Loading...
Loading...
Found 76 Skills
Generate and manage provider-backed video renders for short-form production. Use this when approved upstream assets or prompt plans already exist and you need local render manifests, downloaded video files, and replaceable routes for talking-head or Seedance generation without losing continuity across concepts and personas.
Create, revise, validate, or audit reusable video-production workflows on the PostPlus workflow platform - the node canvas that turns scripts, reference assets, and per-clip prompts into approved, quoted, human-launched video runs. Use for workflow creation requests, 创建工作流, 搭建工作流, multi-clip UGC workflow design, converting a product idea, hook, script, or reference analysis into generation-node workflows, revising an existing workflow, and pre-launch workflow audits.
Design and audit street-interview advertising concepts and shot scripts built around a public conversation, visible microphone, candid respondent state, question-led persuasion, product interaction, and grounded proof. Use for street interview ads, vox-pop ads, man-on-the-street ads, sidewalk interview ads, public reaction ads, interview-style direct-response ads, converting an offer or approved brief into a street-interview script, reviewing an existing street-interview ad, or handing an approved street-interview concept to image or video production.
Package beat-level edit enhancement instructions from a B-roll plan, subtitle chunks, and optional style context. Use this when the goal is to turn B-roll matching into editor-ready guidance for keyword emphasis, micro-animation hints, A-roll stay-on-face logic, B-roll coverage style, and subtitle interaction.
Extract useful frames from local video files based on task intent, such as persona research, shot breakdown, product visibility, UI walkthroughs, visual-style review, or CTA/compliance checks. Use this when the goal is not generic video analysis, but selecting the right still frames and contact sheets for a specific downstream need.
Design State-Led Lifestyle Ads where product capability is hidden inside a desirable human state. Use for "Lifestyle Ad", "State-Led Lifestyle Ad", "能力藏在状态里", premium product ads, Ray-Ban-like ad feel, tasteful product films, turning features into lifestyle ad scripts, shot-by-shot scripts with camera/action/sound/subtitle/purpose, and approved lifestyle scripts that should proceed directly into production via video-batch-runner for hosted video renders, image-batch-runner when still assets are needed first, or workflow-creation when the script should become a reusable workflow on the PostPlus workflow platform.
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.
High-level entry point for cross-platform public social data extraction when the user has not named a platform-specific workflow yet.
Plan short-form post-edit decisions from A-roll, B-roll, scripts, and reference videos. Use this when the goal is not generic video analysis or rendering, but deciding how to cut a social video beat by beat, including where to stay on face, where to insert proof B-roll, how to use reference patterns, and how to package an actionable edit plan for a human editor or downstream timeline tooling.
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.
Control audio generation requests before execution. Use this when the user asks for TTS, persona voice, voice change, translated dub, cloned voice take, podcast audio, or lip-sync audio handoff and the skill must classify the request before handing execution to voice-batch-runner or a video workflow.
Build explicit learn/do-not-copy contracts for image and video generation references. Use this when a prompt uses benchmark videos, contact sheets, frames, or product images and you need to state exactly what the model should learn, what identity elements must change, and which references should be excluded from the first test.