What is competencia-ml?

A workflow for comparing MercadoLibre listings with competing sellers. It uses marketplace data to examine prices, seller performance, catalogue placement, price changes, and category trends.

Use it to monitor competitors, assess price position, investigate catalogue wins or losses, and choose concrete pricing actions.

It replaces a general sense of competition with specific evidence about where a listing is too expensive, losing visibility, or facing changing market conditions.

competencia-ml — Skill for Claude Code and Codex by kokesaurio

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 kokesaurio/mercadolibre-algoritmodigital --skill competencia-ml

Clone the repo

git clone --depth 1 https://github.com/kokesaurio/mercadolibre-algoritmodigital

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kokesaurio/mercadolibre-algoritmodigital/competencia-ml/github.svg)](https://agentmods.dev/skills/kokesaurio/mercadolibre-algoritmodigital/competencia-ml)

Your own site

<a href="https://agentmods.dev/skills/kokesaurio/mercadolibre-algoritmodigital/competencia-ml"><img src="https://agentmods.dev/badge/skills/kokesaurio/mercadolibre-algoritmodigital/competencia-ml/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kokesaurio/mercadolibre-algoritmodigital/competencia-ml"><img src="https://agentmods.dev/badge/skills/kokesaurio/mercadolibre-algoritmodigital/competencia-ml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.00655
Opus 5.5	$0.00035	$0.00262
Sonnet 5.5	$0.00017	$0.00131
Haiku 4.5	$0.00009	$0.00065

Measured 1mo ago against content hash 0ff7490d4f1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

competencia-ml 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.

skills/competencia-ml/SKILL.md · 55 lines

What it actually says

Análisis de competencia en MercadoLibre

Radiografía de posición competitiva con datos, terminando en decisiones de precio concretas, no en observaciones genéricas.

Requisito

Herramientas ml_* del conector de Algoritmo Digital. Si no están, indicá agregar el conector desde https://mcp.algoritmodigital.com.ar y frená.

Flujo

ml_competitividad — posición de precio de cada publicación frente a su competencia directa. Es el corazón del análisis.
ml_competidores — los vendedores monitoreados: reputación, ventas estimadas, precio promedio. Si el usuario quiere seguir a uno nuevo, indicá que se agrega desde el panel del CRM.
ml_cambios_precio — quién movió precios últimamente y hacia dónde; detecta guerras de precio antes de que duelan.
ml_catalogo — en qué publicaciones de catálogo se está ganando o perdiendo la buy box y por cuánto.
ml_mercado — tendencia general de la categoría si el usuario pregunta por el mercado y no solo por sus ítems.

Formato del análisis

🥊 Posición competitiva — [tienda]

Semáforo general: en cuántas publicaciones se está caro / competitivo / barato.
Los 3-5 casos que importan: ítems donde se pierde catálogo o ventas por precio, con el número exacto (nuestro precio vs el del competidor, y la diferencia).
Movimientos recientes de competidores que cambian el juego.
Recomendación por ítem: subir, bajar, sostener — siempre validada contra ml_rentabilidad o ml_simular_precios: nunca recomendar un precio que dé margen negativo, y decirlo explícitamente cuando igualar a la competencia no cierra con los costos.

Aplicar cambios de precio

Si el usuario decide cambiar precios, usá ml_actualizar_publicacion de a un ítem, mostrando antes → después y esperando confirmación explícita de cada cambio. Después verificá con ml_publicaciones.

Qué no hacer

No recomendar "bajar para competir" sin mirar el margen: ese consejo gratis es el que funde vendedores.
No presentar estimaciones de ventas de competidores como datos exactos: son estimaciones y hay que decirlo.
No cambiar ningún precio sin confirmación explícita por ítem.

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.

1mo ago First seen · 55 lines · 87 tokens per session scan A 0ff7490d4f1f

Subscribe to this mod's changes

competencia-ml is a skill published in the GitHub repository kokesaurio/mercadolibre-algoritmodigital (0 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 655 once invoked, about $0.0003 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 2026-09-09.

Analytics and metrics E-commerce algoritmodigital argentina claude mcp mercadolibre

competencia-ml next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
competencia-mlkokesaurio/mercadolibre-algoritmodigital	Skill	0	1mo ago	MIT	A	87	Claude Code, Codex
category-opportunity-indexjoomcode/joompulse-skills	Skill	54	3d ago	MIT	A	221	Claude Code
growing-leaf-category-trackerjoomcode/joompulse-skills	Skill	54	3d ago	MIT	A	213	Claude Code
ml-product-analysisjoomcode/joompulse-skills	Skill	54	3d ago	MIT	A	229	Claude Code
seller-copilotjoomcode/joompulse-skills	Skill	54	3d ago	MIT	A	230	Claude Code
seller-overview-trackerjoomcode/joompulse-skills	Skill	54	3d ago	MIT	A	226	Claude Code
uncontested-niche-finderjoomcode/joompulse-skills	Skill	54	3d ago	MIT	A	222	Claude Code