Skip to content
Agentmart
Submit a tool

llm-providers

Developer reference for connecting to OpenAI, Anthropic, Gemini, DeepSeek, GLM, MiniMax, MiMo, Mistral, xAI, Qwen, Kimi, Cohere, OpenRouter, Together, and…

Skill by 0xdewy

IndexedMIT
Write a review

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/0xdewy-llm-providers

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.

We use your email only for this newsletter. Privacy

About

Developer reference for connecting to OpenAI, Anthropic, Gemini, DeepSeek, GLM, MiniMax, MiMo, Mistral, xAI, Qwen, Kimi, Cohere, OpenRouter, Together, and Groq APIs, covering auth, endpoints, SDKs, models, and provider gotchas. Only use when explicitly requested.

Use cases: ml, security

No 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. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/llm-providers

What's inside

Skill name
llm-providers
Description
Developer reference for connecting to OpenAI, Anthropic, Gemini, DeepSeek, GLM, MiniMax, MiMo, Mistral, xAI, Qwen, Kimi, Cohere, OpenRouter, Together, and Groq APIs, covering auth, endpoints, SDKs, models, and provider gotchas. Only use when explicitly requested.
License
MIT
Instructions
30 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (21)

  • SKILL.md
  • evals.json · evals/
  • alibaba-qwen.md · references/
  • anthropic.md · references/
  • cohere.md · references/
  • concepts.md · references/
  • deepseek.md · references/
  • google-gemini.md · references/
  • groq.md · references/
  • index.md · references/
  • minimax.md · references/
  • mistral.md · references/
  • moonshot-kimi.md · references/
  • openai.md · references/
  • openrouter.md · references/
  • source-map.json · references/
  • together.md · references/
  • xai.md · references/
  • xiaomi-mimo.md · references/
  • zhipu-glm.md · references/
  • search_refs.py · scripts/

SKILL.md (first lines)

# LLM Providers

Wire an application to a hosted LLM API. Each provider has a card in
`references/<provider>.md`: where to get a key, the env var name, REST base
URL, auth header, OpenAI compatibility, official Python and TypeScript SDKs,
working curl, Python, and TS samples, current model names, and gotchas.

## Workflow

1. Identify provider and language. Run
   `scripts/search_refs.py --limit 4 "<provider or feature terms>"` and open
   only the matching card. `references/concepts.md` covers cross-provider
   topics: OpenAI-compatible endpoints, streaming, retries, tool calling, and
   the env-var convention.
2. Take base URL, auth header, env var, and model string from the card, never
   from memory. If the card is stale or lacks the model, say so and check the
   provider docs linked in the card.
3. Copy the card's sample for the target language. Prefer the `openai` SDK
   against a compatible base URL unless the user wants the vendor SDK.
4. Read the key from the card's env var or a secret store. Never hardcode,
   echo, log, or commit a key, and never accept one pasted into the prompt.
5. Surface the card's gotchas (region limits, special headers, context
   limits, multimodal caveats) before the user hits them.
6. Before claiming a snippet runs, confirm the SDK imports
   (`python -c "import openai"` or the card's package).

This skill targets official hosted APIs. It is not for bypassing rate limits,
region locks, or auth.

From 0xdewy/skills, MIT.

More from 0xdewy/skills

Signals

Stars
0
Forks
0
Open issues
2
Last commit (this folder)
Oct 11, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from 0xdewy

Cite this page

llm-providers skill. Agent Mart. https://agentmart.dev/skills/0xdewy-llm-providers (last updated 2026-10-24)