Llm 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 alinaqi/maggy --skill llm-patterns -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
alinaqi
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 alinaqi/claude-bootstrap at 72a456e6cc.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 72a456e6cc
- Manifest
- skills/llm-patterns/SKILL.md
- Scanned
- 1 file, 309 lines
About this skill
What it does
This skill provides a collection of reusable patterns and templates specifically designed to optimize interactions with Large Language Models (LLMs). It helps structure complex requests, define clear constraints, and standardize output formats for more reliable agent behavior.
When to use it
- You need to enforce strict formatting rules, such as JSON or Markdown tables, in your agent's responses.
- You are building multi-step workflows where the LLM must maintain context across several turns without losing focus.
- You want to test different prompting strategies (e.g., few-shot learning, chain-of-thought) to see which yields better results for a specific task.
Key capabilities
- Structured Output Templates: Pre-built schemas to force consistent data formats from the model.
- Context Management Patterns: Techniques to preserve long-term memory and state within a session.
- Role-Playing Frameworks: Defined personas to guide the tone and expertise level of the AI agent.
- Constraint Enforcement: Specific phrasing patterns to prevent hallucinations or deviation from safety guidelines.
Example prompts
- "Apply the 'JSON Mode' pattern to extract only the customer's name and order ID from this unstructured text."
- "Use the 'Chain-of-Thought' pattern to analyze these sales figures before generating a recommendation."
- "Activate the 'Expert Critic' persona to review my draft code for security vulnerabilities."
Tips & gotchas
Ensure you have sufficient context window remaining when applying complex multi-step patterns, as they consume more tokens. Test each pattern with varied inputs to verify it handles edge cases before deploying it in production workflows.