Llm App Patterns
CheckedHelps with LLMs, patterns as part of building AI and machine learning applications workflows.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add jarmen423/skills --skill llm-app-patterns --full-depth -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
jarmen423
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned jarmen423/skills at d016f7d2c7.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- d016f7d2c7
- Scanned
- 1 file, 723 lines
About this skill
What it does
This skill provides a collection of common patterns and techniques for building applications powered by Large Language Models (LLMs). It helps structure interactions, manage context, and guide LLM behavior to achieve specific goals. The patterns cover areas like tool use, conversation management, and data retrieval. This allows developers to create more robust and predictable AI agent experiences.
When to use it
- Building a chatbot that needs to access external APIs: Use the skill’s tool-use patterns to enable the bot to fetch information or perform actions through API calls.
- Creating an agent for complex tasks requiring multiple steps: Leverage conversation management patterns to break down the task into smaller, manageable interactions.
- Developing a data extraction application from unstructured text: Apply data retrieval patterns to efficiently extract specific pieces of information.
- Designing agents that need to remember and reference previous interactions: Utilize context management techniques for maintaining conversational history and user preferences.
Key capabilities
- Tool Use Patterns
- Conversation Management Patterns
- Data Retrieval Patterns
- Context Management Techniques
Example prompts
- "Show me the pattern for using a calculator API in my agent."
- "How can I structure a multi-turn conversation to gather user requirements?"
- "What's the best way to extract dates from a block of text using an LLM?"
Tips & gotchas
This skill assumes some familiarity with LLMs and prompt engineering. Understanding basic concepts like context windows and token limits will help you effectively apply these patterns.