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 pedroiff0/awesome-skills --skill lattes-xml-projetosgit clone --depth 1 https://github.com/pedroiff0/awesome-skillsWrote 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/pedroiff0/awesome-skills/lattes-xml-projetos)<a href="https://agentmods.dev/skills/pedroiff0/awesome-skills/lattes-xml-projetos"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/lattes-xml-projetos/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/pedroiff0/awesome-skills/lattes-xml-projetos"><img src="https://agentmods.dev/badge/skills/pedroiff0/awesome-skills/lattes-xml-projetos.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 | $0.00112 | $0.01796 |
| Opus 5 | $0.00056 | $0.00898 |
| Sonnet 5 | $0.00022 | $0.00359 |
| Haiku 4.5 | $0.00011 | $0.00180 |
Grade A, and why
lattes-xml-projetos 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lattes XML - Itens de Bolsa/Projetos
Overview
Gera ou reconstrói o trecho de importação XML do Currículo Lattes que contém os itens de
bolsa e projetos de pesquisa (seção ATUACOES-PROFISSIONAIS → ATIVIDADES-DE-PARTICIPACAO-EM-PROJETO).
Útil para limpar um currículo, inserir só os projetos em que o usuário participou, ou converter
um texto livre (datas, título, descrição, equipe, financiador) em entradas PROJETO-DE-PESQUISA.
When to Use
- O usuário pede para "limpar" ou "inserir" itens de bolsa/projeto no Lattes em formato XML.
- Precisa converter um texto solto (datas + título + descrição + equipe + financiador) em entradas válidas.
- Não usar para produção bibliográfica, orientações ou dados pessoais (são outras seções).
- Para manter o LaTeX CV em sincronia com estes dados (títulos/datas/cargos), ver skill
latex-cv-maintenance.
Estrutura do XML (formato NOVO de importação do Lattes)
O formato canônico (idêntico ao exportado pelo próprio site, ex.: Lattes_final.xml) é:
CURRICULO-VITAE
DADOS-GERAIS (atributo NOME-COMPLETO, nao elemento filho)
RESUMO-CV
ENDERECO
FORMACAO-ACADEMICA-TITULACAO?
IDIOMAS?
ATUACOES-PROFISSIONAIS
ATUACAO-PROFISSIONAL
VINCULOS TIPO-DE-VINCULO="Bolsista" ...
ATIVIDADES-DE-PARTICIPACAO-EM-PROJETO
PARTICIPACAO-EM-PROJETO
PROJETO-DE-PESQUISA (atributos abaixo, auto-fechante)
PROJETO-DE-PESQUISA é auto-fechante (não tem filhos EQUIPE/FINANCIADOR em importação
mínima de bolsas — o importador do Lattes preenche equipe/financeiro à parte). A DTD antiga
de 2004 exigia filhos, mas o formato novo NÃO os usa; por isso ela não valida (ver Validação).
Atributos de PROJETO-DE-PESQUISA
NOME-DO-PROJETO(CDATA)NATUREZA:PESQUISA|EXTENSAO|DESENVOLVIMENTO|OUTRASITUACAO:EM_ANDAMENTO|CONCLUIDO|DESATIVADOANO-INICIO/ANO-FIM(deixeANO-FIM=""se for atual)NUMERO-GRADUACAO: conta de graduandos como string (ex.: "1", "4", "0")DESCRICAO-DO-PROJETO(texto livre; manter fiel ao original, só normalizar caracteres)- Em
PARTICIPACAO-EM-PROJETO:FLAG-PERIODO="ATUAL"para em andamento,"ANTERIOR"para concluídos.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 102 lines · 112 tokens per session scan A d6121aeba571
lattes-xml-projetos is a skill published in the GitHub repository pedroiff0/awesome-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 1,796 once invoked, about $0.0006 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
2d-materials-research
Use when researching 2D materials.
academic-conference-planning
Use when planning academic conferences.
2d-materials-best-practices
Use when applying 2d materials best practices.
2d-materials-fundamentals
Use when applying 2d materials fundamentals.
2d-materials-troubleshooting
Use when applying 2d materials troubleshooting.
ENT-best-practices
Use when applying ent medicine best practices.