Scanlume ocr api
Skill aiskillstore/marketplace/skills/daanaagua/scanlume-ocr-api
Use when calling the Scanlume OCR API for screenshots, JPG, PNG, or image-based tables, especially when a task needs base64 data URLs, mode selection between simple and formatted OCR, or table-aware structured output. Tambem use quando for necessario chamar a API OCR do https://www.scanlume.com/ para screenshots, JPG, PNG ou tabelas em imagem.From its SKILL.md
npx -y skills add aiskillstore/marketplace --skill scanlume-ocr-apiAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
4.9 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it
Scanlume OCR API
Use this skill when the task is specifically about calling the public OCR API behind https://www.scanlume.com/, not when the user only wants the website UI.
Use este skill quando a tarefa for especificamente chamar a API publica de OCR do https://www.scanlume.com/, e nao quando o usuario so quiser usar a interface do site.
English
Workflow
- Confirm the input is an image, not a PDF.
- Read
references/api-contract.mdbefore building the request. - Choose
simpleonly for raw text speed and lower cost. - Choose
formattedfor headings, multi-block layouts, Markdown, HTML, and tables. - If the user gives a local file path, prefer
scripts/scanlume_ocr.pyto build the data URL and call the API. - Read
references/output-shapes.mdbefore consumingformattedresponses, especially table blocks. - State clearly when a request is blocked by public API limits, such as PDF OCR beta access.
Quick Rules
- Public image OCR endpoint:
POST /v1/api/ocr - Auth:
Authorization: Bearer <SCANLUME_API_KEY> - Content type:
application/json - Payload keys:
modeandbase64 base64must be a full data URL such asdata:image/png;base64,...- Do not claim multipart upload support
- Do not claim remote file URL support
- Do not claim public PDF OCR API availability
Mode Selection
-
Use
simplefor:- quick raw text extraction
- lower cost image OCR
- tasks that only need plain text
-
Use
formattedfor:- screenshots with multiple text blocks
- image-based tables
- output needed in Markdown or HTML
- tasks that benefit from
blocksortableSummary
Helpers
- Read
references/api-contract.mdbefore first use. - Read
references/output-shapes.mdbefore parsing formatted OCR results. - Use
python scripts/scanlume_ocr.py <path> --mode formatted --output mdfor a local table image. - Use
python scripts/scanlume_ocr.py <path> --mode simple --output txtfor plain text extraction.
Constraints
- The public v1 API currently covers image OCR only.
- The website supports PDF OCR, but the public PDF API route is still beta-gated.
simplecosts 1 credit per image.formattedcosts 2 credits per image.- Favor precise claims over marketing claims. If the API cannot do something publicly today, say so.
Portugues (Brasil)
Fluxo
- Confirme que a entrada e uma imagem, nao um PDF.
- Leia
references/api-contract.mdantes de montar a requisicao. - Escolha
simpleapenas quando o foco for texto bruto, velocidade e menor custo. - Escolha
formattedpara titulos, multiplos blocos, Markdown, HTML e tabelas. - Se o usuario fornecer um caminho local, prefira
scripts/scanlume_ocr.pypara gerar a data URL e chamar a API. - Leia
references/output-shapes.mdantes de consumir respostasformatted, principalmente em blocos de tabela. - Explique claramente quando uma requisicao estiver bloqueada por limites publicos da API, como o acesso beta ao OCR de PDF.
Regras Rapidas
- Endpoint publico de OCR de imagem:
POST /v1/api/ocr - Auth:
Authorization: Bearer <SCANLUME_API_KEY> - Tipo de conteudo:
application/json - Chaves do payload:
modeebase64 base64precisa ser uma data URL completa comodata:image/png;base64,...- Nao afirme suporte a multipart upload
- Nao afirme suporte a URL remota de arquivo
- Nao afirme disponibilidade publica da API de PDF
Escolha de Modo
-
Use
simplepara:- extracao rapida de texto bruto
- OCR de imagem com menor custo
- tarefas que so precisam de texto puro
-
Use
formattedpara:- screenshots com multiplos blocos de texto
- tabelas em imagem
- saida em Markdown ou HTML
- tarefas que se beneficiam de
blocksoutableSummary
Helpers
- Leia
references/api-contract.mdantes do primeiro uso. - Leia
references/output-shapes.mdantes de processar respostas formatadas. - Use
python scripts/scanlume_ocr.py <path> --mode formatted --output mdpara uma imagem local com tabela. - Use
python scripts/scanlume_ocr.py <path> --mode simple --output txtpara extracao simples de texto.
Restricoes
- A API publica v1 atualmente cobre apenas OCR de imagem.
- O site https://www.scanlume.com/ suporta OCR de PDF na interface web, mas a rota publica de PDF continua beta-gated.
simplecusta 1 credito por imagem.formattedcusta 2 creditos por imagem.- Prefira afirmacoes precisas a afirmacoes promocionais. Se a API publica ainda nao faz algo hoje, diga isso.
What ships with it: 5 files
93.9 KB alongside SKILL.md, 1 of them executable
agents/
- openai.yaml374 B
references/
- api-contract.md3.2 KB
- output-shapes.md3.6 KB
scripts/
- scanlume_ocr.pyruns6.9 KB
- skill-report.json79.8 KB