run-blueprint

사용 방법

설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.

npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill run-blueprint

시작 전 확인

설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.

원본 Skill 문서

원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.

Run Blueprint

Execute all tasks in a blueprint plan sequentially, respecting dependencies.

Input

plan_path: $ARGUMENTS (required)

Task Tracking Setup

TASK_TRACKING = config_read("task_tracking.enabled", "false")

If TASK_TRACKING:
  BLUEPRINT_ID = "run-blueprint-{timestamp}"
  TASK_MAP = {}  # Maps T1, T2 etc to Claude Task IDs

Workflow

1. Load Blueprint

Read(file_path: plan_path)

Parse the ## Implementation Tasks section:

ID	Task	Points	Dependencies	Status
T1	Setup auth middleware	2	-	⏳
T2	Create login endpoint	2	T1	⏳

Task status icons:

⏳ Pending
🔄 In Progress
✅ Completed
🔴 Failed

1.5. Create Tasks from Table (if tracking enabled)

If TASK_TRACKING:
  For each ROW in implementation_tasks:
    TASK = TaskCreate:
      subject: "{ROW.id}: {ROW.task}"
      activeForm: "Building {ROW.task}"
      metadata: {blueprint_id: BLUEPRINT_ID, task_id: ROW.id, points: ROW.points, source: plan_path}
    TASK_MAP[ROW.id] = TASK.id

  # Set up dependencies
  For each ROW in implementation_tasks where ROW.dependencies != "-":
    BLOCKED_BY = [TASK_MAP[dep] for dep in ROW.dependencies.split(",")]
    TaskUpdate(TASK_MAP[ROW.id], addBlockedBy: BLOCKED_BY)

2. Find Next Task

If TASK_TRACKING:
  TASKS = TaskList()
  BLUEPRINT_TASKS = filter(TASKS, task.metadata.blueprint_id == BLUEPRINT_ID)
  NEXT_TASK = first(BLUEPRINT_TASKS where status == "pending" AND blockedBy.length == 0)
Else:
  For each task in Implementation Tasks:
    If task.status == ⏳:
      If task.dependencies all ✅:
        NEXT_TASK = task
        Break

If no task found (all ✅ or 🔴): Go to Step 5.

3. Execute Task

Skill("build-task") "{task.id}" --no-ship

4. Update Status

If TASK_TRACKING:
  CLAUDE_TASK_ID = TASK_MAP[NEXT_TASK.id]
  TaskUpdate(CLAUDE_TASK_ID, status: "in_progress")
  # After build completes
  If build succeeded: TaskUpdate(CLAUDE_TASK_ID, status: "completed")
  If build failed: TaskUpdate(CLAUDE_TASK_ID, status: "completed", metadata: {result: "failed"})

# Always update markdown (for visibility in file)
Edit(file_path: plan_path):
  If build succeeded: task.status = ✅
  If build failed: task.status = 🔴

Go to Step 2 (next task).

5. Ship

When all tasks are ✅ or 🔴:

Skill("ship-it")

Task ID Formats

System	Format	Example
GitHub Issues	`#{number}`	`#123`
Linear	`{PROJECT}-{number}`	`PROJ-123`
Beads	`BEADS-{number}`	`BEADS-123`
File-based	`TODO-{number}`	`TODO-123`

Error Handling

Scenario	Action
Task build fails	Mark 🔴, continue to next task
All dependencies failed	Skip task, mark 🔴
Blueprint file not found	Error, exit
No tasks section found	Error, exit