# AI Dossier

> Use this tool when you need to automate reproducible AI workflows using a standardized instruction format. The AI Dossier enables large language models (LLMs) to work with .ds.md files, solving problems related to workflow integrity and validation. It accepts .ds.md files and JSON configuration as inputs and produces executable workflows as outputs, ideal for use cases requiring structured automation and validation.

Canonical page: https://skillsregistry.net/skills/ai-dossier  
JSON: https://api.skillsregistry.net/v1/skills/ai-dossier

## Description

Enables LLMs to work with the Dossier automation standard, a structured instruction format (.ds.md files) for reproducible AI workflows. Provides tools for discovering dossier registries, verifying integrity through checksums and Ed25519 signatures, and executing multi-step workflows with built-in validation. Supports both local and remote dossier sources with JSON frontmatter-based configuration.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ai-dossier)
- **Repository:** <https://github.com/imboard-ai/ai-dossier/tree/HEAD/mcp-server>

## 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": "ai-dossier"
    }
  }
}
```

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