Evidence-first completion gate - requires running verification commands and confirming output before making any success claims.
Inherits all available tools
Additional assets for this skill
This skill inherits all available tools. When active, it can use any tool Claude has access to.
name: verification-before-completion description: | Evidence-first completion gate - requires running verification commands and confirming output before making any success claims.
trigger: |
skip_when: |
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.
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
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
EVERY completion message structure:
Example structure:
Let me verify the implementation:
$ npm test
[PASTE FULL OUTPUT]
The tests show 15/15 passing. Implementation is complete.
Wrong structure (violation):
Implementation is complete! Let me verify:
[This is backwards - claimed before verifying]
| Claim | Requires | Not Sufficient |
|---|---|---|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
NEVER use these without evidence:
Using these = lying, not verifying
About to say "all tests pass"?
Check:
No to any = you're lying
"I ran them earlier" = NOT verification "They should pass now" = NOT verification "The previous output showed" = NOT verification
Run. Paste. Then claim.
| Excuse | Reality |
|---|---|
| "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 |
| Type | ✅ CORRECT | ❌ WRONG |
|---|---|---|
| Tests | Run command, see "34/34 pass", then claim | "Should pass now" |
| Regression (TDD) | Write → pass → revert → MUST FAIL → restore → pass | "Written regression test" (no red-green) |
| Build | Run build, see exit 0, then claim | "Linter passed" (linter ≠ compiler) |
| Requirements | Re-read plan → checklist → verify each | "Tests pass, phase complete" |
| Agent delegation | Check VCS diff → verify changes | Trust agent report |
This skill uses these universal patterns:
skills/shared-patterns/state-tracking.mdskills/shared-patterns/failure-recovery.mdskills/shared-patterns/exit-criteria.mdskills/shared-patterns/todowrite-integration.mdApply ALL patterns when using this skill.
| Violation | Detection | Recovery |
|---|---|---|
| Claimed complete without verification | "complete" with no command output, "should work" | Run verification → paste output → then claim |
| Ran command but didn't paste | Mentioned running tests, no output shown | Re-run → copy FULL output → paste → then claim |
| Used banned phrases | "appears to work", "Great!", "Done!" before evidence | Stop → run verification → paste output → evidence-based claim |
Why recovery matters: Claims without evidence = false confidence. Silent failures go undetected until production.
From 24 failure memories:
ALWAYS before:
Rule applies to:
No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.