skills.rest
fratilanico
fratilanicoCOMMUNITY
Explore all skills by this author →
Website𝕏@nicofratilaGitHub

prompt-engineering-apex

Design APEX OS agent prompts with CoT/ToT patterns and JSON-schema constraints.

7|1|Updated Feb 14, 2026
Search Tags:#agents#prompt-design#system-prompt#llm-prompting#cot#tot#apex-os
One-click install
npx skills add https://github.com/fratilanico/apex-os-bad-boy --skill prompt-engineering-apex
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-engineering-apex
Source: https://github.com/fratilanico/apex-os-bad-boy/tree/main/prompt-engineering-apex
Command: npx skills add https://github.com/fratilanico/apex-os-bad-boy --skill prompt-engineering-apex

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use when writing prompts for Claude or any LLM, when agent outputs are inconsistent or low quality, when structuring system prompts for APEX OS agents, or when implementing CoT/ToT reasoning patterns. Triggers on: prompt design, system prompt, instruction engineering, output quality, JSON schema enforcement.

Core Features & Use Cases

  • Seven-component prompt anatomy from HandsOnLLM Ch.6. Every high-stakes agent prompt in APEX OS uses this structure. Deviating = degraded output.
  • CoT/ToT pattern guidance: Zero-shot CoT, Structured CoT, Tree-of-Thought, and anti-patterns to avoid.
  • APEX OS first-class prompts define format, guardrails, and reasoning activators to ensure reliable automation.

Quick Start

Create a seven-component system prompt template that stabilizes LLM outputs for an APEX OS agent and demonstrates CoT/ToT reasoning patterns.

Frequently Asked Questions about prompt-engineering-apex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stabilize inconsistent LLM agent outputs using system prompts?▼

Stabilize inconsistent LLM agent outputs by applying a seven-component prompt anatomy that enforces formatting, guardrails, and JSON-schema constraints to produce reliable, parseable results.

What is the best way to implement Chain of Thought and Tree of Thought prompting patterns?▼

Implement Chain of Thought and Tree of Thought prompting by applying structured pattern guidance, including zero-shot CoT and Tree-of-Thought, while avoiding known anti-patterns that degrade reasoning quality.

How do I enforce JSON schema constraints in LLM prompts for reliable automation?▼

Enforce JSON schema constraints in LLM prompts by defining format and guardrails within first-class system prompts, ensuring the LLM produces reliable and parseable structured data for automation.

Does APEX OS require a specific prompt structure for agent instruction engineering?▼

Yes, APEX OS requires a specific seven-component prompt anatomy for high-stakes agent instruction engineering, ensuring format, guardrails, and reasoning activators are properly defined for reliable automation.

Why does my LLM prompt fail to produce structured outputs and how can I fix it?▼

LLM prompts fail to produce structured outputs due to missing guardrails or JSON-schema enforcement, which you can fix by applying a seven-component prompt anatomy to stabilize the agent's results.

Related Skills

Explore More Software Engineering Skills→
Renzo-TognellaRenzo-Tognella

Pydantic & Data Modeling

Define and validate Pydantic data models for Python schemas.

Community
Intermediate
JamesFincherJamesFincher

instructor

Convert LLM responses into Pydantic-validated JSON with automatic retries.

Community
Advanced
JeffallanJeffallan
10.9k

salesforce-developer

Develop scalable Salesforce applications with Apex, LWC, SOQL, and Salesforce DX.

Community
Advanced
shalin-rahmanshalin-rahman
1

LLM Engineering & Advanced Prompting

Engineer advanced prompting strategies for reliable LLM interactions.

Community
Advanced