Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alinaqi/code-review
Mandatory code reviews via /code-review before commits and deploys
Passed 17 of 20 test cases with the skill, and 13 of 20 without it.
and 7 more in the full report
6 fixed13 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
In an unattended CI/CD build pipeline where a non-trivial code change lacks a corresponding ADR in docs/adr/, what action does the pre-review ADR gate take?
| Checked | Without skill | With skill |
|---|---|---|
| Drafts an ADR with Status: proposed before proceeding. | Missed | Passed |
The instructions your model reads when the skill loads.
Purpose: Enforce automated code reviews as a mandatory guardrail before every commit and deployment. Choose between Claude, OpenAI Codex, Google Gemini, or multiple engines for comprehensive analysis.
Sub-skills:
Before any review engine runs, the ADR gate executes automatically:
docs/adr/, _project_specs/, iCPG ReasonNodes, git history for linked ADRs and specsStatus: proposed, proceedAdded to the standard 7 review categories:
| Category | What It Checks |
|---|---|
| ADR Compliance | Change conforms to documented decisions, no undocumented architectural shifts |
| Finding | Severity |
|---|---|
| Change contradicts accepted ADR | Critical |
| Architectural decision not in any ADR | High |
| ADR exists but is outdated/stale | Medium |
| Minor drift from ADR intent | Low |
See adr-gate.md for full protocol, reverse-engineering rules, and configuration.
test cases passed, vs 13 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.