subagent-task-execution — Claude Code skill: what it does
subagent-task-execution runs a plan task by task, handing each one to its own subagent and checking the result twice before moving on.
no license 172 installs ★ 4 updated 2026-05-08
npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a claude-codeWhat subagent-task-execution does
Point the skill at a plan or a task breakdown and it works through the list in order. It reads the document end to end, pulls out every task with its context and keeps them in a todo list via TodoWrite. Each task then goes to a separate implementer subagent.
Before dispatch, the skill works out which other skills the task needs and passes them along with the description. Any questions from the subagent get answered before work starts. Two reviews follow: one subagent checks the result against the task requirements, another judges quality. Open findings block the next task.
A last pass looks over the whole body of work for consistency. Progress tracking depends on TodoWrite; without that tool in the session there is nowhere to keep the list, so the order ends up in your head.
What it helps with
- work through a long plan one task at a time
- stop context from leaking between tasks
- catch a mismatch with the spec before the task closes
- keep the requirements check apart from the quality review
- bring in the right skill for each task
Example prompts for the agent
- Take the tasks in
plan.mdand run them in order, one subagent per task. - Build the todo list from
tasks.mdwithTodoWriteand keep it current as you go. - Send the result to a spec compliance review and a quality review before marking the task done.
How to install subagent-task-execution
1Skills CLI (Vercel)
npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a claude-code2Manually: put the files in place
~/.claude/skills/subagent-task-execution/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/subagent-task-execution/
1Skills CLI (Vercel)
npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a codex2Manually: put the files in place
.agents/skills/subagent-task-execution/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a cursor2Manually: put the files in place
.cursor/skills/subagent-task-execution/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davidkiss/smart-ai-skills skills/subagent-task-execution2Manually: put the files in place
.github/skills/subagent-task-execution/SKILL.md1Skills CLI (Vercel)
npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a gemini-cli2Platform CLI
gemini skills install https://github.com/davidkiss/smart-ai-skills --path skills/subagent-task-executionManually: put the files in place
.devin/skills/subagent-task-execution/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about subagent-task-execution
How do I install subagent-task-execution in Claude Code?
Run npx skills add davidkiss/smart-ai-skills --skill subagent-task-execution -a claude-code; the skill lands at ~/.claude/skills/subagent-task-execution/SKILL.md.
What does subagent-task-execution do?
It splits a plan into tasks and handles them one at a time: a dedicated subagent implements, then comes a requirements check and a quality review, and only then the next task.
What does the skill need to run?
The TodoWrite tool for the task list, plus the ability to dispatch subagents, since implementation and both reviews run through them.