LogoClawIndex
CasesSkillsAbout
LogoClawIndex

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.

Skills with input: Image files

Browse skills that use this input.

  • pdf - PDF Processing Guide and Toolkit
    pdfdocument-processingtext-extractiontable-extraction

    ★ 123 · Updated 2026-09-21

    Toolkit for extracting text and tables, creating PDFs, merging or splitting documents, and handling PDF forms.

    ⚙ Extract text and tables⚙ Create PDF documents⚙ Merge and split PDFs
  • codex-cli - OpenAI Codex CLI for coding tasks
    codex-clicodingcode-reviewcli

    ★ 59 · Updated 2026-09-18

    Delegates coding tasks such as code review, refactoring, bug fixes, and feature implementation to OpenAI Codex CLI.

    ⚙ Execute coding tasks via CLI⚙ Perform code reviews⚙ Refactor codebase components
  • summarize-all - Summarize All Pro AI summarization tool
    summarizationaipdfyoutube

    ★ 2 · Updated 2026-09-16

    A multi-featured summarization tool that automatically detects content types, selects summary depth, and processes text, PDFs, audio, images, and videos.

    ⚙ Summarize web pages and documents⚙ Answer questions about content⚙ Compare multiple articles
  • xhs-cli - Xiaohongshu CLI tool for browsing, interacting, and posting
    xhsxiaohongshurednotesocial-media

    ★ 654 · Updated 2026-09-13

    A headless-browser CLI tool for Xiaohongshu to search notes, read posts, browse profiles, like, favorite, comment, and publish from the terminal.

    ⚙ Search notes⚙ Read note details⚙ Browse user profiles
  • ckm:brand - Brand identity, voice, messaging, and asset framework
    branddesign-tokensvisual-identityasset-management

    ★ 1 · Updated 2026-09-11

    Provides brand voice definitions, visual identity standards, messaging frameworks, asset validation, and design token sync.

    ⚙ Inject brand context into prompts⚙ Validate asset parameters⚙ Extract palette colors
  • look-tongji-notes - 9-command agent skill suite for Tongji Look
    tongji-looktranscriptionnote-takingcourse-wiki

    ★ 41 · Updated 2026-09-11

    Provides commands to transcribe lectures, generate study notes, build course wikis, and deploy to GitHub Pages for Tongji Look.

    ⚙ Configure credentials and workspace⚙ List and search courses⚙ Transcribe lectures to text files
  • excelize - Read and write Microsoft Excel spreadsheets in Python
    excelspreadsheetpythonxlsx

    ★ 816 · Updated 2026-09-09

    Read and write Microsoft Excel XLAM, XLSM, XLSX, XLTM, and XLTX spreadsheet files using the excelize-py package.

    ⚙ Create spreadsheet files⚙ Read spreadsheet files⚙ Set cell values
  • MARP Presentation Skill - Convert Markdown to MARP Presentations
    presentationmarkdownslidesMARP

    ★ 32 · Updated 2026-06-30

    Convert long-form markdown content into effective MARP slide decks with speaker notes

    ⚙ Convert markdown to slides⚙ Create speaker notes⚙ Apply design principles
  • paddleocr-text-recognition - Extract text from images and PDFs using PaddleOCR
    OCRtext extractionimage processingPDF processing

    ★ 1 · Updated 2026-05-09

    Extracts text with locations from images and PDF documents

    ⚙ Extract text from images⚙ Extract text from PDFs⚙ Read local files
  • nextjs-performance - Next.js Performance Optimization Guide
    front-endperformancenextjsweb-performance

    ★ 602 · Updated 2026-03-11

    Optimize Next.js applications with image, font, caching, and code splitting strategies

    ⚙ optimize images⚙ load fonts⚙ split code
  • learning-md_to_docx - Convert Markdown to Word Document
    docxwordformattingmarkdown

    ★ 0 · Updated 2026-03-10

    Convert markdown lab reports to Word documents with proper formatting

    ⚙ read markdown file⚙ convert to docx⚙ apply formatting
  • seedance-video-creator - Seedance 2.0 Video Creation with Professional Storyboarding
    video-generationai-videostoryboardvideo-editing

    ★ 276 · Updated 2026-02-11

    Generate professional storyboard prompts and create videos through Jimeng API with automatic download

    ⚙ Generate storyboard prompts⚙ Upload image files⚙ Upload video files
  • gem - Multimodal AI Processing with Google Gemini
    multimodal-aigemini-apidocument-processingvision-ai

    ★ 18 · Updated 2026-02-11

    Process and analyze various file types including PDFs, images, videos, and YouTube links using Google's Gemini multimodal AI.

    ⚙ process text queries⚙ analyze PDF documents⚙ analyze image files
  • imggen - OpenAI Image Generation and OCR Command Line Tool
    image-generationopenai-apiocrcli-tool

    ★ 602 · Updated 2026-02-11

    Generate images from text prompts and extract text from images using OpenAI's APIs.

    ⚙ Generate images from text prompts⚙ Extract text from images⚙ Create transparent background images