Audit semantic and keyboard accessibility.
中文简介正在准备中。当前显示原文说明。
Assess nontrivial completion evidence.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Evidence before claims. Verification should be fresh, decisive, and proportionate to the result being asserted. For an obvious low-impact local edit, apply the direct check without loading this skill or creating a formal verification artifact. Use this fuller workflow when the evidence choice, failure interpretation or completion boundary is nontrivial, or when explicitly invoked.
Before claiming that work is complete, fixed, passing, deployed, sent, published, or otherwise in a verified state:
Do not replace a required runtime check with source inspection, a build with lint, or end-to-end evidence with an agent's success message. Do not run an entire test universe when a targeted regression plus the repository's required gate proves the claim.
| Claim | Decisive evidence |
|---|---|
| Targeted bug fixed | Reproduce the original symptom or run its regression test |
| Tests pass | The named test command exits successfully with zero relevant failures |
| Build succeeds | The actual build command exits successfully |
| Visual issue fixed | Inspect the rendered affected state at relevant viewports |
| Requirements met | Check each material acceptance criterion against code, output, or runtime evidence |
| External state changed | Read back the exact account, message, deployment, or service state |
| Research complete | State sources searched, semantic coverage, exclusions, and unresolved limits |
Use precise labels such as:
Never imply whole-system certification from a sample. Previous evidence may provide context, but a current completion claim needs current verification when the state could have changed.
A subagent report is evidence about what the subagent observed, not automatic proof of completion. Inspect the relevant diff or artifact and run the smallest decisive verification before adopting its claim.
Stop when the acceptance criteria are supported at the required confidence. Record residual limitations instead of adding ceremonial checks that cannot change the decision.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Audit semantic and keyboard accessibility.
中文简介正在准备中。当前显示原文说明。
Finish accessibility and performance details.
中文简介正在准备中。当前显示原文说明。
Evaluate agent and skill behavior or routing.
中文简介正在准备中。当前显示原文说明。
Design memory provenance and tenant isolation.
中文简介正在准备中。当前显示原文说明。
Resolve agent ownership and handoff design.
中文简介正在准备中。当前显示原文说明。
Define coherent motion timing and rhythm.
中文简介正在准备中。当前显示原文说明。