anavvanzin
@anavvanzin
Public Skills
corpus-scout
by anavvanzin
Agente de pesquisa iconográfica autônoma para o corpus da tese ICONOCRACY (PPGD/UFSC). Localiza candidatos ao corpus em acervos digitais públicos (Gallica, BnF, Europeana, Library of Congress, BNDigital, British Museum, Numista, Colnect) e entrega cada candidato como nota atômica pronta para o vault Obsidian com frontmatter padronizado, análise iconográfica preliminar, classificação de regime iconocrático, e rastreabilidade GitHub/Drive. Acionar sempre que a tarefa envolver: buscar imagens para o corpus, encontrar candidatos por país/período/suporte/regime, auditar lacunas de cobertura do corpus, gerar notas SCOUT-XXX, executar qualquer das 16 campanhas de busca, ou expandir o corpus sem upload manual de imagens. Nunca acionar para análise de imagens já enviadas pelo usuário — nesse caso usar o IconoCode diretamente.
sync-corpus
by anavvanzin
"Run the full corpus sync pipeline in safe sequence: validate schemas, check vault drift, diff records to corpus export, rebuild companion data, refresh dashboards, and report endurecimento status."
manifesto-gravura
by anavvanzin
Transforma um texto longo (manifesto, ensaio, capítulo, memorial, apresentação de projeto) mais um conjunto de ilustrações numa página HTML autônoma e hospedável, na estética de gravura editorial: papel creme, tinta sépia, vermelho oxblood, serifas Cormorant/EB Garamond, capitulares, pranchas de figuras com legendas e cartões de "ficha técnica". Aceita como fonte um PDF (ex.: export do Claude Design) do qual extrai o texto e as imagens embutidas, ou markdown/texto solto acompanhado de uma pasta de imagens. Use sempre que Ana pedir para "virar o manifesto em site/HTML", "usar as ilustrações que enviei", "fazer a página na estética de gravura", "montar o frontispício", "transformar o PDF do manifesto numa página", ou quando quiser dar forma editorial a prosa acadêmica já escrita usando iconografia real (moedas, selos, gravuras, esculturas). NÃO reescreve o texto da autora — preserva a voz e a prosa; NÃO inventa legendas nem fabrica atribuições de imagem.
ecc-iconocracy-guide
by anavvanzin
Mapa de tarefas da tese ICONOCRACIA para as skills, modos do agente, comandos ECC e ferramentas MCP realmente disponíveis neste repositório. Use quando o usuário pedir "qual skill uso para X", "que ferramentas tenho", "guia ecc", "como faço Y na tese", ou estiver em dúvida sobre qual entrada acionar.
video-editing
by anavvanzin
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
translator
by anavvanzin
Professional translation using Codex's native capabilities. Use this skill when the user needs to translate text between languages with high quality, or when content needs to be localized for different language audiences.
archive-fallback
by anavvanzin
Retry-and-fallback routine for Gallica/Europeana/LOC/BnF/Numista image fetches. Try IIIF manifest first, 2 retries with backoff, then Playwright bypass, then metadata-only record with #imagem-pendente. Use when the user says "arquivo falhou", "tentar fallback", "gallica 429", "europeana timeout", or when SCOUT or ARGOS reports repeated archive failures. Invoked as a sub-routine by SCOUT/ARGOS.
fal-ai-media
by anavvanzin
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
x-api
by anavvanzin
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
dmux-workflows
by anavvanzin
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Codex, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
gitnexus-cli
by anavvanzin
"Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\""
gitnexus-cli
by anavvanzin
"Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\""
gitnexus-guide
by anavvanzin
"Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\""
gitnexus-refactoring
by anavvanzin
"Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\""
dir410346
by anavvanzin
Assistente academico para a disciplina DIR410346 (PPGD/UFSC, Prof. Diego Nunes, 2026.1, segundas-feiras). Le o vault Obsidian em iconocracy-corpus/vault/obsidian-dir410346/ (MOC + aulas 01-13 + leituras + memoriais + templates). Produz memoriais de leitura (400-600 palavras em PT, tom caloroso em primeira pessoa, ABNT NBR 6023:2025, sem travessoes), prepara aulas, fichamentos e artigos acelerados. Mapeia conexoes com a tese ICONOCRACIA apenas quando o material da aula as evocar naturalmente.
validate-corpus
by anavvanzin
Valida os schemas JSON do corpus ICONOCRACY e reporta erros, avisos e quantidade de registros válidos. Use quando o usuário pedir para validar o corpus ou checar integridade dos dados.
SQLite Database Expert
by anavvanzin
Expert in SQLite embedded database development for Tauri/desktop applications with focus on SQL injection prevention, migrations, FTS search, and secure data handling
data-visualization
by anavvanzin
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
obsidian-markdown
by anavvanzin
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
pandoc-pdf-generation
by anavvanzin
PDF generation from markdown via Pandoc/XeLaTeX. TRIGGERS - markdown for PDF, print document, pandoc
pandoc-docx
by anavvanzin
Universal document conversion using Pandoc with focus on DOCX format. Use when converting documents to or from DOCX format, including Markdown, HTML, PDF, and other formats. Supports: (1) Converting other formats to DOCX (Markdown, HTML, reStructuredText, etc.), (2) Converting DOCX to other formats, (3) Custom DOCX templates and styling, (4) Batch document processing
obsidian-deep-research
by anavvanzin
Builds and grows an Obsidian knowledge base through iterative deep research using zettelkasten methodology. Processes documents into atomic vault notes, researches topics from the web, queries existing vault knowledge, and manages research backlogs. Use when the user mentions an Obsidian vault, MOCs, atomic notes, research backlog, or asks to research, investigate, or add findings to their vault. Also use when given a document or report for vault integration.
nextjs-turbopack
by anavvanzin
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
x-api
by anavvanzin
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.