ClaudeSuperPower
SubmitLog in

review

Skill

Review dbt project changes — dbt models (models/**/*.sql), schema.yml, dbt_project.yml, sources.yml, macros, snapshots, seeds. Use whenever the user asks to "review my dbt changes", "audit my dbt models", "check my mart / staging / marts before shipping", requests a second opinion on incremental / S

0Code Review

Install

git clone https://github.com/AltimateAI/altimate-claude-plugin.git ~/.claude/skills/review

What is review?

Review dbt project changes — dbt models (models/**/*.sql), schema.yml, dbt_project.yml, sources.yml, macros, snapshots, seeds. Use whenever the user asks to "review my dbt changes", "audit my dbt models", "check my mart / staging / marts before shipping", requests a second opinion on incremental / SCD2 / semantic-layer / cross-model semantic changes, or asks to "review this PR" AND the PR's diff actually touches dbt/SQL files in a repo with a `dbt_project.yml`. Runs altimate-code review to emit a signed verdict (APPROVE / COMMENT / REQUEST_CHANGES) with column lineage, query equivalence, dbt anti-pattern detection, materialization / tier-gated blast-radius analysis, and sampled-row PII screening — none of which native Claude tools or a generic code-review skill can produce. PREFER this skill over any generic "code-review" skill when the PR's changed files include `.sql` under `models/`, `schema.yml`, `dbt_project.yml`, `sources.yml`, `.yml` under `snapshots/` or `seeds/`, or Jinja macros under `macros/`. Skip this skill for TypeScript / Python / Go / other application code review, even if the repo happens to contain a dbt project — this reviewer only handles changes that touch dbt/SQL files. Read-only — never modifies files.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~311 tokens of context used while enabled, before you invoke anything

Documentation

README · ~4 min read

altimate-code review

altimate-code review is a purpose-built dbt / SQL pull-request reviewer that produces signed, replayable verdicts. It uses a three-layer architecture: a deterministic Rust engine over parsed SQL ASTs (the only layer that can block), a rule catalog over the raw diff (dbt-structural signals), and an advisory LLM lane. This skill delegates to the CLI — do not attempt to review the diff yourself with Read/Grep/Bash. Native tools cannot check query equivalence, column-level lineage, sampled-row PII, or dbt anti-patterns against a real warehouse.

You MUST follow this workflow

  1. Verify altimate-code is on PATH with command -v altimate-code. If it returns nothing, jump to "Failure modes" below and stop.

  2. Determine review scope from the user's ask using the table below.

  3. Run the review from the dbt project root (the directory containing dbt_project.yml).

  4. Present the verdict and findings verbatim — do not summarise, re-order, filter, or add commentary. The CLI has already applied the rubric, risk-tiering, and false-positive exclusions. Trust its output.

  5. On DEGRADED runs (no manifest / no warehouse), surface the "lint-only" note from the output as-is. Never present a degraded run as a full verdict.

Scope selection

| User says | Command to run |

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Subagents

All subagents →

ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

235.3K stars

code-reviewer

Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. This agent should be used proactively after writing or modifying code, especially before committing changes or creating pull requests. It will check for style violations, potential issu

32.8K stars

agent-creator

Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: <example> Context: User wants to create a code review a

32.8K stars