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.
git clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote 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/commands/doncheli/don-cheli-sdd/crear-skill)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/crear-skill"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/crear-skill/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/commands/doncheli/don-cheli-sdd/crear-skill"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/crear-skill.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 | $0.00070 | $0.01466 |
| Opus 5 | $0.00035 | $0.00733 |
| Sonnet 5 | $0.00014 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
crear-skill 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 5d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:crear-skill
Objetivo
Meta-skill que permite crear nuevas habilidades para Don Cheli de forma iterativa. Genera el SKILL.md, lo prueba con un prompt de test, evalúa el resultado, y propone mejoras — repitiendo el ciclo hasta lograr calidad óptima.
Compatible con el formato oficial de Anthropic Skills y con el formato HABILIDAD.md de Don Cheli.
Uso
/dc:crear-skill "Generador de reportes semanales del equipo"
/dc:crear-skill --desde-patron # Detectar tarea repetitiva y convertirla en skill
/dc:crear-skill --formato anthropic # Generar solo SKILL.md (formato Anthropic)
/dc:crear-skill --formato doncheli # Generar HABILIDAD.md (formato Don Cheli, default)
/dc:crear-skill --formato dual # Generar ambos formatos
Proceso (5 fases iterativas)
Fase 1: Descubrimiento (1 min)
Preguntar al usuario:
- ¿Qué tarea quieres automatizar? — Descripción en lenguaje natural
- ¿Con qué frecuencia la haces? — Diaria, semanal, por PR, etc.
- ¿Qué inputs necesita? — Archivos, datos, contexto
- ¿Qué output esperas? — Formato, estructura, destino
- ¿Qué grado de libertad tiene? — Alto (texto libre), medio (pseudocódigo), bajo (script exacto)
Fase 2: Generación del Draft (2 min)
Generar automáticamente:
- Metadata YAML (name, description) — optimizada para matching (esto es lo más importante)
- Instrucciones paso a paso en el body
- Ejemplos concretos con inputs/outputs reales
- Referencias a archivos adicionales si > 500 líneas
Principio clave: Solo incluir lo que Claude NO sabe. Omitir conocimiento general, lenguajes, librerías comunes. Enfocarse en reglas específicas del proyecto/empresa.
Fase 3: Test con Prompt Real (1 min)
- Ejecutar la skill con un prompt de prueba proporcionado por el usuario
- Capturar el output completo
- Medir: tokens consumidos, tiempo de ejecución, calidad del resultado
Fase 4: Evaluación (1 min)
Evaluar contra criterios:
| Criterio | Peso | Cómo se mide |
|---|---|---|
| Accuracy | 40% | ¿El output es correcto y completo? |
| Token efficiency | 20% | ¿Cuántos tokens consumió? ¿Hay contenido innecesario? |
| Consistency | 20% | ¿Produce resultados consistentes con diferentes inputs? |
| Metadata match | 20% | ¿Se activa con los prompts correctos? ¿Falsos positivos? |
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.
- 5d ago First seen · 149 lines · 0 tokens per session scan A 3ad5bd49f169
crear-skill is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 29d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,466 once invoked, about $0.0003 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 2026-09-03.
Other commands, from other repositories
add-todo
Capture idea or task as todo from current conversation context.
note
Zero-friction idea capture. Append, list, or promote notes to todos.
resume-work
Resume work from previous session with full context restoration.
resume
Pick up where you left off. Restores context and suggests next action.
statusline
Install or configure the PBR status line in Claude Code.
iterate
A command that repeatedly selects, completes, checks, and records development tasks within one coding session.