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.
npx skills add gethouston/houston --skill evaluar-a-un-candidatogit clone --depth 1 https://github.com/gethouston/houstonWrote 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/skills/gethouston/houston/evaluar-a-un-candidato)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02467 |
| Opus 5 | $0.00038 | $0.01234 |
| Sonnet 5 | $0.00015 | $0.00493 |
| Haiku 4.5 | $0.00008 | $0.00247 |
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.
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.
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.
- 9d ago First seen · 196 lines · 76 tokens per session scan A 6dafbf5fa19b
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.
Other skills, from other repositories
hps-retro-tv
A family history told through five decades of home movies — the opening question, the eras, and what the footage reveals. Built as a decision-grade story deck for family, close friends.
hps-memphis-pop
A pop-culture retrospective on how 1980s design language shaped today's apps — the scenes, the turning point, and the takeaway. Built as a decision-grade story deck for talk audience, design community.
html-ppt-zhangzara-pink-script
A wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends.
html-ppt-zhangzara-8-bit-orbit
A gamer's journey building a retro-arcade collection — the obsession, the hunt, and what the machines came to mean. Built as a decision-grade story deck for friends, hobby community.
html-ppt-zhangzara-retro-zine
A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.
error-recovery-skill
Handle errors gracefully with retry strategies and fallback patterns.