bs-checklisted

# Confidence Check Force the assistant to audit its own confidence on a claim before the user acts on it, sends it to a client, or pushes it to production. Designed to catch AI slop - plausible, well-worded output that has not actually been validated against evidence - at the moment it would cost something. > **Make it yours (recommended):** this skill fires best when its `description` knows *your* high-stakes moments. Add your stack (your CMS, workflow engine, cloud provider), your client-facing rituals, and your own trigger phrases to the frontmatter description. Also see the **Domain lenses** section at the bottom - add a lens per domain you work in. ## Subcommand dispatch (read before anything else) Parse the first word of the invocation arguments: | First word | Audit type | Action | |---|---|---| | `premise` | Wrong problem / premise acceptance | Read `protocols/premise.md` -> execute. Skip the verify pipeline entirely. | | `approach` | Premature commitment / anchoring bias | Read `protocols/approach.md` -> execute. Skip the verify pipeline entirely. | | `fresh` | High stakes - all 9 reasoning patterns in a fresh-context sub-agent | Read `protocols/fresh.md` -> execute. Skip the verify pipeline entirely. | | `quick` / `full` / `direct` / none / anything else | Claim verification (is this TRUE?) | Continue below - verify pipeline. | **Lane rule (do not blend lanes):** `premise` and `approach` audit *thinking* - right problem? right approach? - and end in a reframe/