| name | verification-before-completion |
| description | Use BEFORE claiming any long-running CERN compute step finished — REANA workflow runs, HTCondor / lxbatch jobs, xrdcp / rucio download transfers, uproot iterate loops over many files, distributed Dask reductions, multi-stage REANA pipelines, ROOT macros that produce output files. Block the "done" claim until concrete evidence is shown: `reana-client status` output, condor `JobStatus`, exit code, output file size from `ls -la` / `xrdfs stat`, cutflow row counts, fit convergence. The body of the skill, vendored from obra/superpowers, gives the gate function and worked dialogues. Disambiguator phrase: completion-evidence gate. |
CERN verifiable plan format
When planning a multi-step analysis or workflow, emit a verifiable plan
before executing. Each step names a concrete check that proves it
succeeded. Example shape:
1. Submit REANA workflow → verify: reana-client status shows "finished"
2. Download output ROOT file → verify: ls -lh shows non-zero size, xrdfs stat matches
3. Run uproot loop over output → verify: cutflow table row counts match expected N_events
4. Produce normalised histogram → verify: integral matches cross_section × lumi within 1%
Concrete checks for CERN workloads:
| Step type | Concrete check |
|---|
| REANA workflow | reana-client status → finished; step logs show exit 0 |
| HTCondor / lxbatch job | condor_q or bjobs exit; output file present with non-zero size |
xrdcp / Rucio download | ls -lh / xrdfs stat size matches source; optional checksum |
uproot iterate loop | Cutflow row counts printed per file; no silent exception swallowing |
| Fit / pyhf | Convergence status (minuit.valid); NLL value printed |
"Should work" and "looks correct" are not concrete checks.
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.
The Iron Law
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
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
| 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 |
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
| 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 |
Key Patterns
Tests:
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
Build:
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
Requirements:
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
Agent delegation:
✅ 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.
