subagent-task-execution
Use when executing tasks from a task breakdown document in the current session.
- Installs
- 171
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/davidkiss/smart-ai-skills --skill subagent-task-execution- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads subagent-task-execution automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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.
-
Per-Task Execution Loop:
- Skill Discovery: Before starting a task, identify which specialized skill(s) are needed for its execution (e.g.,
coding,brainstorming, or any project-specific skills). - Dispatch Implementer: Dispatch a subagent to perform the task. Provide the subagent with the full task description, any identified skills, and the necessary context.
- Interactive Clarification: If the subagent has questions, answer them clearly before they proceed with implementation.
- Task Implementation: The subagent performs the task, following the identified best practices and skills.
- Verification & Review:
- Spec Compliance Review: A separate subagent verifies that the result exactly matches the task requirements (no more, no less).
- Quality Review: A final review stage to ensure the output meets the highest standards of the domain (e.g., code quality, documentation clarity, etc.).
- Completion: Mark the task as completed in the todo list.
- Skill Discovery: Before starting a task, identify which specialized skill(s) are needed for its execution (e.g.,
-
Finalization:
- Once all tasks are complete, perform a final holistic review of the entire body of work to ensure consistency and overall quality.
Key Principles
- Discovery First: Always look for and apply the most relevant skills for the specific task at hand.
- Isolation: Each task should be treated as a distinct unit of work.
- Review Loops: Never move to the next task if the current one has open issues from either the spec or quality reviews.
- Subagent Specialization: Use subagents as specialized workers, providing them with all the context they need upfront.
Red Flags
- Skipping the skill discovery phase.
- Combining multiple tasks into a single subagent invocation.
- Proceeding with a task while reviews are still pending or failing.
- Ignoring subagent questions or providing vague answers.
- Failing to update the todo list as progress is made.
FAQ
What does the subagent-task-execution skill do?
Use when executing tasks from a task breakdown document in the current session.
How do I install subagent-task-execution?
Run npx skills add https://github.com/davidkiss/smart-ai-skills --skill subagent-task-execution in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/subagent-task-execution/ (personal) or .claude/skills/subagent-task-execution/ (project).
Which AI agents can use subagent-task-execution?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is subagent-task-execution safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains subagent-task-execution?
It is published by davidkiss in davidkiss/smart-ai-skills. It has 171 recorded installs.
More from davidkiss/smart-ai-skills
reflection
davidkiss/smart-ai-skills
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.
coding
davidkiss/smart-ai-skills
MUST use for all coding related tasks - includes general coding best practices and software engineering principles to build robust, maintainable, and scalable software.
task-breakdown
davidkiss/smart-ai-skills
Use when you have specs or requirements for a multi-step task to break it down into detailed tasks, before executing it
brainstorming
davidkiss/smart-ai-skills
You MUST use this skill before any creative or complex work. Explores user intent, requirements and design before actually executing on the task.
skill-editor
davidkiss/smart-ai-skills
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.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。