ai-agents-external-claims

# ai-agents External Claims <!-- vendor-portability: contributor-facing knowledge pack for the rjmurillo/ai-agents repo itself; intentionally references upstream paths (.agents/, .claude/, scripts/, build/) because its audience is repo contributors, not plugin consumers (issue #2050) --> This repo runs verification-based governance: a claim is true when a primary source, gate, or command output says it is, not when a vendor blog, a summary, or an agent asserts it. This skill is the front-gate for one specific claim class: external, vendor, and third-party assertions that arrive from outside the repo and are about to land inside a repo artifact (an ADR, a retro, a memory, a PR description, a session log) or an external deliverable. A wrong number un-cited from a published artifact costs more than the one or two fetches that would have caught it in the same pass. Audience: a zero-context contributor (human or model) holding an external claim and deciding whether it may enter a durable artifact. This skill is the discipline for verifying claims that originate OUTSIDE the repo. For proving an idea that originates inside the repo (hypothesis, probe, eval baseline), use `ai-agents-research-methodology`. For what counts as test evidence for code, use `ai-agents-validation-and-qa`. This skill hardens the general-purpose gstack `claim-verification-before-ingest` pattern into the repo's own artifact-ingest path. ## Triggers - `verify an external claim` - `check a vendor number` - ...