Run any Skill in Manus with one click

handoff

Stars1

Forks2

UpdatedJune 14, 2026 at 08:24

Export an approved Build Gate brief to the downstream coding ecosystem you actually use — Spec-Kit (specs/NNN-slug/{spec,plan,tasks}.md), Kiro (.kiro/specs/<slug>/{requirements,design,tasks}.md), GStack (/office-hours brief), or Claude Code (AGENTS.md + CLAUDE.md). Use when Evidence + Product + Build Gate have all been approved and you're ready to start implementation in your coding agent of choice.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

kimsanguine

kimsanguine/hplan

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

5 files

SKILL.md

readonly

name	handoff
description	Export an approved Build Gate brief to the downstream coding ecosystem you actually use — Spec-Kit (specs/NNN-slug/{spec,plan,tasks}.md), Kiro (.kiro/specs/<slug>/{requirements,design,tasks}.md), GStack (/office-hours brief), or Claude Code (AGENTS.md + CLAUDE.md). Use when Evidence + Product + Build Gate have all been approved and you're ready to start implementation in your coding agent of choice.
argument-hint	[brief.json] [--target spec-kit\|kiro\|gstack\|claude\|all]
allowed-tools	["Read","Write","Bash"]
model	inherit

Handoff — Build Gate → Downstream Coding Ecosystem

Running for: $ARGUMENTS

Core Goal

hplan은 단독 도구가 아니라 전처리기. Build Gate가 통과하면 결과물을 spec-kit / kiro / gstack / claude code 어느 곳으로든 export.
단일 brief JSON → 4개 생태계 동시 export 가능 (--target all).
각 생태계의 네이티브 컨벤션 (spec-kit의 specs/NNN-slug/, Kiro의 .kiro/specs/) 그대로 따름.

Trigger Gate

Use This Skill When

Evidence + Product + Build Gate 모두 approved
COGS sentinel GREEN 또는 CONDITIONAL_GO with mitigations
사용자가 명시적으로 "이제 Spec-Kit으로 가자" / "Kiro에서 구현" / "GStack /office-hours로"
팀 전체 onboarding — AGENTS.md + CLAUDE.md를 새 repo에 박을 때

Route to Other Skills When

Build Gate 미통과 → 거꾸로 가서 cogs-sentinel, decision-log 확인
Export 후 spec-kit/kiro 안에서의 개별 task 분해 → 각 생태계 native tool
Export 후 PRD shape 정교화 → deliver/prd

Boundary Checks

❌ hooks/gate_guard.py가 활성화된 프로젝트에서 Build Gate 미승인 → handoff 호출 차단 (의도된 동작).
❌ 단일 target만 지정해도 다른 target은 영향 받지 않음 (idempotent per target).

Inputs

python3 hplan/scripts/export_handoff.py brief.json --target all --root .

{
  "product_name": "SocialDraft",
  "problem": "1인 마케터가 SNS 게시글당 30-45분을 쓰는데 캠페인 데드라인을 자주 놓친다",
  "icp": "주 10건+ SNS 콘텐츠 직접 작성하는 1인 마케터 (현재 범용 AI 챗봇 수동 사용)",
  "jtbd": "When 미팅 끝나자마자, I want 액션 + 메일, so I can 같은 날 답신",
  "functional_requirements": [...],
  "acceptance_criteria": [...],
  "cogs_ceiling": "$2.70/paid user/month",
  "latency_budget": "p95 < 90초",
  "counter_position": "범용 AI 챗봇은 단발성 답변, SocialDraft는 브랜드 톤 학습 + 5개 동시 생성",
  "not_build": ["일반 음성 받아쓰기", "CRM first-class"],
  "mvp_slice": "Zoom 종료 → 1분 안에 액션 + 메일",
  "decision": "build"
}

Steps

Confirm Build Gate decision is build or CONDITIONAL_GO in decision-log.
Confirm cogs-sentinel result is GREEN (or CONDITIONAL_GO with mitigations).
Run export_handoff.py <brief.json> --target <target>.
Verify generated files at harness/exports/<target>/.
Copy or symlink to actual project directory (spec-kit at repo root, kiro at .kiro/, etc.).

Outputs

Target	Path
spec-kit	`harness/exports/spec-kit/specs/NNN-slug/{spec,plan,tasks}.md`
kiro	`harness/exports/kiro/.kiro/specs/<slug>/{requirements,design,tasks}.md`
gstack	`harness/exports/gstack/office-hours-brief.md`
claude	`harness/exports/claude/AGENTS.md` + `CLAUDE.md`

Verification

All requested target files exist after run
spec-kit specs/NNN-slug/ uses auto-incremented NNN
Kiro .kiro/specs/<slug>/ exists with 3 files
GStack brief includes "Next GStack Steps" section
Claude AGENTS.md mentions COGS sentinel as build gate

More from this repository

same repository

design-token

kimsanguine/hplan

2-step 디자인 파이프라인: --step brief (타겟 분석 → DESIGN_BRIEF.md 생성) → --step token (토큰/DESIGN.md 생성). --step all이 기본값.

2026-06-141

memory-arch

kimsanguine/hplan

Design an agent memory system — working memory, episodic memory, semantic memory, and procedural memory. Use when building agents that need to remember context across sessions, learn from interactions, or maintain persistent knowledge. Covers storage strategy, retrieval patterns, and context management.

2026-06-141

orchestration

kimsanguine/hplan

Select and design the right orchestration pattern for multi-agent systems. Evaluate Sequential, Parallel, Router, and Hierarchical patterns against your use case requirements. The Router pattern covers both agent selection (classify input to the right specialist) and model selection (route tasks to the right LLM by complexity to balance cost, latency, quality, and fallback chains). Use when deciding how multiple agents should coordinate, share context, delegate tasks, or which model each task should run on.

2026-06-141

strategy

kimsanguine/hplan

전략 설계 통합 — 비즈니스 모델 캔버스(biz-model), 경쟁 해자 분석(moat), 성장 루프 설계(growth-loop) 통합. Use when defining business strategy, competitive positioning, or growth mechanics for an AI product.

2026-06-141

agent-setup

kimsanguine/hplan

에이전트 환경 설정 통합 — 7요소 인스트럭션 작성(agent-instructions)과 CLAUDE.md/AGENTS.md 구성(claude-md) 통합. 에이전트 정체성·도구·제약·실패 모드 정의부터 프로젝트 메모리 파일까지 한 스킬로. Use when setting up a new agent or updating agent instructions.

2026-06-141

ask-team

kimsanguine/hplan

PM이 사람에게 질문하고 답을 모으는 비동기 채널 — comms MCP(Gmail/Notion/Zoom/Slack)를 감싸는 번역기. --mode ask(질문 초안 작성), --mode pull-answers(스레드·회의록에서 답 수집), --mode digest(수집한 답 요약 → decision-log/ticket-bridge 라우팅), --mode review(PRD 스테이크홀더 리뷰 — 리뷰어 배정·코멘트 수집·Signoff audit trail), --mode solo(팀원 없을 때 Claude가 역할 대리 시뮬레이션), --mode init(팀 세팅 대화형 온보딩). 메시지를 자동 발송하지 않는다 — 초안/코멘트까지만. 솔로 유저는 solo, 기업 PM은 review로 분기. Use when a PM needs to ask teammates for status/decisions, run a multi-stakeholder PRD review, and collect answers into hplan.

2026-06-141

name	handoff
description	Export an approved Build Gate brief to the downstream coding ecosystem you actually use — Spec-Kit (specs/NNN-slug/{spec,plan,tasks}.md), Kiro (.kiro/specs/<slug>/{requirements,design,tasks}.md), GStack (/office-hours brief), or Claude Code (AGENTS.md + CLAUDE.md). Use when Evidence + Product + Build Gate have all been approved and you're ready to start implementation in your coding agent of choice.
argument-hint	[brief.json] [--target spec-kit\|kiro\|gstack\|claude\|all]
allowed-tools	["Read","Write","Bash"]
model	inherit

Handoff — Build Gate → Downstream Coding Ecosystem

Running for: $ARGUMENTS

Core Goal

hplan은 단독 도구가 아니라 전처리기. Build Gate가 통과하면 결과물을 spec-kit / kiro / gstack / claude code 어느 곳으로든 export.
단일 brief JSON → 4개 생태계 동시 export 가능 (--target all).
각 생태계의 네이티브 컨벤션 (spec-kit의 specs/NNN-slug/, Kiro의 .kiro/specs/) 그대로 따름.

Trigger Gate

Use This Skill When

Evidence + Product + Build Gate 모두 approved
COGS sentinel GREEN 또는 CONDITIONAL_GO with mitigations
사용자가 명시적으로 "이제 Spec-Kit으로 가자" / "Kiro에서 구현" / "GStack /office-hours로"
팀 전체 onboarding — AGENTS.md + CLAUDE.md를 새 repo에 박을 때

Route to Other Skills When

Build Gate 미통과 → 거꾸로 가서 cogs-sentinel, decision-log 확인
Export 후 spec-kit/kiro 안에서의 개별 task 분해 → 각 생태계 native tool
Export 후 PRD shape 정교화 → deliver/prd

Boundary Checks

❌ hooks/gate_guard.py가 활성화된 프로젝트에서 Build Gate 미승인 → handoff 호출 차단 (의도된 동작).
❌ 단일 target만 지정해도 다른 target은 영향 받지 않음 (idempotent per target).

Inputs

python3 hplan/scripts/export_handoff.py brief.json --target all --root .

{
  "product_name": "SocialDraft",
  "problem": "1인 마케터가 SNS 게시글당 30-45분을 쓰는데 캠페인 데드라인을 자주 놓친다",
  "icp": "주 10건+ SNS 콘텐츠 직접 작성하는 1인 마케터 (현재 범용 AI 챗봇 수동 사용)",
  "jtbd": "When 미팅 끝나자마자, I want 액션 + 메일, so I can 같은 날 답신",
  "functional_requirements": [...],
  "acceptance_criteria": [...],
  "cogs_ceiling": "$2.70/paid user/month",
  "latency_budget": "p95 < 90초",
  "counter_position": "범용 AI 챗봇은 단발성 답변, SocialDraft는 브랜드 톤 학습 + 5개 동시 생성",
  "not_build": ["일반 음성 받아쓰기", "CRM first-class"],
  "mvp_slice": "Zoom 종료 → 1분 안에 액션 + 메일",
  "decision": "build"
}

Steps

Confirm Build Gate decision is build or CONDITIONAL_GO in decision-log.
Confirm cogs-sentinel result is GREEN (or CONDITIONAL_GO with mitigations).
Run export_handoff.py <brief.json> --target <target>.
Verify generated files at harness/exports/<target>/.
Copy or symlink to actual project directory (spec-kit at repo root, kiro at .kiro/, etc.).

Outputs

Target	Path
spec-kit	`harness/exports/spec-kit/specs/NNN-slug/{spec,plan,tasks}.md`
kiro	`harness/exports/kiro/.kiro/specs/<slug>/{requirements,design,tasks}.md`
gstack	`harness/exports/gstack/office-hours-brief.md`
claude	`harness/exports/claude/AGENTS.md` + `CLAUDE.md`

Verification

All requested target files exist after run
spec-kit specs/NNN-slug/ uses auto-incremented NNN
Kiro .kiro/specs/<slug>/ exists with 3 files
GStack brief includes "Next GStack Steps" section
Claude AGENTS.md mentions COGS sentinel as build gate