evaluar-a-un-candidato

evaluar-a-un-candidato is a skill for Claude Code, Codex from gethouston/houston. It costs 76 tokens per session (2,467 once invoked), scanned A, original, MIT.

A candidate assessment that compares a résumé or public LinkedIn profile with the requirements for an open role. It includes a score, supporting evidence, warning signs, and topics to explore in interviews.

In plain words
What is it for?
Reviewing one candidate, ranking a batch of résumés, or checking whether a LinkedIn profile fits a role.
Why use it?
It reduces the time spent reviewing applications and makes screening decisions easier to explain. It also keeps assessments tied to the role’s stated requirements.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Reviewing one candidate, ranking a batch of résumés, or checking whether a LinkedIn profile fits a role.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gethouston/houston/evaluar-a-un-candidato
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 gethouston/houston --skill evaluar-a-un-candidato
Clone the repo
git clone --depth 1 https://github.com/gethouston/houston

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 evaluar-a-un-candidato

README.md
[![agentmods](https://agentmods.dev/badge/skills/gethouston/houston/evaluar-a-un-candidato/github.svg)](https://agentmods.dev/skills/gethouston/houston/evaluar-a-un-candidato)
Your own site
<a href="https://agentmods.dev/skills/gethouston/houston/evaluar-a-un-candidato"><img src="https://agentmods.dev/badge/skills/gethouston/houston/evaluar-a-un-candidato/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 evaluar-a-un-candidato

Your own site · 80×15
<a href="https://agentmods.dev/skills/gethouston/houston/evaluar-a-un-candidato"><img src="https://agentmods.dev/badge/skills/gethouston/houston/evaluar-a-un-candidato.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,467 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00076 $0.02467
Opus 5 $0.00038 $0.01234
Sonnet 5 $0.00015 $0.00493
Haiku 4.5 $0.00008 $0.00247

Measured 9d ago against content hash 6dafbf5fa19b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

evaluar-a-un-candidato 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.

store/agents-i18n/es/people/.agents/skills/evaluar-a-un-candidato/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluar a un Candidato

Dos rutas, una misma salida: un archivo de candidato por postulante, calificado contra la rúbrica del puesto. Elige source según lo que tengas a mano.

Cuándo usarla

  • source=resume: "revisa este currículum", "revisa la pila de currículums para {role}", "clasifica estos currículums", "quién es el más fuerte del montón". Se admite tanto individual como por lote.
  • source=linkedin: "califica {LinkedIn URL}", "¿es apto el candidato para {role}?", "puntúa este perfil", "0-100 en este LinkedIn". Uno por invocación. Por lote: se corre varias veces.

Ambas rutas encadenan con preparar-a-un-entrevistador y resumir-un-proceso-de-entrevistas, que esperan que exista candidates/{slug}.md.

Conexiones que necesito

Realizo el trabajo externo a través de Composio. Antes de correr esta habilidad, verifico que las categorías de abajo estén conectadas. Si falta alguna, nombro la categoría, te pido que la conectes desde la pestaña de Integraciones, y me detengo.

  • Archivos (Google Drive): recoger los PDF de currículum que sueltes. Obligatoria cuando la fuente es currículum.
  • Extracción web (Firecrawl): leer URLs públicas de LinkedIn o de perfil. Obligatoria cuando la fuente es LinkedIn.
  • Hojas de cálculo (Google Sheets, Airtable): escribir de vuelta la pila clasificada si quieres una. Opcional.
  • ATS (Ashby, Greenhouse, Lever, Workable): deduplicar y escribir de vuelta el estado del candidato. Opcional.

Si ninguna de las categorías obligatorias está conectada, me detengo y te pido que conectes la que corresponde a tu fuente.

Información que necesito

Primero leo tu contexto de personal. Por cada campo obligatorio que falte, hago UNA pregunta en lenguaje sencillo (mejor modalidad: app conectada > archivo > URL > texto pegado) y espero.

  • Rúbrica del puesto: Obligatoria. Por qué la necesito: califico a cada candidato contra tus imprescindibles. Si falta, pregunto: "¿Para qué puesto y nivel es este candidato, y cuáles son tus tres principales imprescindibles?"
  • Currículum o perfil: Obligatorio. Por qué lo necesito: no tengo nada que evaluar sin él. Si falta, pregunto: "Suelta el currículum en tu carpeta de Drive conectada, o pega la URL de LinkedIn."
  • Nombre del candidato: Opcional. Por qué lo necesito: para archivar bien bajo el slug correcto. Si no lo tienes, lo tomo del currículum o del perfil y sigo adelante.

Read the full file on GitHub · 196 lines

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 · 196 lines · 76 tokens per session scan A 6dafbf5fa19b

Subscribe to this mod's changes

evaluar-a-un-candidato is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,467 once invoked, about $0.0004 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.