# deepseek-harness

> deepseek-harness — henryz838978-deepseek-harness. Use this tool when you need to harness and interact with DeepSeek V4-Pro or V4-Flash devices, solving integration and protocol quirk problems through its Python library, CLI, and MCP server. It provides a standardized interface for inputs and outputs, streamlining the process with 16 documented protocol quirks and 12 probes. Ideal for use in development and testing contexts where reliable DeepSeek device communication is crucial.

Canonical page: https://skillsregistry.net/skills/henryz838978-deepseek-harness  
JSON: https://api.skillsregistry.net/v1/skills/henryz838978-deepseek-harness

## Description

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

## Trust

- **Trust score (0–1):** 0.73
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/HenryZ838978/deepseek-harness)

## 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": "henryz838978-deepseek-harness"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/henryz838978-deepseek-harness` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/henryz838978-deepseek-harness/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