Loading...
Loading...
Found 61 Skills
Turn an existing HTML page, landing page, oral script, memo draft, result table, or structured source material into a Xiaohongshu card-style image note. Use this when the user wants page-by-page card planning, cover copy, card text, or a design-ready Xiaohongshu图文 brief based on source material rather than writing a plain note from scratch. This skill is especially for 3:4 Xiaohongshu cards that may mix image-led pages with high-density memo pages, using strong information hierarchy and screenshot-worthy text density rather than generic sparse carousel copy.
Research TikTok Shop listings, shops, pricing, and benchmark products through a local normalize-and-analyze workflow.
Research Xiaohongshu accounts from validated recent-post surfaces, then aggregate account-level content signals without pretending follower or bio metrics are available when the validated profile actor is empty.
Research TikTok Creative Center or ad-library style datasets for winning ad patterns, regions, objectives, hook language, and creative signals without mixing paid ads with organic creator discovery.
Run fact-grounded image generation batches for short-form video production, especially persona images, first-frame candidates, and light consistency edits. Use this when persona and concept inputs already exist and you need local image assets, prompt records, and reusable model-call metadata. This skill should stay anchored to benchmark-backed persona locks and should save both raw provider responses and normalized local asset manifests.
High-level entry point for cross-platform public social data extraction when the user has not named a platform-specific workflow yet.
Transcribe local or remote audio into durable text and timestamp artifacts using hosted Whisper models. Use this when the job is speech-to-text from audio files and you need request/response persistence, optional timestamps, and subtitle-ready outputs.
Turn validated benchmark research into campaign briefs and concept candidates for short-form video production. Use this when you already have research artifacts such as reports, master tables, pattern tables, or comment analyses and need to produce fact-grounded briefs, concept lists, hook options, or test plans. This skill must stay anchored to real source data and should not invent angles, personas, or claims that are not supported by the available research.
Mine Instagram comments to extract audience language, pain points, objections, FAQs, and purchase-intent signals from shortlisted posts or Reels.
Convert normalized timed transcript data into subtitle artifacts such as SRT and VTT. Use this when a stable normalized transcript JSON already exists and the main job is subtitle chunking, timing normalization, and export packaging.
Control image generation requests before execution. Use this when the user wants text-to-image, image edit, reference-image generation, product image, persona image, banner, thumbnail, storyboard image, or image batch variants and the skill must identify inputs, classify the task, choose model/reference rules, then hand off to image-batch-runner.
Scout Instagram hashtag opportunities, branded mentions, and campaign spread to monitor public UGC and creator participation.