Never claim completion without fresh verification 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。
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the command in THIS message, you cannot claim it passes.
Before claiming ANY success:
1. IDENTIFY → What command proves this claim?
2. RUN → Execute the FULL command
3. READ → Full output, check exit code
4. VERIFY → Does output confirm the claim?
5. CLAIM → Only now, with evidence
Skip ANY step = lying, not verifying.
| Claim | Requires | NOT Sufficient |
|---|---|---|
| "Tests pass" | Test output: 0 failures | "Should pass", previous run |
| "Build works" | Build output: exit 0 | Linter passing |
| "Bug fixed" | Test of original symptom | "Code changed" |
| "Linter clean" | Linter output: 0 errors | "Looks right" |
| "Feature complete" | All requirements checked | "Tests pass" |
If you catch yourself:
STOP. Run the verification.
| You Think | Reality |
|---|---|
| "Should work now" | RUN IT |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ tests |
| "I'm tired" | Exhaustion ≠ excuse |
Tests:
✅ [run test] → See "34/34 pass" → "All tests pass"
❌ "Tests should pass now"
Build:
✅ [run build] → See "exit 0" → "Build passes"
❌ "Build looks good"
Requirements:
✅ Re-read requirements → Check each → Report gaps
❌ "Tests pass so it's complete"
From actual failures:
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
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。
Complete methodology for preventing AI hallucinations. Use when accuracy is critical and you need Claude to verify before claiming, cite before asserting, and admit uncertainty instead of guessing.
中文简介正在准备中。当前显示原文说明。
Transform rough ideas into solid designs through structured questioning
中文简介正在准备中。当前显示原文说明。
Canvas API Connection Skill
中文简介正在准备中。当前显示原文说明。
Forces every code-related claim to include file:line citations. No citation means the claim must be verified or removed. Use when building documentation, writing code reviews, or any output that others will rely on.
中文简介正在准备中。当前显示原文说明。
Assign confidence scores (0-100) to every claim in a response. Helps users understand which parts are verified facts and which are educated guesses. Use when the user needs to know how much to trust each part of the answer.
中文简介正在准备中。当前显示原文说明。
Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding every statement in actual text from the codebase. Use when working with large files or unfamiliar code.
中文简介正在准备中。当前显示原文说明。