Using Llm
- 28 installs
- 5k repo stars
- Updated August 4, 2026
- dtyq/magic
Lists available LLMs and sends chat-completion requests programmatically so a solo builder can call an LLM inside a snippet or agent flow.
About
using-llm lets an agent list the available large language models and send chat-completion requests programmatically. A solo builder reaches for it when they need to call an LLM from within a code snippet, tool, or agent workflow rather than through a chat UI. It abstracts the model-invocation plumbing so LLM calls can be embedded directly in an app.
- List available large language models
- Send chat-completion requests in code
- Call an LLM from inside a snippet or agent
Using Llm by the numbers
- 28 all-time installs (skills.sh)
- Ranked #9,462 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/dtyq/magic --skill using-llmAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 28 |
|---|---|
| repo stars | ★ 5k |
| Last updated | August 4, 2026 |
| Repository | dtyq/magic ↗ |
What it does
Lists available LLMs and sends chat-completion requests programmatically so a solo builder can call an LLM inside a snippet or agent flow.
Who is it for?
embedding LLM calls into snippets, tools, or agents
When should I use this skill?
you need to invoke an LLM programmatically
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10