# satori

> satori — timoncool-satori. Use this tool when you need to improve the accuracy of Claude Code by capturing and learning from user corrections and tool failures. Satori solves the problem of inefficient manual updates by automating the process of creating and refining skill drafts, which are then activated after human approval. It takes in user corrections and tool failures as inputs and outputs refined skill drafts, making it ideal for use cases where continuous learning and improvement are crucial.

Canonical page: https://skillsregistry.net/skills/timoncool-satori  
JSON: https://api.skillsregistry.net/v1/skills/timoncool-satori

## Description

A self-learning MCP server for Claude Code that captures user corrections and tool failures, distills them into skill drafts, and activates them only after human approval.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/d0uz90kv5c)
- **Repository:** <https://github.com/timoncool/satori>

## 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": "timoncool-satori"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/timoncool-satori` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/timoncool-satori/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