Claude MarketplacesSubmit
davidkiss avatar

Subagent Task Execution

davidkiss/smart-ai-skills

If you're working through a multi-step plan or task breakdown, this skill gives you a structured way to execute it without cutting corners. It enforces a one task, one subagent approach with mandatory review stages: you prep a todo list, dispatch a specialized subagent for each task with skill discovery beforehand, then run both spec compliance and quality reviews before marking anything complete. The workflow is rigid by design, with explicit red flags like skipping reviews or batching tasks together. It's overkill for simple work, but if you need guardrails to prevent sloppy execution when juggling complex dependencies, the structured handoffs and verification loops actually enforce the discipline most people skip when they're moving fast.

skills.sh installs
172
GitHub stars
4
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add davidkiss/smart-ai-skills --skill subagent-task-execution --agent claude-code

Installs into .claude/skills of the current project.

Files

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

  1. Preparation:
    • Read the entire plan or task breakdown.
    • Extract all tasks with their full context.
    • Create a structured todo list using the TodoWrite tool.
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/davidkiss/smart-ai-skills
Category
AI & Agent Building
First seen
Jun 3, 2026

More from davidkiss/smart-ai-skills

All 5

Recommended

More AI & Agent Building
1webmaxru avatargithub-agentic-workflowswebmaxru/agent-skillsgithub agentic workflows155skills.sh installs
2hoodini avatarcopilot-docshoodini/ai-agents-skillsConfigure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-spe147skills.sh installs
3webmaxru avatarprompt-apiwebmaxru/agent-skillsprompt api146skills.sh installs
4thedivergentai avatargodot-mcp-setupthedivergentai/gd-agentic-skills[PREREQUISITE] Install and configure Godot MCP server for programmatic scene manipulation via Model Context Protocol. Use when user explicitly requests MCP-base126skills.sh installs
5cclank avatarprompt-translatorcclank/lanshu-awesome-ai-video-kit把一条 AI 视频提示词从源模型(如 Sora 2)的写法风格转换为目标模型(如 Kling 3.0 / Wan 2.7 / Veo 3.1 等)的最佳实践写法。基于 110 条 10 场景 × 11 模型对照基准数据(prompts/data/cross-model-matrix.json),不是凭直觉重写,而是查表0skills.sh installs
6github avatarmcp-implementation-security-reviewgithub/awesome-copilotReview the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions0skills.sh installs