# claude-code-dig

> claude-code-dig — dragonliu2018-claude-code-dig. Use this tool when you need to preserve and restore complex coding projects, archiving transcripts and recovering working states to prevent loss of context due to compaction. It solves problems of lost progress and forgotten code by allowing models to "dig back" into previous work. Ideal for use with Claude Code and git version control systems.

Canonical page: https://skillsregistry.net/skills/dragonliu2018-claude-code-dig  
JSON: https://api.skillsregistry.net/v1/skills/dragonliu2018-claude-code-dig

## Description

Never lose context to compaction. Archive pre-compaction transcripts, restore working state, and let the model dig back into what it forgot — MCP tools for Claude Code.

## Trust

- **Trust score (0–1):** 0.56
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Dragonliu2018/claude-code-dig)

## 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": "dragonliu2018-claude-code-dig"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dragonliu2018-claude-code-dig` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dragonliu2018-claude-code-dig/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