# forge

> forge — tt-wang-forge. Use this tool when you need to optimize and automate Claude Code workflows with enhanced reliability and efficiency. It solves problems of sequential processing, error handling, and memory management by introducing parallel work, intelligent retry, and memory capabilities. Ideal for complex projects, it takes Claude Code as input and outputs a robust plan-execute-validate loop, integrating with git for version control.

Canonical page: https://skillsregistry.net/skills/tt-wang-forge  
JSON: https://api.skillsregistry.net/v1/skills/tt-wang-forge

## Description

Turn Claude Code into a plan-execute-validate loop with parallel work, intelligent retry, and memory

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-23

## Source

- **Source listing:** [GitHub](https://github.com/TT-Wang/forge)

## 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": "tt-wang-forge"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tt-wang-forge` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tt-wang-forge/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