# ai-explore-review-loop

> ai-explore-review-loop — kanyun-inc-ai-explore-review-loop-plugin. Use this tool when you need to automate GitHub pull-request reviews and integrate with Claude Code sessions. It solves the problem of manually polling for review updates, allowing for a seamless review/fix/push loop. The tool takes GitHub pull-request reviews as input and outputs continued review sessions, utilizing Supabase durable state and Realtime wake-ups via stdio MCP.

Canonical page: https://skillsregistry.net/skills/kanyun-inc-ai-explore-review-loop-plugin  
JSON: https://api.skillsregistry.net/v1/skills/kanyun-inc-ai-explore-review-loop-plugin

## Description

Enables Claude Code sessions to wait for a durable, exact-head GitHub pull-request review and continue the same review/fix/push loop without polling, using Supabase durable state and Realtime wake-ups via ordinary stdio MCP.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bv3nsk4ts9)
- **Repository:** <https://github.com/kanyun-inc/ai-explore-review-loop-plugin>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "kanyun-inc-ai-explore-review-loop-plugin"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kanyun-inc-ai-explore-review-loop-plugin` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kanyun-inc-ai-explore-review-loop-plugin/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt