prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

1.69x

Quality

54%

Does it follow best practices?

Impact

83%

1.69x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/llm-application-dev/skills/prompt-engineering-patterns/SKILL.md

Evaluation results

77%

21%

Product Review Analysis Pipeline

Structured output pipeline with LangChain

Criteria

Without context

With context

ChatAnthropic import

100%

Correct model name

100%

with_structured_output usage

100%

ChatPromptTemplate.from_messages

100%

Pydantic Field descriptions

100%

70%

Async ainvoke

100%

ValidationError catch

JSONDecodeError catch

Fallback on error

50%

System message included

100%

Chain composition operator

100%

78%

23%

Multi-Step Problem Solving Assistant for an Edtech Platform

Chain-of-thought reasoning with self-consistency

Criteria

Without context

With context

Zero-shot CoT trigger

100%

Steps section label

44%

100%

Answer section label

77%

100%

Verification section label

44%

100%

Verification triggers revision

60%

70%

Self-consistency sample count

100%

Self-consistency temperature

Majority vote selection

100%

Few-shot CoT step format

Confidence reported

100%

Separate verification call

100%

94%

57%

Intelligent Customer Support Bot with Knowledge Base Retrieval

Dynamic few-shot selection with prompt caching

Criteria

Without context

With context

VoyageAI embeddings import

100%

voyage-3-large model

100%

Chroma vectorstore

100%

k=2 examples selected

100%

User/Assistant example format

100%

Prompt caching cache_control

100%

Direct Anthropic SDK

100%

claude-sonnet-4-6 model

100%

RAG context-only instruction

100%

RAG fallback phrase

50%

100%

Citation notation

66%

Hard vs soft constraints

50%

Repository: wshobson/agents
Commit: 91fe43e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Product Review Analysis Pipeline Multi-Step Problem Solving Assistant for an Edtech Platform Intelligent Customer Support Bot with Knowledge Base Retrieval

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.