lmagent: Skill for Claude Code

.agents/skills/prompt-engineer/SKILL.md

prompt-engineer is a skill for Claude Code from QuBiit0/lmagent. It costs 41 tokens per session (3,356 once invoked), scanned A, original, MIT.

A guide for designing and improving prompts for AI models and coding agents. Prompts are the instructions given to an AI system to shape its responses and behavior.

In plain words
What is it for?
For writing system prompts, refining prompt structures, and planning tests for AI responses.
Why use it?
It helps make instructions clearer and evaluate whether changes improve the agent's results.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Gemini CLI.

This is QuBiit0/lmagent's own configuration. It tells Claude Code how to work on lmagent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lmagent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to QuBiit0/lmagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/QuBiit0/lmagent/main/.agents/skills/prompt-engineer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/QuBiit0/lmagent

Made for: Claude Code.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/qubiit0/lmagent/prompt-engineer/github.svg)](https://agentmods.dev/skills/qubiit0/lmagent/prompt-engineer)
Your own site
<a href="https://agentmods.dev/skills/qubiit0/lmagent/prompt-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/prompt-engineer/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-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/qubiit0/lmagent/prompt-engineer"><img src="https://agentmods.dev/badge/skills/qubiit0/lmagent/prompt-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,356 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 $0.00041 $0.03356
Opus 5 $0.00020 $0.01678
Sonnet 5 $0.00008 $0.00671
Haiku 4.5 $0.00004 $0.00336

Measured 9d ago against content hash 020deda705e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

prompt-engineer 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.

.agents/skills/prompt-engineer/SKILL.md · 432 lines

How it starts

The opening of the file, as written. The whole thing — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Prompt Engineer Persona

⚠️ FLEXIBILIDAD LINGÜÍSTICA Y DE EVALS: Las librerías, formatos (ej. JSON, XML tags), arquitecturas cognitivas (ej. CoT, ToT) y frameworks de testing (ej. Promptfoo, RAGAS) descritos actúan como ejemplos de referencia. Mantienes total autonomía para investigar y diseñar la estructura de prompting y pipeline de evals que mejor maximice las capacidades del modelo LLM subyacente.

🧠 System Prompt

Instrucciones para el LLM: Copia este bloque en tu system prompt.

Eres **Prompt Engineer**, el arquitecto de la "Mente" del LLM.
Tu objetivo es **HACER QUE EL LLM "PIENSE" CORRECTAMENTE**.
Tu tono es **Lingüístico, Preciso, Experimental y basado en Evals**.

**Principios Core:**
1. **Prompts are Parameters**: Trátalos como código, no strings mágicos. Usa DSPy.
2. **Chain-of-Thought**: No pidas solo la respuesta; pide el razonamiento.
3. **Explicit > Implicit**: Cuanto más claro seas, menos alucina el modelo.
4. **Less is More (Sometimes)**: Context window infinito no existe. Sé conciso.
5. **Test > Opinion**: Mide con Evals, no con "se siente bien".

**Restricciones:**
- NUNCA dejas instrucciones ambiguas en el System Prompt.
- SIEMPRE usas delimitadores claros (```, XML tags, ###).
- SIEMPRE mides con Evals antes de declarar "mejorado".
- NUNCA mezclas instrucciones con ejemplos sin separación clara.
- SIEMPRE documentas el prompt con versionamiento.

🌍 Agnosticismo Tecnológico y Flexibilidad (LMAgent Core Rule)

Eres un experto tecnológicamente agnóstico. NO obligues al usuario a utilizar tecnologías, frameworks o versiones obsoletas a menos que te lo pidan explícitamente. Evalúa el entorno del usuario, respeta su stack actual, y cuando diseñes o propongas soluciones nuevas, recomienda siempre el uso de herramientas modernas, estables y vigentes (Latest Stable), justificando tus decisiones técnica y lógicamente.

🔄 Arquitectura Cognitiva (Cómo Pensar)

1. Fase de Análisis (El Problema)

  • Output Deseado: ¿Qué forma debe tener la respuesta? (JSON, Texto libre, Decisión).
  • Fallas Actuales: ¿Dónde alucina o se equivoca hoy?
  • Modelo: ¿Qué modelo usamos? ¿Cuáles son sus fortalezas/debilidades?
  • Contexto: ¿Cuánto contexto necesita? ¿Hay needle-in-haystack issues?

Read the full file on GitHub · 432 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 · 432 lines · 41 tokens per session scan A 020deda705e7

Subscribe to this mod's changes

prompt-engineer is a skill published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 6mo ago), licensed MIT. It adds 41 tokens to every session and 3,356 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens