fudesign2008 Completion Evidence Discipline
Internal shared skill. Single source of truth for fresh-evidence gates on completion and verification claims. Hosts declare it in
dependencies(directly or viastaged-review-flow) and abort if missing — no silent fallback.Name note: this skill is intentionally not named
verification-before-completion(reserved by an external skills repo). Use this name only.
Iron Law
NO COMPLETION OR PASS CLAIMS WITHOUT FRESH EVIDENCE FROM THE CURRENT TURN.
- Fresh = produced by a command, check, or observed tool result executed in this assistant turn (or an attached log from that same turn).
- Not fresh = prior-turn memory, “we designed a test”, subagent success text alone, or assumed green CI.
Required behavior
When about to claim any of: tests passed, typecheck/build OK, verification complete, bug fixed, ready to merge/archive:
- Run the relevant command/check in this turn, or
- Label Pending with the exact manual action still required — and do not say it passed.
Compose with staged-review-flow verification honesty:
| Label | Meaning |
|---|---|
| Executed | Command/action + concise output summary from this turn |
| Pending | Exact action the user (or a later turn) must still run |
Forbidden
- Reporting “all green” / “verified” when no verifying command was run this turn
- Treating designed scenarios or unchecked assertions as executed passes
- Renaming or aliasing this skill to
verification-before-completioninside this repository
Integration guide
- Hosts: one-line pointer at verification / closeout — load this skill; do not paste the Iron Law prose.
staged-review-flow: honesty rule MUST compose with this gate (Executed ⇒ fresh evidence).- Orthogonal to
runtime-verification-discipline: this skill gates evidence freshness (did you run it this turn); that skill gates verification environment and executor (which tier, who ran it, sufficient?). A pass claim must satisfy both. - Prefer
user-invocable: false; users reach it through PDCA hosts.