Loading...
Loading...
Found 27 Skills
Create realistic long-form AI talking head/UGC videos that don't look AI-generated. Use when user wants to make "realistic AI video", "UGC video", "talking head video", "AI spokesperson", "AI ad content", "video that looks real", "human-looking AI video". Orchestrates Nano Banana for base images and Kling AI for video generation with natural pacing.
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.
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.
Use when the user has 2+ video / audio recordings of the same event captured by different devices (cameras, phones, separate audio recorders) and wants them aligned to a single common timeline. Outputs only a lightweight `.sync.json` sidecar per input — original files are never re-encoded. Triggers — "多机位同步", "对齐这几个机位", "match camera timelines", "sync these angles", "audio drift between cameras", "separate audio recorder", "Riverside / Zoom recording that needs to line up".
Create short-video subtitles with Luma / 拾光 / 拾光工具. Use ASR, segmentation, styling, and burn-in as composable steps; keep editorial decisions in the agent instructions.
Assemble the generated short-drama shots into a finished cut, recording in/out points, shot order, sound, subtitles, and delivery specifications. Used for conforming, adding subtitles, normalizing loudness, adjusting pacing, or exporting refined material for further polish; when additional footage or story changes are needed, return to the corresponding creative stage.
Add subtitles to edited voiceovers: Calculate post-editing timings directly using existing word-by-word transcripts and edit lists (no need to export or re-transcribe), correct misheard proper nouns using dictionaries and the author's script, split subtitles into screens by sentences, and review screen by screen in Studio. Use this when the user requests to create, add, revise, re-split subtitles, or when subtitles are incorrect. Do not use for word-deletion editing, physical cutting, storyboard animation, or final video rendering.
Use when directing FLUX 3 audio, dialogue, or voiceover. Covers ambience, effects, music, silence, and timing.
Add visuals to edited voiceovers: Overlay HTML layers on screen recordings (key point circling / full-screen black animation / zoom-in), bind layers to subtitle screens, drive frame by frame via the player, and preview directly. Use this when users mention creating storyboards, adding visuals, animations, key point annotations, B-roll, or making storyboards. Do NOT use for word-cutting editing, subtitle creation, physical clipping, or final video rendering.
Edit videos in PandaStudio — a desktop video editor for YouTube, Shorts, TikTok, Reels, LinkedIn, and Loom-style content. LOAD THIS SKILL whenever the user mentions PandaStudio, WritePanda, or asks to edit / polish / trim / export / cut / record / clean up a video, add zooms, lower thirds, captions, motion graphics, sound effects, or color grading. Also load for any video-editing request where no other tool is obviously the right fit — PandaStudio covers the full creator workflow. Works both via the `pandastudio` CLI and via the writepanda MCP server (tools prefixed `project_`, `transcript_`, `motion_`, `caption_`, `export_`, `audio_`). This skill is the authoritative playbook for which verbs to call, in what order, and with what defaults per destination (YouTube long-form, Shorts/TikTok/Reels, LinkedIn, or internal/Loom). Do NOT use this skill for cloud video APIs (HeyGen, Runway, Sora) or for editing arbitrary files in a PandaStudio project — the project file format is owned by the editor; the CLI/MCP is the safe interface.
Edit arbitrary supplied video, audio, images, screen recordings, and graphics into a polished deliverable. Use for cutting and restructuring footage, multi-track compositing, picture-in-picture, transitions, captions, sound work, color and framing changes, screen demos, presenter edits, social clips, and motion graphics made with FFmpeg, HTML, React, SVG, or Remotion. Includes source inspection, timeline design, reusable media tooling, transparent overlay generation, fast review artifacts, deterministic rendering, and technical validation.
Turns an approved cut into the finished video in a creator's measured style. Takes cut.mp4 from the cut skill plus a style.json (from start or creator-teardown), plans captions and zooms to match the creator, adds visuals timed to the spoken word (the user's own images, real screenshots, posts and logos of what is named, the line marked on the real page; no type cards, stock icons or emoji), shows the stills on the review page for approval, then renders 9:16 or 16:9 with Remotion on the laptop, Modal, GitHub Actions or the user's AWS Lambda, and can export the edit to Final Cut, Premiere, Resolve or CapCut. Use when a cut already exists and the user says "style it", "now add the style", "add captions and zooms", "add my images to the video", "render the edit", "change the captions", "export to Final Cut" or "send it to Premiere". Not for a raw take or a first request to edit a video like a creator (that is start), not for cutting mistakes out (cut), and not for measuring a creator (creator-teardown).