Menu
Use when about to claim ANY research result status — requires running verification, reading full output, and providing evidence before making claims; always active, no exceptions
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | results-verification-protocol |
| description | Use when about to claim ANY research result status — requires running verification, reading full output, and providing evidence before making claims; always active, no exceptions |
Claiming a result without verification is fabrication, not efficiency. This skill is ALWAYS active.
Core principle: Evidence before claims, always.
Violating the letter of this rule is violating the spirit of this rule.
NO RESULT CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim the result.
BEFORE claiming ANY result status:
1. IDENTIFY: What command or check proves this claim?
2. RUN: Execute it now, fresh, complete
3. READ: Full output — every line, every number
4. VERIFY: Does the output actually support the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence attached
5. ONLY THEN: Make the claim
Skip any step = fabrication, not verification
| Claim | Requires | Not Sufficient |
|---|---|---|
| "Tests pass" | Test output showing 0 failures | "Should pass", previous run |
| "Method outperforms baseline" | Numbers from BOTH methods, statistical test result (p-value/CI) | One method's numbers, "looks better" |
| "Analysis complete" | All analysis outputs present and inspected | Script ran without errors |
| "Experiment finished" | Full results table, all seeds, all conditions | Partial results, single seed |
| "Paper ready" | Checklist of every claim mapped to supporting evidence | "All sections written" |
| "Results are significant" | Statistical test output with exact values | Eyeballing differences |
| "Reproducible" | Independent re-run producing same results | "Same code, should work" |
Never use these without attached evidence:
Replace with evidence. Every time.
| Excuse | Reality |
|---|---|
| "I'm confident it works" | Confidence ≠ evidence. Run verification. |
| "I just ran it" | Show the output. Fresh evidence for every claim. |
| "The previous run passed" | Previous ≠ current. Run again. |
| "It's just a small change" | Small changes break things. Verify. |
| "I'll verify after finishing everything" | Verify each step. Compound errors are harder to find. |
| "The numbers look right" | Looking ≠ checking. Show the exact output. |
Claim without evidence = fabrication
Evidence without fresh run = assumption
Run the command. Read the output. Show the numbers. THEN claim the result.
This is non-negotiable.
Use when designing the evaluation protocol for a method development project — locks primary metrics, datasets, seeds, statistical tests, and baseline list into an immutable contract
Use when G2 (plan freeze) and G3 (execution readiness) gates have passed — handles all implementation, baseline reproduction, experimentation, and iteration for both Type M and Type D projects; this is Phase 4
Use when research direction is validated (G1 passed) and the project needs method design, analysis framework, evaluation protocol, or story line — this is Phase 3 and must complete before any code or experiments
Reusable protocol for multi-agent discussions that iterate until convergence. Used by results-integration (Phase 5) and paper-writing (Phase 6) to ensure discussions actually resolve issues rather than just noting them.
Use when and ONLY when the user explicitly requests paper writing and G4 (write-ready) gate has passed — handles LaTeX structure, senior-level writing, reference verification, and iterative refinement
Use when Phase 1 (research-direction-exploration) is complete and G1 gate has passed — subjects the research problem to adversarial defense-style questioning, classifies project intent, re-evaluates venue target, and produces a final feasibility ruling before any method design begins