Borrowing it
Nothing to install: this file belongs to pyramidheadshark/claude-scaffold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pyramidheadshark/claude-scaffold/main/.claude/skills/prompt-engineering/SKILL.mdgit clone --depth 1 https://github.com/pyramidheadshark/claude-scaffoldWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pyramidheadshark/claude-scaffold/prompt-engineering)<a href="https://agentmods.dev/skills/pyramidheadshark/claude-scaffold/prompt-engineering"><img src="https://agentmods.dev/badge/skills/pyramidheadshark/claude-scaffold/prompt-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pyramidheadshark/claude-scaffold/prompt-engineering"><img src="https://agentmods.dev/badge/skills/pyramidheadshark/claude-scaffold/prompt-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00859 |
| Opus 5 | $0.00000 | $0.00430 |
| Sonnet 5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
prompt-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineering
When to Load This Skill
Load when working with: system prompts, few-shot examples, chain-of-thought, prompt templates, system_prompt, few_shot, prompt evaluation, "промпт", CoT, output formatting, structured output.
System Prompt Structure
A production system prompt has four sections:
## Role
Who Claude is in this context.
## Context
What the system is, what data Claude has access to, key constraints.
## Task
What Claude must do. Be specific — avoid "help the user".
## Output Format
Exact format of the response. Include examples.
Keep system prompts under 2000 tokens. Longer prompts reduce Claude's effective context for user content.
Few-Shot Examples
Place examples AFTER the main instruction, not before. Three examples outperform one. Use diverse examples that cover edge cases.
SYSTEM_PROMPT = """
You are a document classifier. Classify the document into one of: invoice, contract, receipt, other.
Examples:
Document: "Payment due by 30 days for services rendered..."
Label: invoice
Document: "This agreement is made between Party A and Party B..."
Label: contract
Document: "Thank you for your purchase. Total: $42.00"
Label: receipt
"""
Chain-of-Thought
Use explicit CoT for reasoning tasks. Add "Think step by step" or "First reason through the problem, then give your answer."
SYSTEM_PROMPT = """
You are a data analyst. When answering questions about data:
1. First, identify what the question is asking
2. List the relevant data points
3. Reason through the calculation
4. State your final answer
Do not skip directly to the answer.
"""
Do NOT use CoT for classification or extraction tasks — it wastes tokens without improving accuracy.
Structured Output
For JSON output, provide the exact schema in the system prompt:
SYSTEM_PROMPT = """
Extract the following fields from the document. Return ONLY valid JSON, no other text:
{
"date": "YYYY-MM-DD or null",
"amount": float or null,
"vendor": "string or null",
"category": "invoice|receipt|contract|other"
}
"""
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 140 lines · 0 tokens per session scan A b52ed89867ff
prompt-engineering is a skill published in the GitHub repository pyramidheadshark/claude-scaffold (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 859 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ai-ml-engineering
AI/ML Engineering Review: Reviews AI/ML systems for production readiness — model serving, MLOps pipelines, LLM integration patterns, prompt engineering, evaluation frameworks, and responsible AI. Covers model deployment, feature stores, experiment tracking, monitoring/drift detection, and AI safety. Use when the user…
gemini
Skill "gemini" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai gemini model tuning, workflow decision tree, phase 0: environment & iam setup {#phase-0}, 0.1 authentication & project context and 0.2 enable apis.
llm-competition-pipeline
Use when: (1) Entering an LLM-based Kaggle competition (open-source model required, prompt engineering, few-shot), (2) Need to choose between base models (Qwen, DeepSeek, LLaMA), (3) Designing a prompt strategy (zero-shot, few-shot, chain-of-thought), (4) Deciding whether fine-tuning is worth the GPU cost vs prompt…
ai-automation
Workflow automation skills using AI. Build chatbots, automate repetitive tasks, integrate LLMs into pipelines, design intent-based assistants. Triggers on: chatbot, automation, workflow, AI agent, RAG, LLM integration, intent recognition, conversation design.
prompt-design
A structured method for designing prompts, the instructions given to an AI system. It covers the situation, the desired output, constraints, context, user input, and replaceable variables.
prompt-evaluation
A structured method for testing and comparing prompts, the instructions given to an AI. It uses defined criteria, test examples, comparisons, scores, and a recommendation.