Skip to content
Get packs

Execute Approved Tasks

Carry an agreed task through to working, verified code with test evidence

Source Download skill
Repository
Yeachan-Heo/oh-my-claudecode
Stars
40,512
Licence
MIT
Files
1 file

What it does

When installed, the agent follows a structured build workflow once a task is clear: it confirms scope, splits work into independent pieces (in parallel where sensible), makes small changes, verifies as it goes, and then reports what changed, what was tested, and what is still open. It also discourages over-engineering, extra dependencies, and placeholder or skipped tests.

Great for

  • Developers who already know what they want built and want the agent to finish it with verification
  • Teams wanting consistent, evidence-based completion reports from an AI coding agent
  • Multi-step coding tasks that benefit from parallel sub-agents

Skip it if

  • Vague or exploratory requests; the skill tells the agent to plan first, so it adds little there
  • Tasks where you need an independent reviewer, since the skill says to hand off approval to review or verify rather than self-approve
  • Projects where the agent is not allowed to run tests or modify files, because the workflow depends on both

Try asking

  • “Implement the agreed password-reset endpoint and show me the tests that pass”
  • “Build the three independent components from this spec in parallel and report what is still open”
  • “Finish the task list in TODO.md and keep going until it is empty, with verification notes”
Step-by-step guide: how to use Execute Approved TasksInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    execute.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip execute.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip execute.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give a clear, agreed task description before invoking it so the skill can skip planning and build directly
  • Ask for a separate review or verify pass afterwards, since the skill deliberately does not approve its own work
  • Name the test command you expect so the evidence section reflects the checks you care about

What's inside

  • SKILL.md

Redistributed unmodified from Yeachan-Heo/oh-my-claudecode under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.