Prompt engineer
A curated marketplace of open Agent Skills (SKILL.md) — the real skills I use day to day, compatible with the open skills ecosystem.
npx -y skills add Vasallo94/skill-issue --skill prompt-engineerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Disena, itera y versiona prompts de LLM. Documenta el proceso de optimizacion con metricas y variantes.
SKILL.md
1.7 KB, 447 tokens by cl100k_base, as published. Nobody here has run it
Prompt Engineer
Cuando usar esta skill
- Cuando disenes un nuevo prompt para un LLM.
- Cuando iteres sobre un prompt existente para mejorar resultados.
- Cuando quieras documentar y versionar tus prompts.
[!CAUTION] Antes de crear o editar notas, lee las [[.agents/REGLAS_GLOBALES|Reglas Globales]].
Estructura de Documentacion
Los prompts se guardan en 04_Recursos/Prompts/ con esta estructura:
04_Recursos/Prompts/
<proyecto>/
<prompt-name>.md
<prompt-name>-v2.md
Plantilla de Prompt
---
title: "Prompt: Nombre Descriptivo"
tags: [prompt, proyecto]
type: recurso
status: borrador
project: nombre-proyecto
version: 1.0
created: 2026-06-09
updated: 2026-06-09
---
Secciones:
- Objetivo (que debe lograr este prompt)
- Prompt (el texto completo)
- Variables (tabla con nombre, tipo, descripcion)
- Ejemplos de uso (input/output)
- Historial de versiones (version, fecha, cambios, resultado)
- Notas de optimizacion
Principios de Diseno de Prompts
- Se especifico: Cuanto mas concreto, mejor resultado.
- Da ejemplos: Few-shot prompting mejora significativamente.
- Define el rol: "Eres un experto en X..."
- Especifica formato: "Responde en JSON/Markdown/lista..."
- Itera con datos: Prueba con inputs reales, no imaginarios.
Flujo de Trabajo
- Draft: Escribe version inicial.
- Test: Prueba con varios inputs.
- Measure: Documenta resultados.
- Iterate: Ajusta basandote en datos.
- Version: Guarda cada iteracion significativa.
Gives 0 of the 12 instructions most prompt engineering skills give in 447 tokens
Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06
- ask at most three clarifying questionsin 22 of 563, across 15 files
- respond in the user input languagein 14 of 563, across 9 files
- preserve the original intentin 13 of 563, across 11 files
- Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
- Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
- Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
- Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
- validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
- generate quantitative baseline performance reportsin 12 of 563, across 2 files
- create representative test scenariosin 12 of 563, across 2 files
- treat prompts as codein 12 of 563, across 5 files
- test prompts on diverse inputsin 12 of 563, across 8 files
Said here and by no other author read
- Read global rules before editing notes
- Save prompts using the specified directory structure
- Use the provided YAML frontmatter template
- Be specific in the prompt design
- Provide usage examples in the prompt
- Define the LLM role explicitly
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.