Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Design and audit evidence-led educational short-form ads that turn a viewer problem, question, contradiction, or comparison into a clear explanation, clause-matched visual proof, an earned product or offer entry, and a practical changed state. Use for Educational Ads, explainer ads, expert or spokesperson ads…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
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 durable run metadata. Keep requests anchored to…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Inspect multiple reference or benchmark videos shot by shot, record observable visual and audio evidence independently for each source, then synthesize their recurring short-form style grammar, one-off details, imitation boundaries, and generator risks in one human-readable Markdown report. Use before image prompt…
Skill Claude CodeCodex
End-to-end TikTok or Instagram slideshow production with vibe-driven prompt writing, local JSON slide management, optional localhost review GUI, batch GPT Image 2 generation, and text overlay compositing. Use this when the user wants to create slideshows or carousels from scratch, including script planning, image…
Skill Claude CodeCodex
Write dense storyboard-grid prompts for short-form image or previsualization workflows. Use this when a generation task needs a 6-9 panel grid with hook logic, visible actions, product timing, and negative constraints before image or video generation.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Convert normalized timed transcript data into subtitle artifacts such as SRT and ASS. Use this when a stable normalized transcript JSON already exists and the main job is subtitle chunking, timing normalization, and export packaging.
Skill Claude CodeCodex
Design, recommend, or audit creator-led short-form product ads built around direct address, believable product interaction, observable proof, and a natural personal verdict. Use for UGC ads, creator ads, selfie testimonials, product reviews, misconception-led or skeptic-to-believer ads, problem-reframe-proof ads…
Skill Claude CodeCodex
Orchestrate the public UGC creative production line from product or research evidence through creator logic, storyboard, image/video/audio generation handoffs, montage planning, and QA. Use this when the user asks for a repeatable UGC-style ad or creator video workflow rather than one isolated media asset.
Skill Claude CodeCodex
Analyze local or remote social videos through PostPlus, especially for TikTok/Reels shot beats, timelines, voiceover or on-screen text capture, creative strategy, and natural Markdown outputs. Use this when you need video-level analysis beyond metadata and want results linked back to source metadata.
Skill Claude CodeCodex
Generate one or many videos through PostPlus from a brief, script, prompt, image, audio, or reference video. Use for text-to-video, image-to-video, first/last-frame video, multimodal reference video, talking-head video, and motion transfer. The agent chooses the matching released endpoint from current schema, writes…
Skill Claude CodeCodex
Transcribe local or remote videos into timed transcripts and subtitle-ready artifacts through PostPlus. Use this when the input is a video and the goal is speech extraction, caption generation, or edit-prep timing.
Skill Claude CodeCodex
Generate and manage persona-aware voice assets for short-form video production, including voice design, script-specific audio takes, and future reusable voice identities. Use this when persona registries and scripts already exist and you need local audio assets, voice manifests, and reviewable voice iterations without…
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Prepare social publishing requests and approval artifacts through the PostPlus platform-owned social publishing workspace.