Loading...
Loading...
Found 108 Skills
This skill provides universal quality standards for any custom task, ad-hoc request, or campaign step that does not have a specific pre-defined instruction set. Apply these standards to deliver world-class marketing assets regardless of task type.
Documentation-driven project development workflow. Intelligently determines task types, executes existing plans or generates new plans using feature-dev. **Use Cases:** - Complete project documentation exists, need to execute development tasks - User specifies to execute a certain plan (e.g., "Execute plan 001") - User requests to develop new features (automatically uses feature-dev to generate plans) **Prerequisites:** - The project should already have a docs/ documentation structure (PRD, SAD, etc.) - For new projects, it is recommended to first use the project-docs-setup skill to create complete documentation - If plan formulation is needed, it is recommended to use the project-planning skill **Relationship with Other Skills:** - project-docs-setup: Creates project documentation structure - project-planning: Formulates development plans (requirement clarification + design discussion + plan writing) - project-workflow: Executes development plans + updates documentation - Recommended workflow: project-docs-setup → project-planning → project-workflow **Trigger Methods:** - "Execute plan 001" / "Continue 001-user-authentication" - "Start development" / "Execute plan" / "Continue last task"
Automate Short IO tasks via Rube MCP (Composio). Always search tools first for current schemas.
Automate Postgrid Verify tasks via Rube MCP (Composio). Always search tools first for current schemas.
This skill should be used when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Implements Manus-style file-based planning with task_plan.md, findings.md, and progress.md.
Implement one prd.json task per iteration using tracer-bullet + compound mindset. Triggers on: ratatouille:.
Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.
Use when the user says "vm", "voice mode", "team", "coordinate", or needs to orchestrate multiple agents working on related tasks in parallel
Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.
在當前會話中執行具有獨立任務的實施計劃時使用
Use at the start of any conversation - Determine how to find and use skills, requiring the skill tool to be invoked before any response (including clarification questions)
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.