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 pesquisar-um-temagit 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/pesquisar-um-tema)<a href="https://agentmods.dev/skills/gethouston/houston/pesquisar-um-tema"><img src="https://agentmods.dev/badge/skills/gethouston/houston/pesquisar-um-tema/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/pesquisar-um-tema"><img src="https://agentmods.dev/badge/skills/gethouston/houston/pesquisar-um-tema.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 | $0.00068 | $0.01561 |
| Opus 5 | $0.00034 | $0.00781 |
| Sonnet 5 | $0.00014 | $0.00312 |
| Haiku 4.5 | $0.00007 | $0.00156 |
Grade A, and why
pesquisar-um-tema 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pesquisar Um Tema
Template de origem: Gumloop "AI Research Agent with Automated Report Generation". Adaptado para repasse a outros quatro agentes de marketing, não memorandos de investidor de 20 páginas.
Quando usar
- "pesquisar {topic}" / "preciso de um briefing sobre {topic}" / "qual é o estado de {topic}".
- "resumir o que está acontecendo em {category}".
- Chamado implicitamente por outras skills (
plan-a-campaign,watch-my-competitors,profile-my-customer) quando elas encontram uma lacuna de evidência que precisa de uma pesquisa dedicada.
Conexões que preciso
Eu executo trabalho externo através do Composio. Antes desta skill rodar, verifico se as categorias abaixo estão conectadas. Se faltar, eu nomeio a categoria, peço para você conectar na aba Integrações e paro.
- Busca na web (Exa ou Perplexity) - o motor que encontra e classifica as fontes. Obrigatório, sem alternativa útil, eu preciso de um índice de busca para começar.
- Raspagem de web (Firecrawl) - opcional, busca o texto completo de forma limpa. Se não estiver conectado, eu recorro a uma busca HTTP básica em cada URL de fonte, mais rústica, mas o suficiente para puxar citações de páginas estáticas.
Se a busca na web não estiver conectada, eu paro. A alternativa de raspagem me mantém funcionando por conta própria.
Informações que preciso
Eu leio primeiro o seu contexto de marketing. Para cada campo obrigatório que estiver faltando, eu faço UMA pergunta em linguagem simples (melhor modalidade: app conectado > upload de arquivo > URL > colar) e espero.
- Seu posicionamento - Obrigatório. Por que preciso: um briefing que não filtra pelo seu cliente ideal e categoria é só pesquisa genérica da internet. Se estiver faltando, eu pergunto: "Quer que eu redija seu posicionamento primeiro? É uma skill, leva uns cinco minutos."
- A pergunta de pesquisa - Obrigatório. Por que preciso: escopo inflado torna os briefings inúteis. Se estiver faltando, eu pergunto: "Qual é a única pergunta que esse briefing deve responder, e qual decisão ele destrava?"
- Profundidade - Opcional, padrão standard. Se estiver faltando, eu pergunto: "Quão fundo devo ir, uma varredura de quinze minutos, um mergulho de uma hora, ou uma execução profunda? Se você não tiver preferência, eu sigo com a profundidade padrão."
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 · 92 lines · 68 tokens per session scan A 3bed0c9a5b07
pesquisar-um-tema is a skill published in the GitHub repository gethouston/houston (113 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,561 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 skills, from other repositories
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…
attribution
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives…
co-marketing
When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marketing,' 'cross-promotion,' 'collaborate with another company,' 'partnership…
analytics
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this,"…