Agent Skills › Yeachan-Heo/oh-my-claudecode › execute

execute

GitHub

将已确认的任务转化为可运行且经过验证的代码。涵盖任务拆解、并行实现、持续验证及结果汇报，强调小步快跑、复用现有模式、保持代码简洁可逆，并在提交前确保测试通过或明确报告失败原因。

skills/execute/SKILL.md Yeachan-Heo/oh-my-claudecode

需要执行已明确需求的开发任务将设计或计划转化为实际代码实现构建独立功能单元并验证其正确性

npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -g -y

More Options

Use without installing

npx skills use Yeachan-Heo/oh-my-claudecode@execute

指定 Agent (Claude Code)

npx skills add Yeachan-Heo/oh-my-claudecode --skill execute -a claude-code -g -y

安装 repo 全部 skill

npx skills add Yeachan-Heo/oh-my-claudecode --all -g -y

预览 repo 内 skill

npx skills add Yeachan-Heo/oh-my-claudecode --list

Frontmatter

{
    "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.

Take a task from agreed intent to working code, with evidence that it works.

Confirm the task is clear enough to build. If it is not, plan first.
Break the work into independent units; run genuinely independent units in parallel.
Implement the smallest correct change per unit, reusing existing utilities and patterns.
Verify as you go, not only at the end.
Report what changed, what was verified, and what remains.

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.

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.

Before claiming done:

6688a30 Current 2026-10-19 08:27
强化了技能描述和提示词护栏，新增两条规则：实施前需修复或标记偏离惯例的临时方案；在断言或跳过技能步骤前必须阅读其源码。
e9e8fa3 2026-09-03 09:14
更新上游路由代理列表，移除ultrawork，新增ultrapilot。
74e4e11 2026-08-28 11:11