subagent-task-execution
Subagent Task Execution
Overview
This skill is used to execute a set of tasks (typically from a task breakdown or plan). It focuses on high-quality execution by dispatching specialized subagents for each task, ensuring each task is performed correctly and verified before moving to the next.
Core Principle
One Task, One Subagent, Multi-Stage Review. By isolating each task and applying a structured review process, we ensure high quality and prevent context pollution.
The Process
- Preparation:
- Read the entire plan or task breakdown.
- Extract all tasks with their full context.
- Create a structured todo list using the
TodoWritetool.
More from davidkiss/smart-ai-skills
reflection
MUST use this skill when user provides feedback / ask to do things in certain way, or when a tool call fails - for self-improvement - to learn user preferences and store them in AGENT.md / CLAUDE.md, and to propose improvements to skills.
623coding
MUST use for all coding related tasks - includes general coding best practices and software engineering principles to build robust, maintainable, and scalable software.
279task-breakdown
Use when you have specs or requirements for a multi-step task to break it down into detailed tasks, before executing it
155brainstorming
You MUST use this skill before any creative or complex work. Explores user intent, requirements and design before actually executing on the task.
112skill-editor
Creates, updates, and manages Agent Skills following the Claude Code style. Use this skill when the user wants to add a new capability, create a new skill, or modify an existing skill.
96investigator
Use this skill when the user asks to "analyze", "research", "how do I", or "what's the best way" to understand project context, impact of potential actions, and root causes of issues.
1