ai-verify — verification in three tiers (Graph Engineering)

Three ways to verify, depending on who fires them: skills you run on purpose, skills that fire themselves mid-workflow, and a chain of review lanes. The chain's router decides which lanes run from the evidence in the diff, never from its size.

Tier 1 — standalone (you run it on purpose)

• Per-requirement verdict against what was actually asked, with a list of gaps → tiers/1-standalone/verify-feature/SKILL.md
• Extract the requirements from the conversation into numbered, falsifiable claims → tiers/1-standalone/spec-extract/SKILL.md

Tier 2 — embedded (fires by itself, mid-workflow)

• Browser verification of the finished feature + blast radius of the routes that depend on the change → tiers/2-embedded/feature-verify/SKILL.md, with blast_radius.ts, setup_harness.sh and references/
• A second opinion from a fresh model instance with no visibility into your reasoning → tiers/2-embedded/second-opinion/SKILL.md

Tier 3 — chain (review lanes picked by evidence)

• Router that picks lanes, estimates cost, and executes → tiers/3-chain/review-router/SKILL.md
• Lanes: code-audit · security-audit · a11y-audit · perf-audit · design-check · build-check
• Merge of all lanes into one deduplicated report → full-review; scope and diff conventions → CONVENTIONS.md

Setup guide and entry router → VERIFICATION-SETUP-GUIDE.md. Evals (apply real bugs and score the reviewer) → evals/README.md: apply-pack.ts, score.ts, bug-catalog.md, example pack answer-key.json.

Lifecycle

Lane: light, standard, full Writes: the verdict, and the open checkpoint's review notes when one exists Read by: CI, the human Dies: with the milestone Next: ai-security when the security trigger fired; ai-write when the public interface changed; ai-visual-recap otherwise

Source: Graph Engineering — Verification Skills (skills from the video, generalized to any stack; attributed, no license — issue H4; no public repo declared in the source).

The ai-engineering seam

1. The router picks the tier using the source's taxonomy.
2. The judge runs at tier decide; the model comes from the ai-engineering config.toml pin. Binary checks run at tier verify.
3. The evals (apply-pack.ts/score.ts) run in ai-engineering's own CI, not in the user's project.
4. Outputs: the verdict is the report. When a checkpoint is open, the same verdict is written into that checkpoint's review notes. Style follows ai-brainstorm › references/artifact-design.md.