prompt-engineering

prompt-engineering is a skill for Claude Code, Codex from jamestorrevillas/dev-skills. It costs 92 tokens per session (1,734 once invoked), scanned A, original, MIT.

A guide for writing, improving, and debugging instructions given to AI models such as Claude, GPT, Gemini, or Copilot. It treats a prompt as a clear specification of the role, goal, context, and required output.

In plain words
What is it for?
Use it to design prompts, plan AI workflows, define output formats, and add checks that verify whether the model produced the requested result.
Why use it?
It helps reduce inconsistent AI results caused by vague goals, missing background, or unclear formatting requirements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it to design prompts, plan AI workflows, define output formats, and add checks that verify whether the model produced the requested result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jamestorrevillas/dev-skills/prompt-engineering
Install

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.

Any agent
npx skills add jamestorrevillas/dev-skills --skill prompt-engineering
Clone the repo
git clone --depth 1 https://github.com/jamestorrevillas/dev-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for prompt-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/prompt-engineering/github.svg)](https://agentmods.dev/skills/jamestorrevillas/dev-skills/prompt-engineering)
Your own site
<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/prompt-engineering"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/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.

agentmods 80×15 button for prompt-engineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/prompt-engineering"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/prompt-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01734
Opus 5 $0.00046 $0.00867
Sonnet 5 $0.00018 $0.00347
Haiku 4.5 $0.00009 $0.00173

Measured 9d ago against content hash d1782932f490, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.github/skills/prompt-engineering/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Engineering

Core Philosophy

A great prompt is not a magic spell — it's a specification. The more precisely you define the goal, context, constraints, and output format, the more reliably the AI performs. Think of prompting like writing a function signature: the model is the implementation, you are the interface designer.

The Golden Rule: If the output isn't what you wanted, the problem is almost always in the prompt — not the model.


Prompt Anatomy (4-Part Structure)

Every effective prompt has four components:

ROLE:    Who the AI should be (expertise, perspective, voice)
GOAL:    What you want done (specific, unambiguous task)
CONTEXT: Relevant background, data, constraints, examples
OUTPUT:  Exact format, length, structure of the response

Example

ROLE: You are a senior TypeScript developer with expertise in React and Next.js.
GOAL: Review this component for performance issues and suggest specific improvements.
CONTEXT: This is a client component in Next.js 15 App Router. 
         Performance is critical — this renders on every keystroke.
         [paste code here]
OUTPUT: List issues as BLOCKER / WARNING / SUGGESTION with specific fix for each.

Core Techniques

Zero-Shot

Ask directly with no examples. Works for well-understood tasks.

Write a conventional commit message for this diff: [diff]

Few-Shot

Provide 2–3 examples before the real task. Best for format-sensitive or pattern-matching tasks.

Examples:
Input: Added login form → Output: feat(auth): add login form with email/password
Input: Fixed null crash → Output: fix(api): handle null response from user endpoint

Now write a commit message for: [diff]

Chain-of-Thought (CoT)

Force step-by-step reasoning. Add "Think step by step" or "Reason through this before answering."

Is this API design RESTful? Think step by step before answering.

Role / Persona Assignment

Set expertise level and perspective upfront.

You are a security engineer specializing in OWASP Top 10.
Review this authentication code for vulnerabilities.

Read the full file on GitHub · 230 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago First seen · 230 lines · 0 tokens per session scan A d1782932f490

Subscribe to this mod's changes

prompt-engineering is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 92 tokens to every session and 1,734 once invoked, about $0.0005 per session on Opus 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 2026-08-31.