Lets an agent define repo-native AI review checks as markdown files and run them as repeatable pull request status checks in CI.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Enforce source-controlled AI checks in CI before merging risky changes with Continue CLI"
slug: "enforce-source-controlled-ai-checks-in-ci-before-merging-risky-changes-with-continue-cli"
description: "Lets an agent define repo-native AI review checks as markdown files and run them as repeatable pull request status checks in CI."
github_stars: 32622
verification: "security_reviewed"
source: "https://github.com/continuedev/continue"
author: "Continue Dev"
publisher_type: "organization"
category: "CI/CD Integrations"
framework: "Multi-Framework"
tool_ecosystem:
github_repo: "continuedev/continue"
github_stars: 32622
---
# Enforce source-controlled AI checks in CI before merging risky changes with Continue CLI
Lets an agent define repo-native AI review checks as markdown files and run them as repeatable pull request status checks in CI.
## Prerequisites
Continue CLI, GitHub or CI system, repository checkout
## Installation
Use the upstream install or setup path that matches your environment:
- npm i -g @continuedev/cli
Requirements and caveats from upstream:
- Or with npm (requires Node.js 20+):
Basic usage or getting-started notes:
- Paste this into your coding agent of choice:
- Help me write checks for this codebase: https://continue.dev/walkthrough
- ## How it works
- Source: https://github.com/continuedev/continue
- Extracted from upstream docs: https://raw.githubusercontent.com/continuedev/continue/HEAD/README.md
## Documentation
- https://docs.continue.dev
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/enforce-source-controlled-ai-checks-in-ci-before-merging-risky-changes-with-continue-cli/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.