Skip to content
Back to skills

Durindoor Chat

BSecurity

Send chat and code-generation requests through DurinDoor using OpenAI or Anthropic request formats.

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 19, 2026
ai-agentsbashgitapi

Works with

  • api

Security analysis

B88/100
  • criticalSends environment variables or credentials to an external URL

Pro shows the line behind each finding and how to fix it

Scanned September 19, 2026

npx -y skills add bloodf/durindoor --skill durindoor-chat --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Durindoor Chat?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Durindoor Chat
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/bloodf-durindoor-chat/badge)](https://www.skillsdirectory.com/skills/bloodf-durindoor-chat)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: durindoor-chat
description: Send chat and code-generation requests through DurinDoor using OpenAI or Anthropic request formats.
---

# DurinDoor Chat

Requires `DURINDOOR_URL` and, when enabled, `DURINDOOR_KEY`.

## Discover

```bash
curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models" | jq -r '.data[].id'
MODEL_ID="$(curl -s -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models" | jq -r '.data[0].id')"
```

## OpenAI format

```bash
curl -X POST "$DURINDOOR_URL/v1/chat/completions" \
  -H "Authorization: Bearer $DURINDOOR_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"model\":\"$MODEL_ID\",\"messages\":[{\"role\":\"user\",\"content\":\"Hi\"}],\"stream\":false}"
```

For streaming, set `stream:true` and consume SSE until `data: [DONE]`.

## Anthropic format

```bash
curl -X POST "$DURINDOOR_URL/v1/messages" \
  -H "Authorization: Bearer $DURINDOOR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d "{\"model\":\"$MODEL_ID\",\"max_tokens\":1024,\"messages\":[{\"role\":\"user\",\"content\":\"Hi\"}]}"
```

Use only a model or combo returned by discovery. Provider availability changes with connections and gateway version.

Reference: https://github.com/bloodf/durindoor/blob/main/docs/reference/api.mdx

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.