multiAI Summary Pending
vibers-code-review
Human review workflow for AI-generated GitHub projects with spec-based feedback, security review, and follow-up PRs from the Vibers service.
28,273 stars
bysickn33
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/vibers-code-review/SKILL.md --create-dirs "https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/plugins/antigravity-awesome-skills-claude/skills/vibers-code-review/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/vibers-code-review/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How vibers-code-review Compares
| Feature / Agent | vibers-code-review | Standard Approach |
|---|---|---|
| Platform Support | multi | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Human review workflow for AI-generated GitHub projects with spec-based feedback, security review, and follow-up PRs from the Vibers service.
Which AI agents support this skill?
This skill is compatible with multi.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Vibers — Human Code Review for AI-Generated Projects
You push code. We review it against your spec, fix issues, and send a PR.
## When to Use
Use this skill when:
- You want human review for AI-generated code pushed to GitHub
- You have a project spec and want reviewers to check implementation against it
- You want review feedback delivered as a follow-up PR with suggested fixes
- You are comfortable granting the Vibers service collaborator access to the repository
## Quick Start (3 steps)
### Step 1. Add collaborator
Go to your repo → Settings → Collaborators → Add **`marsiandeployer`**
### Step 2. Add GitHub Action
Create `.github/workflows/vibers.yml`:
```yaml
name: Vibers Code Review
on:
push:
branches: [main]
jobs:
review:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 2
- uses: marsiandeployer/vibers-action@v1
with:
spec_url: 'https://docs.google.com/document/d/YOUR_SPEC_ID/edit'
telegram_contact: '@your_telegram'
```
| Parameter | What it does |
|-----------|-------------|
| `spec_url` | Link to your spec (Google Doc, Notion, etc.). **Must be publicly accessible** (or "anyone with the link can view"). Without access to spec, review is impossible. |
| `review_scope` | `full` (default), `security`, or `spec-compliance` |
| `telegram_contact` | Your Telegram — we'll message you when review is ready |
### Step 3. Add commit rules to your AI agent
Add this block to your project's `CLAUDE.md`, `.cursorrules`, or `AGENTS.md`:
```markdown
## Commit messages
Every commit MUST include a "How to test" section in the body:
- Live URL to open and verify the change
- Step-by-step what to click/check
- Test credentials if login is required
- Expected result for each step
Example:
feat: Add user registration form
How to test:
- Open https://myapp.vercel.app/register
- Fill in email/password, submit
- Check that confirmation email arrives
- Try submitting with invalid email — should show error
- Login: test@example.com / demo123
```
Without "How to test" the reviewer has to guess what to verify, and the review takes longer.
**Done.** Now every push triggers a notification. You'll get a PR with fixes, usually within 24 hours.
## What Happens After Setup
1. You push code → GitHub Action sends us the commit details
2. We read your spec and review changed files
3. We fix issues directly in code and submit a PR
4. You review the PR, merge or comment
We check: spec compliance, security (OWASP top 10), AI hallucinations (fake APIs/imports), logic bugs, UI issues.
We don't check: code style (use ESLint/Prettier), performance benchmarks, full QA (use Playwright/Cypress).
## Limitations
- Requires a GitHub repository and adding `marsiandeployer` as a collaborator
- The referenced spec must be accessible to the review workflow
- The service is not a replacement for full QA, benchmark testing, or local security review
- Turnaround depends on the external Vibers review service
## Pricing
| Plan | Rate | Details |
|------|------|---------|
| **Promo** | $1/hour | Full review + PRs with fixes. We ask for honest feedback in return. |
| **Standard** | $15/hour | Full review + security audit + priority turnaround. |
No subscriptions. No contracts. Pay per review.
## Feedback & Support
Send feedback directly from your agent:
```bash
curl -X POST https://vibers.onout.org/feedback \
-H 'Content-Type: application/json' \
-d '{"message": "Your question or issue", "repo": "https://github.com/you/your-repo"}'
```
Both `message` and `repo` are required. Response: `{"status": "accepted"}`.
Contacts:
- Telegram: [@onoutnoxon](https://t.me/onoutnoxon)
- Moltbook: [moltbook.com](https://moltbook.com) — user **noxon**
- GitHub: [marsiandeployer](https://github.com/marsiandeployer)
## FAQ
**Do I need an API key?**
No. Add collaborator + action, that's it.
**What languages?**
JS/TS, Python, React, Next.js, Django, Flask, and more. If it's on GitHub, we review it.
**What if I disagree with a fix?**
Comment on the PR. We discuss and adjust.
**Can I use this without GitHub?**
Yes — write to Telegram with your code and spec.