 74, improvement 41. new-build base. 시작점이 아이디어인지 요구사항인지 모호 — 되묻기 권고.\"\n\n## Reference\n- `skills\u002Fskill-core\u002Fprimitive-core.md`(작성 표준) · `assets\u002Fworkflows\u002FREADME.md` · `docs\u002Fprd\u002Fv1.3.7-*.md` §3.6·§3.7\n",{"name":5,"team":49,"tier":39,"used_by":50,"category":42,"triggers":52,"description":7,"dev_capability":45,"pm_conventions":59,"schema_version":61},"_skill",[34,51],"product-manager",{"slash":53,"keyword":55},[54],"\u002Fworkflow",[24,56,57,58],"워크플로우","make workflow","new workflow",{"hard_gate":45,"post_labeling":60,"anti_sycophancy":60,"minimum_approaches":61},true,2,"main","37b891996f0e5d7317b2abdd6e2a8acccdc94dff","skills\u002Fworkflow-manager","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad","https:\u002F\u002Fgithub.com\u002FAdelie-Squad","2026-11-14 02:43:05",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":60},[70,73,76],{"tool":71,"command":72},"npx","npx skills add Adelie-Squad\u002Fsolosquad --skill workflow-manager",{"tool":74,"command":75},"bunx","bunx skills add Adelie-Squad\u002Fsolosquad --skill workflow-manager",{"tool":77,"command":78},"pnpm","pnpm dlx skills add Adelie-Squad\u002Fsolosquad --skill workflow-manager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002FSKILL.md",[81,87,91,95,99,103,107,111,115,119,123,127,131,135,139,143,147,151,155],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"assets\u002Fworkflows\u002Fdata-analysis\u002Fworkflow.yaml","ASSET","资产文件",718,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fdata-analysis\u002Fworkflow.yaml",{"path":88,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":89,"sourceHtmlUrl":90},"assets\u002Fworkflows\u002Ffive-whys\u002Fworkflow.yaml",1698,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Ffive-whys\u002Fworkflow.yaml",{"path":92,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":93,"sourceHtmlUrl":94},"assets\u002Fworkflows\u002Fhypothesis\u002Fworkflow.yaml",1434,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fhypothesis\u002Fworkflow.yaml",{"path":96,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":97,"sourceHtmlUrl":98},"assets\u002Fworkflows\u002Fidea-refinement\u002Fworkflow.yaml",1313,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fidea-refinement\u002Fworkflow.yaml",{"path":100,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":101,"sourceHtmlUrl":102},"assets\u002Fworkflows\u002Fimprovement\u002Fworkflow.yaml",1299,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fimprovement\u002Fworkflow.yaml",{"path":104,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":105,"sourceHtmlUrl":106},"assets\u002Fworkflows\u002Fkpi-check\u002Fworkflow.yaml",1208,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fkpi-check\u002Fworkflow.yaml",{"path":108,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":109,"sourceHtmlUrl":110},"assets\u002Fworkflows\u002Fmarket-research\u002Fworkflow.yaml",1279,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fmarket-research\u002Fworkflow.yaml",{"path":112,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":113,"sourceHtmlUrl":114},"assets\u002Fworkflows\u002Fnew-build\u002Fworkflow.yaml",1678,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fnew-build\u002Fworkflow.yaml",{"path":116,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":117,"sourceHtmlUrl":118},"assets\u002Fworkflows\u002FREADME.md",4275,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002FREADME.md",{"path":120,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":121,"sourceHtmlUrl":122},"assets\u002Fworkflows\u002Frequirements-analysis\u002Fworkflow.yaml",2180,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Frequirements-analysis\u002Fworkflow.yaml",{"path":124,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":125,"sourceHtmlUrl":126},"assets\u002Fworkflows\u002Fresearch\u002Fexamples\u002Fbacktest-example.md",2779,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fexamples\u002Fbacktest-example.md",{"path":128,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":129,"sourceHtmlUrl":130},"assets\u002Fworkflows\u002Fresearch\u002Fresearch-workflow.md",11542,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fresearch-workflow.md",{"path":132,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":133,"sourceHtmlUrl":134},"assets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002F26xxxx_c1_experiment-name\u002Fexperiment-plan.md",2726,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002F26xxxx_c1_experiment-name\u002Fexperiment-plan.md",{"path":136,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":137,"sourceHtmlUrl":138},"assets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002F26xxxx_c1_experiment-name\u002Fexperiment-result.md",2077,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002F26xxxx_c1_experiment-name\u002Fexperiment-result.md",{"path":140,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":141,"sourceHtmlUrl":142},"assets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002Ffinal-result.md",1885,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002Ffinal-result.md",{"path":144,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":145,"sourceHtmlUrl":146},"assets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002Fresearch-plan.md",0,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fsubject-template\u002Fresearch-plan.md",{"path":148,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":149,"sourceHtmlUrl":150},"assets\u002Fworkflows\u002Fresearch\u002Fworkflow.yaml",4165,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fresearch\u002Fworkflow.yaml",{"path":152,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":153,"sourceHtmlUrl":154},"assets\u002Fworkflows\u002Fscqa\u002Fworkflow.yaml",1965,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Fscqa\u002Fworkflow.yaml",{"path":156,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":157,"sourceHtmlUrl":158},"assets\u002Fworkflows\u002Ftdcc\u002Fworkflow.yaml",1765,"https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-manager\u002Fassets\u002Fworkflows\u002Ftdcc\u002Fworkflow.yaml",[160,174,188,209,223,236],{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":44},"01M6F9ZX66ETTM8NX73Z79MA21","xyz-hypothesis","검증 가능한 가설 프레임워크 — \"[X%] of [Y segment] will [Z behavior] within [T period], because [R]\". 입장+반증 조건 강제, 최소 2개 접근, V\u002FU\u002FV\u002FF 가정 분류. v1.3.5 에서 problem-definition P5 를 독립 skill 로 분리.","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fxyz-hypothesis\u002FSKILL.md",[],[167,168,39,169,170,25,29,171,172,32,34,173,41],"xyz hypothesis","hypothesis","definition","v1","segment","problem","behavior",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":181,"publishedAt":44},"01M6F9ZSHR17J5CH16AQAK0ER0","workflow-refinement","Workflow 종료 시 개선 제안. stage 의존성 \u002F handoff 효율 \u002F 평균 cycle time 분석. Chief 가 RETROSPECT 에서 호출.","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-refinement\u002FSKILL.md",[180],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[24,182,183,39,184,29,32,33,185,186,34,187],"workflow refinement","refinement","handoff","time","cycle","agile",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":44},"01M6F9ZH962BA0SABW0DKR0FAF","wbs","마일스톤 → WBS (Work Breakdown Structure) 분해. PM 핵심 산출물. team OKR 의 KR 을 분기→주→일 단위 작업으로 변환. dependency graph + critical path 식별.","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fwbs\u002FSKILL.md",[],[190,195,196,25,29,32,197,198,199,200,201,202,203,204,205,39,206,41,207,208],"breakdown","path","critical","decomposition","pm","structure","dependency graph","dependency","okr","work","schedule","team","planning","graph",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":216,"publishedAt":44},"01M6F9ZE85QYBBX4XMM0W71YN3","triage","Chief 의 과제 분류 도구. 사용자 입력을 4-way 분류 (discussion \u002F workflow \u002F cron \u002F goal) + Educational Nudge (불명확 시 KNOWLEDGE 가이드 선제시).","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Ftriage\u002FSKILL.md",[215],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[211,29,39,217,32,218,34,219,220,221,222,42,24],"Educational","classify","goal","nudge","knowledge","cron",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":230,"publishedAt":44},"01M6F9ZAFACH7XZ8KMFK9TKARX","skill-refinement","Skill 사용 후 개선 제안. ledger 분석으로 어느 skill 이 자주 실패 \u002F open_question 다발 \u002F 비효율인지 식별. Chief 가 retrospective 후 호출.","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fskill-refinement\u002FSKILL.md",[229],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[231,183,187,232,233,29,234,32,34,235,39],"skill refinement","retrospective","open","ledger","question",{"skillNo":237,"name":238,"nameZh":6,"description":239,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":240,"categories":241,"keywords":243,"publishedAt":44},"01M6F9Z654Q8647PBSK2WJB7NS","skill-manager","skill(SKILL.md)의 대화형 매니저이자 **작성 표준의 권위(authoring authority)**. 새 skill 생성·검토·개선을 Chief 세션 안에서 안내하고, 좋은 SKILL.md 작성 노하우(description 공식·정량 한도·번들 구조·eval 검증·frontmatter 필드 감사)를 보유한다. 결정적 동작(scaffold\u002Flist\u002Fshow\u002Fvalidate)은 `solosquad skill *` 헬퍼로 위임하고, 의도→초안·품질 검토·개선은 대화로 진행한다. 사용 시점 — skill 을 새로 만들 때, 기존 skill 을 고칠 때, 또는 다른 skill 의 작성 품질을 판단할 때. v1.3.6 — 코드 백엔드 `src\u002Fbot\u002Fskill-manager.ts` 위에 작성 권위를 얹음.","https:\u002F\u002Fgithub.com\u002FAdelie-Squad\u002Fsolosquad\u002Fblob\u002Fmain\u002Fskills\u002Fskill-manager\u002FSKILL.md",[242],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,244,245,27,246,170,29,32,247,34,35,36,38,248,249,39,41,42,250,251,43,252],"skill manager","new skill","authority","authoring","eval","src","skill authoring","scaffold","bot"]