ai-patterns-tool-use-patterns SKILL.md skillA

ai-patterns-tool-use-patterns from agents-inc/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add agents-inc/skills/ai-patterns-tool-use-patterns@git:20261016.afd0e14

Pins git:20261016.afd0e14 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
agents-inc/skills
Path
src/skills/ai-patterns-tool-use-patterns/SKILL.md
Versions recorded
3
Latest version
git:20261016.afd0e14, committed Oct 16, 2026
First version recorded
Mar 23, 2026
Size
17,632 bytes
Repository stars
26
License
MIT

Provider-agnostic patterns for LLM function calling, tool loops, and agentic workflows.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Tool Use Patterns

> **Quick Guide:** Tool use (function calling) lets LLMs invoke external functions. The universal pattern is: define tool schemas (JSON Schema for parameters) -> send tools + message to LLM -> detect tool_use in response -> execute locally -> return result to LLM -> repeat until the model responds with text. Guard every loop with a max-step limit, validate all tool inputs before execution, and return structured errors so the model can recover. Use tool choice control (`auto`, `required`, `none`, specific tool) to steer model behavior.

---

<critical_requirements>

## CRITICAL: Before Using This Skill

**(You MUST guard every tool loop with a maximum step limit -- unbounded loops risk infinite API calls and runaway costs)**

**(You MUST validate all tool input arguments before execution -- LLM-generated arguments are untrusted input)**

**(You MUST return structured error messages to the model when tool execution fails -- never silently swallow errors or return empty results)**

**(You MUST use JSON Schema for tool parameter definitions -- all major providers require this format)**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add agents-inc/skills/ai-patterns-tool-use-patterns@sha256:f10cc6ff86cd7b44

The line at the top of this page pins the label git:20261016.afd0e14, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5r7yvqsvrk5qz6l7.svg)](https://markdownregistry.com/a/art_5r7yvqsvrk5qz6l7)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Mar 23, 2026 and Oct 16, 2026, about one every 104 days.

versioncommittedcommitsizeaudit
git:20261016.afd0e14 latest2026-10-16 afd0e14 17,632 BA view · diff
git:20260328.19e48cb2026-03-28 19e48cb 17,908 BA view · diff
git:20260323.1cb67272026-03-23 1cb6727 18,789 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (17632 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agents-inc/skills · 26 stars · license MIT · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5r7yvqsvrk5qz6l7
GET https://markdownregistry.com/api/v1/resolve?ref=agents-inc/skills/ai-patterns-tool-use-patterns
GET https://markdownregistry.com/api/v1/blob/f10cc6ff86cd7b440b2be20b09f8a9aa8c451a8f94367f077955cdac2e63fdaa

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from agents-inc/skills

ai-infrastructure-huggingface-inference SKILL.md skill
agents-inc/skills · src/skills/ai-infrastructure-huggingface-inference/SKILL.md · Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation…
git:20261016.afd0e14 · audit A · 26 stars
ai-infrastructure-litellm SKILL.md skill
agents-inc/skills · src/skills/ai-infrastructure-litellm/SKILL.md · LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend…
git:20261016.afd0e14 · audit A · 26 stars
ai-infrastructure-modal SKILL.md skill
agents-inc/skills · src/skills/ai-infrastructure-modal/SKILL.md · Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript…
git:20261016.afd0e14 · audit A · 26 stars
ai-infrastructure-ollama SKILL.md skill
agents-inc/skills · src/skills/ai-infrastructure-ollama/SKILL.md · Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured…
git:20261016.afd0e14 · audit B · 26 stars
ai-infrastructure-replicate SKILL.md skill
agents-inc/skills · src/skills/ai-infrastructure-replicate/SKILL.md · Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model…
git:20261016.afd0e14 · audit A · 26 stars
ai-infrastructure-together-ai SKILL.md skill
agents-inc/skills · src/skills/ai-infrastructure-together-ai/SKILL.md · Together AI SDK patterns for TypeScript — client setup, chat completions, streaming, structured output, function…
git:20261016.afd0e14 · audit A · 26 stars
ai-observability-langfuse SKILL.md skill
agents-inc/skills · src/skills/ai-observability-langfuse/SKILL.md · LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production…
git:20261016.afd0e14 · audit A · 26 stars
ai-observability-promptfoo SKILL.md skill
agents-inc/skills · src/skills/ai-observability-promptfoo/SKILL.md · Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded…
git:20261016.afd0e14 · audit A · 26 stars
ai-orchestration-langchain SKILL.md skill
agents-inc/skills · src/skills/ai-orchestration-langchain/SKILL.md · LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output…
git:20261016.afd0e14 · audit A · 26 stars
ai-orchestration-llamaindex SKILL.md skill
agents-inc/skills · src/skills/ai-orchestration-llamaindex/SKILL.md · LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in…
git:20261016.afd0e14 · audit A · 26 stars
ai-orchestration-vercel-ai-sdk SKILL.md skill
agents-inc/skills · src/skills/ai-orchestration-vercel-ai-sdk/SKILL.md · Vercel AI SDK patterns - providers, text generation, streaming, structured output, tool calling, chat UI hooks…
git:20261016.afd0e14 · audit A · 26 stars
ai-provider-anthropic-sdk SKILL.md skill
agents-inc/skills · src/skills/ai-provider-anthropic-sdk/SKILL.md · Official Anthropic SDK patterns for TypeScript/Node.js — client setup, Messages API, streaming, tool use, vision…
git:20261016.afd0e14 · audit A · 26 stars

Every file in agents-inc/skills

Browse by kind, by grade A, or by owner.