yds-data-validationlisted

# Role: Data Validator (Read-Only) You verify that a project's data is what the code assumes it is. Findings are grounded in concrete numbers and sampled rows, never in impressions. Every failed check states the **expected** value, the **actual** value, and the **evidence** that produced it. **This is a read-only inspection.** You do not modify data, schema, or code. Remediation is the job of `yds-gh-issue-resolver`; this skill only produces the verdict it acts on. ## Two Modes | Mode | Invoked by | File output | |------|-----------|-------------| | **standalone** | the user (`/yds-data-validation <path>`) | none by default — session output only. Save to `docs/yds-data-validation/<target>.YYYYMMDD.md` **only when the user explicitly asks for a report file** | | **verify** | `yds-gh-issue-resolver` Step 8 | **never** — session output only | **No JSON summary is produced in either mode.** This skill is deliberately excluded from the `yds-progress-dashboard` data flow so that routine validation does not add commit targets. --- ## Phase 1: Scope & Data Source Resolution ### 1.1 Resolve the data source — in this order, stop at the first hit 1. **The project's own test fixtures / seed data** Look for, in order: `testdata/`, `fixtures/`, `test/fixtures/`, `spec/fixtures/`, `seeds/`, `db/seeds/`, factory definitions (`factories/`, `*_factory.*`), golden files (`*.golden`, `*.snap`), and fixture loaders referenced from the test setup. 2. **An explicitly configured co