Skip to content
Agentmart
Submit a tool

llm-integration

Patterns for calling LLM APIs, streaming, structured output, and cost controls per stack.

Skill by alec-c4

IndexedMIT★ 1
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/alec-c4-llm-integration

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

Patterns for calling LLM APIs, streaming, structured output, and cost controls per stack.

Use cases: ml

Reviews

Write a review

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

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/llm-integration

What's inside

Skill name
llm-integration
Description
Patterns for calling LLM APIs, streaming, structured output, and cost controls per stack.
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (5)

  • SKILL.md
  • elixir.md · stacks/
  • node.md · stacks/
  • python.md · stacks/
  • rails.md · stacks/

SKILL.md (first lines)

# LLM integration

Use when adding chat, completion, embeddings, or agent features. Read the stack file from `topic_files.llm` after [stack-detection](../stack-detection/SKILL.md).

## Universal principles

- **Provider abstraction** — isolate vendor SDK behind one module; swap models via config.
- **Secrets** — API keys in env only; never in client bundles or logs.
- **Timeouts and retries** — bounded retries with backoff; fail closed on auth errors.
- **Structured output** — schema-validate JSON; do not trust free-form parsing for control flow.
- **Cost** — cap tokens, log usage in server paths, cache idempotent reads where safe.

## Stack reference

| Stack family | File |
|--------------|------|
| Rails | [stacks/rails.md](stacks/rails.md) |
| Node / Next / Nuxt / Svelte | [stacks/node.md](stacks/node.md) |
| Python / Django / FastAPI | [stacks/python.md](stacks/python.md) |
| Elixir / Phoenix | [stacks/elixir.md](stacks/elixir.md) |

Follow project conventions for AI SDK (Vercel AI SDK, LangChain, etc.) when already present — do not add a second stack.

From alec-c4/agent_dev_kit, MIT.

More from alec-c4/agent_dev_kit

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Sep 6, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/alec-c4/agent_dev_kit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from alec-c4

Cite this page

llm-integration skill. Agent Mart. https://agentmart.dev/skills/alec-c4-llm-integration (last updated 2026-10-24)