# decision-graph

> decision-graph — vietqtran-decision-graph. Use this tool when you need to manage and query decision history in AI-assisted codebases, solving problems of transparency and accountability by tracking logic changes, authors, and rationales. It takes Markdown files as input and outputs searchable decision graphs via SQLite FTS5, with integration with MCP servers for AI agents. Ideal for use cases requiring auditable and explainable decision-making processes.

Canonical page: https://skillsregistry.net/skills/vietqtran-decision-graph  
JSON: https://api.skillsregistry.net/v1/skills/vietqtran-decision-graph

## Description

Decision memory layer for AI-assisted codebases — trả lời 'logic nghiệp vụ này có từ bao giờ, ai quyết, vì sao'. Markdown là nguồn sự thật, SQLite FTS5 để search, MCP server cho AI agent.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** verified
- **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/vietqtran/decision-graph)

## 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": "vietqtran-decision-graph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vietqtran-decision-graph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vietqtran-decision-graph/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