iFly-Skills
Speech synthesis, translation, OCR, proofreading, and contract review
All Skills in This Repository (8)
Pure Emerald Level Indicatorsifly-voiceclone-tts
Clone custom voices from audio samples and synthesize speech via iFlytek APIs.
ifly-text-proofread
Proofreads Chinese official documents and detects typos, punctuation errors, and semantic issues via CLI and iflytek's API.
ifly-image-understanding
Send images and questions to iFlytek Spark Vision via WebSocket for image understanding.
ifly-hyper-tts
Generates audio files from text via the Jira API.
ifly-pdf&image-ocr
Extract text from images and PDFs and convert PDFs to JSON, Markdown, or Word.
ifly-translate
Translate text via iFlytek's machine translation API from CLI.
ifly-speed-transcription
Transcribe long audio files via the iFLYTEK Speed Transcription API.
ifly-ocr-invoice
Extract structured invoice data from images and PDFs via the iFlytek OCR API.
Frequently Asked Questions
FAQPage SchemaHow to install iFly-Skills?▼
Run `npx skills add iflytek/iFly-Skills --all -g -y` in your terminal to install all skills in this collection globally.
What can iFly-Skills do?▼
It covers text-to-speech, voice cloning, audio transcription, translation, video dubbing, OCR for invoices and PDFs, Chinese proofreading, image understanding, and contract risk review.
Do I need an iFLYTEK account to use these skills?▼
Yes. Most skills require API credentials from the iFLYTEK console, set as environment variables like XFYUN_APP_ID, XFYUN_API_KEY, and XFYUN_API_SECRET.
Can I use iFly-Skills without coding experience?▼
Yes. Once installed, your agent runs the underlying Python scripts automatically based on your plain-language requests.
Does iFly-Skills support contract review?▼
Yes. The contract review skill handles scanned PDFs and images, detects clause risks, checks bilingual consistency, and outputs structured review reports.
Related Repositories in Content & Communication
View All in Content & Communication→skills
Official Anthropic skills for documents, design, and developer workflows
humanizer
Rewrite AI-sounding text so it reads like a person wrote it
UniGetUI
Automate software translation reviews, diffs, and localization quality checks