vc-auditlisted

READ-ONLY falsification of a completed plan or multi-task implementation. Builds a per-task requirements matrix, then proves or refuses each claim against code + tests evidence. Default verdict is UNVERIFIED — PASS is earned, never assumed. Runs whenever a written plan claims completion, regardless of upstream — workflow, implement, marbles, human work, or a mix. Trigger phrases: "audit", "vc-audit", "task-by-task audit", "verify implementation plan", "spec falsification", "post-marbles audit", "did this plan actually land", "weryfikuj implementację", "audyt planu", "co naprawdę wylądowało", "falsyfikacja completion".
vetcoders/vibecrafted · ★ 1 · AI & Automation · score 63

Install: claude install-skill vetcoders/vibecrafted

> **Invocation for `vc-audit` (launcher `audit`)** > > Same three-path _shape_ as the fleet, with **this** skill's literals — see the > canonical [Delegation Matrix](../DELEGATION_MATRIX.md): > > - [Shared three paths](../DELEGATION_MATRIX.md#shared-three-paths) > - [Launcher catalogue](../DELEGATION_MATRIX.md#launcher-catalogue-core-runtime) > - [Per-launcher rule](../DELEGATION_MATRIX.md#per-launcher-rule-the-semantic-delta) > - [Native vs external](../DELEGATION_MATRIX.md#native-subagents-vs-external-workers) > > | Path | Literal for this skill | > | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | > | 1. User-launched worker | `vibecrafted audit <agent>` | > | 2. Interactive | `/vc-audit` — execute **in this session**; use native subagents when required; do **not** externalize merely because a launcher exists | > | 3. Agent-operator | may dispatch the worker form above via `vc-dispatch` / operator lines while preserving this skill's identity | > Freer native on some runs ≠ abandon external fleet. `vc-dispatch` and `vc-ship` keep their own identities. <!-