메뉴
Provides robust mechanisms for agents to dynamically load and execute markdown workflows.
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
Token-saving terse mode — no filler, no narration, just results
Reviews TypeScript code using functional programming principles. Use when reviewing PRs or checking code quality.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you are unfamiliar with a section of code or need to understand how it fits into the bigger picture.
| name | workflow-loader |
| description | Provides robust mechanisms for agents to dynamically load and execute markdown workflows. |
This skill provides the capability for AI Agent to robustly load, read, and execute external workflow files defined in the .mitra/agents/{agent}/workflows/ directory.
By default, an instruction like "Action: Load backend.md" is ambiguous. The LLM might:
This skill provides strict Tools (Python scripts) that you MUST use when a workflow is requested.
When a user asks "What can you do?" or you need to see available modules for an agent:
Run:
If it is
./scripts/list_workflows.sh --agent {agent_name}
Example: ./scripts/list_workflows.sh --agent architect
When you trigger a menu handler (e.g., *backend) or need to execute a specific process:
Run:
./scripts/load_workflow.sh --agent {agent_name} --workflow {workflow_name}
Example: ./scripts/load_workflow.sh --agent architect --workflow backend
Once the content is loaded (printed to your context):
load_workflow.sh script, you haven't loaded it.