一键导入
verification-before-completion
Use before claiming work complete, fixed, or passing - requires fresh evidence before any completion claim
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use before claiming work complete, fixed, or passing - requires fresh evidence before any completion claim
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when shaping a feature before implementation - turns rough ideas into an approved markdown spec and local task directory
Use to execute an approved local markdown task directory iteratively - work the current Now slice, update docs, then stop
Use when implementation is complete and verified - delete finished local task docs, present integration options, and clean up safely
Use for advanced markdown task-doc operations - split work, reprioritize slices, delete finished local task dirs, and keep docs clean
Use after executing a task directory - verifies implementation against plan.md, acceptance checks, and anti-goals
Use when starting any conversation - establishes skill selection and the local task-doc workflow
| name | verification-before-completion |
| description | Use before claiming work complete, fixed, or passing - requires fresh evidence before any completion claim |
<codex_compat> This skill was ported from Claude Code. In Codex:
SKILL.md from disk.spawn_agent (dispatch in parallel when needed).<skill_overview> Completion claims without fresh verification are not acceptable. Evidence first. </skill_overview>
<rigidity_level> LOW FREEDOM - No exceptions. Run the command, read the output, then make the claim. </rigidity_level>
<quick_reference>
| Claim | Required evidence |
|---|---|
| Tests pass | Fresh test output with no failures |
| Build succeeds | Fresh build output with exit 0 |
| Task slice complete | Updated tasks.md plus verification evidence |
| Feature complete | Acceptance checks in plan.md satisfied with evidence |
Not sufficient: “should work”, “looks done”, or stale output. </quick_reference>
<when_to_use>
Done<the_process>
What exact statement are you about to make?
Run the specific command or check that proves that claim.
Confirm the output actually supports the claim.
If the work is complete:
Donecontext.md if it matters</the_process>