메뉴
Create visual workflow plans for project work, with typed graph nodes, links to agent execution, and Dashboard URLs.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | workflow |
| description | Create visual workflow plans for project work, with typed graph nodes, links to agent execution, and Dashboard URLs. |
| userInvocable | true |
| allowedTools | ["project.current","project.task_list","project.task_get","project.workflow"] |
Use this skill when the user explicitly asks for a workflow, visual plan, workflow-mode execution, or when the task benefits from a visible step graph.
When active:
project.workflow for workflow state; do not write workflow files directlyagent_step nodes to agent/session/delegated-task IDs through typed metadataDo not create workflows outside this skill.
Runtime instructions for Ask mode: answer directly without code mutation.
Runs configurable multi-round research with compare, review, and explore modes, visible progress, source collection, and final sourced answers.
Creates and maintains project-board tasks with correct dedupe, umbrella/root linking, dependencies, tags, authors, assignments, and autopilot queue placement.
Runtime instructions for Plan mode: produce implementation or investigation plans without code mutation.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".