Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bloodf-durindoor
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/durindoor
What's inside
- Skill name
durindoor- Description
- Set up and discover capabilities on a DurinDoor AI gateway. Use when the user mentions DurinDoor, DURINDOOR_URL, or needs a capability-specific DurinDoor skill.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# DurinDoor ## Setup ```bash export DURINDOOR_URL="http://localhost:20128" export DURINDOOR_KEY="YOUR_DURINDOOR_API_KEY" curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/api/health" ``` Send authenticated requests with `Authorization: Bearer $DURINDOOR_KEY`. Omit the header only when the gateway explicitly allows unauthenticated requests. ## Discover models ```bash curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models" # chat and combos curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/image" # image generation curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/tts" # text-to-speech curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/stt" # speech-to-text curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/embedding" # embeddings curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/web" # web search and fetch; inspect kind curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/rerank" # reranking curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/video" # video generation curl -H "Authorization: Bearer $DURINDOOR_KEY" "$DURINDOOR_URL/v1/models/music" # music generation ``` Use a returned `data[].id` as the request's `model`. Media endpoints (TTS, STT, embeddings, image, video, music, web search, web fetch) also accept no `model`: the gateway then uses the default model and fallbacks set in **Dashboard → Media Routes**, and answers HTTP 400 `no_provider_for_kind` if no connected provider serves that endpoint. Web entries identify `kind` as `webSearch` or `webFetch`. `/v1/models/web` discovers models; requests go to `POST /v1/search` or `POST /v1/web/fetch`. ## Capability skills - Chat: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-chat/SKILL.md - Images: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-image/SKILL.md - TTS: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-tts/SKILL.md - STT: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-stt/SKILL.md - Embeddings: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-embeddings/SKILL.md - Web search: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-web-search/SKILL.md - Web fetch: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-web-fetch/SKILL.md - Video: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-video/SKILL.md - Music: https://raw.githubusercontent.com/bloodf/durindoor/refs/heads/main/skills/durindoor-music/SKILL.md Reference: https://github.com/bloodf/durindoor/blob/main/docs/reference/api.mdx
From bloodf/durindoor, MIT.
More from bloodf/durindoor
- 0.624score
durindoor-tts
bloodf
Convert text to speech through DurinDoor using a model discovered from /v1/models/tts.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-video
bloodf
Generate video through DurinDoor using the dashboard's video route or a model discovered from /v1/models/video.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-chat
bloodf
Send chat and code-generation requests through DurinDoor using OpenAI or Anthropic request formats.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-embeddings
bloodf
Generate vector embeddings through DurinDoor using a model discovered from /v1/models/embedding.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-image
bloodf
Generate images through DurinDoor with a model discovered from /v1/models/image.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-music
bloodf
Generate music through DurinDoor using the dashboard's music route or a model discovered from /v1/models/music.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-stt
bloodf
Transcribe audio through DurinDoor using a model discovered from /v1/models/stt.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-web-fetch
bloodf
Fetch a URL through DurinDoor with a webFetch model discovered from /v1/models/web.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-web-search
bloodf
Search the web through DurinDoor with a webSearch model discovered from /v1/models/web.
SkillAFreshness: A★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 1
- Open issues
- 200
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
- Last release
- Oct 8, 2026 (20 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bloodf/durindoor
- Website
- durindoor.vercel.app/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bloodf
- 0.624score
durindoor-tts
bloodf
Convert text to speech through DurinDoor using a model discovered from /v1/models/tts.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-video
bloodf
Generate video through DurinDoor using the dashboard's video route or a model discovered from /v1/models/video.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-chat
bloodf
Send chat and code-generation requests through DurinDoor using OpenAI or Anthropic request formats.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-embeddings
bloodf
Generate vector embeddings through DurinDoor using a model discovered from /v1/models/embedding.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-image
bloodf
Generate images through DurinDoor with a model discovered from /v1/models/image.
SkillAFreshness: A★ 10Claude Code +9 - 0.624score
durindoor-music
bloodf
Generate music through DurinDoor using the dashboard's music route or a model discovered from /v1/models/music.
SkillAFreshness: A★ 10Claude Code +9
Cite this page
durindoor skill. Agent Mart. https://agentmart.dev/skills/bloodf-durindoor (last updated 2026-10-24)