execute · yeachan-heo — Claude Code skill: what it does, how to install
The execute skill takes a well-defined task through implementation and verification. Use it when you want working code and a clear account of what was checked.
MIT 307 installs ★ 40,997 updated 2026-10-24
npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a claude-codeWhat execute does
execute splits work into independent units and runs those units in parallel when they do not depend on one another. A single unit can be handled directly; multiple independent units can go to executor agents, while team is available for coordinated parallel work.
The workflow checks whether the task is clear enough to build. If it is not, planning comes first. It favors small, reversible changes and disallows adding dependencies without an explicit request. That makes a temporary workaround harder to leave behind as an accepted project convention.
Before calling the work done, collect verification evidence, report test results, and list anything still open. Implementation and approval are separate passes: hand the result to review or verify rather than approving your own work.
What it helps with
- Split a task into independent units
- Implement an agreed change in small steps
- Check code as implementation proceeds
- Record verification results and open work
- Hand completed work off for separate approval
Example prompts for the agent
- Implement the agreed change in this project and verify it as you go.
- Break this task into independent parts and run the parts that have no dependencies in parallel.
- Finish the task, gather verification evidence, and report what remains open.
How to install execute
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a claude-code2Manually: put the files in place
~/.claude/skills/execute/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/execute/
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a codex2Manually: put the files in place
.agents/skills/execute/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a cursor2Manually: put the files in place
.cursor/skills/execute/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Yeachan-Heo/oh-my-claudecode skills/execute2Manually: put the files in place
.github/skills/execute/SKILL.md1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a gemini-cli2Platform CLI
gemini skills install https://github.com/Yeachan-Heo/oh-my-claudecode --path skills/executeManually: put the files in place
.devin/skills/execute/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -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 execute
How do I install execute in Claude Code?
Run npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a claude-code. The skill file is at ~/.claude/skills/execute/SKILL.md.
What does execute do?
It guides a clear task through implementation and code checks, then reports changes, verification evidence, and remaining work.
How does execute handle parallel work?
It runs only independent units in parallel. Multiple units can be assigned to executor agents; team is for coordinating parallel workers.
Source text
SKILL.md · MIT
--- name: execute description: Carry an approved task through to working, verified code --- # Execute Use this skill when the work is understood and the job is to build it. This is the canonical execution workflow. `autopilot`, `ralph`, `ultragoal`, `ultrapilot`, `pipeline`, and `swarm` route here. ## Goal Take a task from agreed intent to working code, with evidence that it works. ## Workflow 1. Confirm the task is clear enough to build. If it is not, plan first. 2. Break the work into independent units; run genuinely independent units in parallel. 3. Implement the smallest correct change per unit, reusing existing utilities and patterns. 4. Verify as you go, not only at the end. 5. Report what changed, what was verified, and what remains. ## Scale Match the machinery to the task: - **Single unit** — implement directly, verify, done. - **Several independent units** — delegate to `executor` agents in parallel. - **Long-running or unbounded** — keep a durable task list and continue until the list is empty. - **Needs coordinated parallel workers** — use `team`. Do not spin up coordination for work that one focused pass would finish. ## Rules - Prefer deletion over addition when behavior is preserved. - Do not add dependencies without an explicit request. - Keep diffs small and reversible. - Work on two tracks at once: finish the task in front of you, and notice what would make the next task easier or safer — the second track is a proposal, not a detour. - No workarounds: a deviation from convention that only unblocks you today (a skipped check, a hard-coded value, a manual step) is fixed or flagged before feature work lands on top of it — it never silently becomes the norm. - Before asserting what a skill or protocol does, or skipping one of its steps, read its source — summaries are for finding it, not for standing in for it. - Placeholder TODOs, `test.skip`, and stub tests are blockers, not progress. - Authoring and approval are separate passes — do not self-approve; hand off to `review` or `verify`. ## Completion Before claiming done: - No pending tasks - Tests pass, or failures are reported plainly - Verification evidence collected ## Output - Files changed - What was implemented - Evidence it works - What is still open
© Yeachan-Heo · MIT · Yeachan-Heo/oh-my-claudecode
Similar skills
SKILL.md skills catalog →execute by other authors comes first.