AgentSkillsCN

obra-verification-before-completion

在最终敲定答案或PR之前，请务必使用此方法：确认需求已满足，执行各项检查，并避免在VS Code Copilot Agent模式下，仅凭“看起来不错”就草率结案。

SKILL.md
--- frontmatter
name: obra-verification-before-completion
description: Use before finalizing answers or PRs: confirm requirements met, run checks, and avoid “looks good” without evidence in VS Code Copilot Agent mode.

Verification Before Completion

Overview

Claiming work is complete without verification is dishonesty, not efficiency.

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

Copilot Completion Checklist

✅ Requirements

  • •Re-state what “done” means (from the user request).
  • •Confirm each requirement is satisfied (link to files/lines if possible).

✅ Correctness

  • •Consider edge cases (inputs, nulls, errors).
  • •Add regression tests when fixing bugs.

✅ Quality

  • •Lint/format follows project rules.
  • •No debug prints/logs left behind unless requested.
  • •Minimal diff; clear naming.

✅ Verification commands (choose what fits repo)

  • •Tests: …
  • •Lint: …
  • •Build: …
  • •Typecheck: …

❌ No fabricated verification

  • •If you can’t run commands, provide them and state you didn’t execute them.

The Iron Law

code
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

The Gate Function

code
BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
   - If NO: State actual status with evidence
   - If YES: State claim WITH evidence
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying

Common Failures

ClaimRequiresNot Sufficient
Tests passTest command output: 0 failuresPrevious run, "should pass"
Linter cleanLinter output: 0 errorsPartial check, extrapolation
Build succeedsBuild command: exit 0Linter passing, logs look good
Bug fixedTest original symptom: passesCode changed, assumed fixed
Regression test worksRed-green cycle verifiedTest passes once
Agent completedVCS diff shows changesAgent reports "success"
Requirements metLine-by-line checklistTests passing

Red Flags - STOP

  • •Using "should", "probably", "seems to"
  • •Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
  • •About to commit/push/PR without verification
  • •Trusting agent success reports
  • •Relying on partial verification
  • •Thinking "just this once"
  • •Tired and wanting work over
  • •ANY wording implying success without having run verification

Rationalization Prevention

ExcuseReality
"Should work now"RUN the verification
"I'm confident"Confidence ≠ evidence
"Just this once"No exceptions
"Linter passed"Linter ≠ compiler
"Agent said success"Verify independently
"I'm tired"Exhaustion ≠ excuse
"Partial check is enough"Partial proves nothing
"Different words so rule doesn't apply"Spirit over letter

Key Patterns

Tests:

code
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"

Regression tests (TDD Red-Green):

code
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)

Build:

code
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)

Requirements:

code
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"

Agent delegation:

code
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report

Why This Matters

From 24 failure memories:

  • •your human partner said "I don't believe you" - trust broken
  • •Undefined functions shipped - would crash
  • •Missing requirements shipped - incomplete features
  • •Time wasted on false completion → redirect → rework
  • •Violates: "Honesty is a core value. If you lie, you'll be replaced."

When To Apply

ALWAYS before:

  • •ANY variation of success/completion claims
  • •ANY expression of satisfaction
  • •ANY positive statement about work state
  • •Committing, PR creation, task completion
  • •Moving to next task
  • •Delegating to agents

Rule applies to:

  • •Exact phrases
  • •Paraphrases and synonyms
  • •Implications of success
  • •ANY communication suggesting completion/correctness

The Bottom Line

No shortcuts for verification.

Run the command. Read the output. THEN claim the result.

This is non-negotiable.