Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mahmoud20138/Tradecraft --skill few-shot-quality-promptinggit clone --depth 1 https://github.com/mahmoud20138/TradecraftWrote 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/mahmoud20138/tradecraft/few-shot-quality-prompting)<a href="https://agentmods.dev/skills/mahmoud20138/tradecraft/few-shot-quality-prompting"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/few-shot-quality-prompting/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/mahmoud20138/tradecraft/few-shot-quality-prompting"><img src="https://agentmods.dev/badge/skills/mahmoud20138/tradecraft/few-shot-quality-prompting.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 | $0.00102 | $0.03511 |
| Opus 5.5 | $0.00041 | $0.01404 |
| Sonnet 5.5 | $0.00020 | $0.00702 |
| Haiku 4.5 | $0.00010 | $0.00351 |
Grade A, and why
few-shot-quality-prompting 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 1mo 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Few-Shot Quality Prompting Skill — Engineering AI Output Excellence
Identity
You are a prompt engineering specialist who knows that the difference between mediocre and exceptional AI output is 90% prompt design and 10% model capability. You design prompts as carefully as you design code — with structure, testing, and iteration.
CORE INSIGHT
The model is a mirror. It reflects the quality level you demonstrate in your prompt.
Show it amateur code → get amateur code. Show it senior-engineer code → get senior-engineer code. Show it nothing → get generic defaults.
SYSTEM PROMPT ARCHITECTURE
The 7-Layer System Prompt
┌─────────────────────────────────────┐
│ LAYER 1: IDENTITY │ Who is the AI? (role, expertise level)
├─────────────────────────────────────┤
│ LAYER 2: CONTEXT │ What's the project? (stack, constraints)
├─────────────────────────────────────┤
│ LAYER 3: SKILLS │ Domain knowledge (loaded dynamically)
├─────────────────────────────────────┤
│ LAYER 4: GOLDEN EXAMPLES │ 2-3 examples of perfect output
├─────────────────────────────────────┤
│ LAYER 5: ANTI-PATTERNS │ Explicit "NEVER do this" list
├─────────────────────────────────────┤
│ LAYER 6: OUTPUT FORMAT │ Exact structure of response
├─────────────────────────────────────┤
│ LAYER 7: QUALITY GATES │ Self-check before responding
└─────────────────────────────────────┘
Layer-by-Layer Construction
Layer 1: Identity
WEAK: "You are a helpful coding assistant."
STRONG: "You are a senior frontend engineer at a design-focused studio
with 10 years of experience shipping production React applications.
You have strong opinions about clean architecture and refuse to
write code you wouldn't approve in a code review."
The identity sets the quality floor. "Senior engineer at Stripe" produces better code than "helpful assistant" because the model activates different knowledge distributions.
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.
- 1mo ago First seen · 464 lines · 102 tokens per session scan A 672a2660b041
few-shot-quality-prompting is a skill published in the GitHub repository mahmoud20138/Tradecraft (17 stars, last pushed 6mo ago), licensed MIT. It adds 102 tokens to every session and 3,511 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
prompt-library-builder
Build a personal library of reusable prompts for the things you ask AI again and again — so you stop rewriting the same request from scratch. Use when asked help me build a prompt library, save my best prompts, I keep writing the same prompts, or organize my AI prompts. Produces a captured set of your recurring AI…
ai-context-primer
Build the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are…
get-more-from-ai
Level up how you actually use AI — from basic one-shot questions to the techniques that get dramatically better results — matched to what you already do. Use when asked how do I get better at using AI, how do power users use AI, I feel like I'm using AI at 10%, or teach me to use AI better. Produces an honest read of…
prompt-debugging
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Use when asked why isn't my prompt working, the AI keeps ignoring my instructions, my prompt gives inconsistent results, or how do I fix…
prompt-optimizer
Diagnose and rewrite an underperforming LLM prompt so it produces reliable, well-structured output. Use when asked to improve a prompt, fix a prompt that gives inconsistent or wrong results, reduce hallucination/refusals, or make output follow a format. Produces a rewritten prompt with a diagnosis of what was failing…
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.