# AgentCut prompts: Agent prompts for editing jobs Paste these into Claude, Codex or Cursor once your MCP server or tool is connected. Each one plans first, asks before it changes anything, and works on a copy. Source: https://agentcut.dev/prompts/#agent Written by AgentCut unless credited. Free to copy, edit and use. Run anything that edits a project on a copy first. --- ## 1. Cut silences on a timeline, with markers first When to use it: You want an agent in Premiere, Resolve or CapCut to remove dead air from an interview or talking head edit without losing control of the cut. Works with: Auto Cut for Premiere Pro (https://agentcut.dev/tools/auto-cut-premiere-rafcopy/), MCP Bridge for Adobe Premiere Pro (https://agentcut.dev/tools/mcp-bridge-for-adobe-premiere-pro/), Wasserman's Unofficial DaVinci MCP (https://agentcut.dev/tools/wasserman-s-unofficial-davinci-mcp/), Resolve MCP Server (guycochran) (https://agentcut.dev/tools/resolve-mcp-server-guycochran/), SmartCut MCP (CapCut talking-head) (https://agentcut.dev/tools/smartcut-mcp-capcut-talking-head/) Save as: cut-silences-timeline.md ~~~~markdown On the timeline "[TIMELINE NAME]" only (it is a duplicate, the original is safe): 1. Find every pause longer than [0.6] seconds on the dialogue track [A1]. 2. Do NOT cut yet. Add a red marker at the start of each pause, named "PAUSE s". 3. Report: number of pauses, total time they add up to, and the 5 longest with timecodes. After I review the markers and say go: 4. Remove each marked pause, keeping 4 frames of handle on both sides so words are not clipped. 5. Ripple the gaps closed on all tracks together so B roll and music stay in sync with dialogue. If a cut would break a clip on another track, skip it and mark it "SKIPPED: overlap". 6. Tell me the old and new duration and how many cuts you made. ~~~~ --- ## 2. Auto captions onto the timeline in a house style When to use it: You need captions for a finished edit and want them on the timeline as editable text, not burned in. Works with: MCP Bridge for Adobe Premiere Pro (https://agentcut.dev/tools/mcp-bridge-for-adobe-premiere-pro/), PremierPro MCP Server (ayushozha) (https://agentcut.dev/tools/premierpro-mcp-server-ayushozha/), DaVinci Resolve MCP Server (samuelgursky) (https://agentcut.dev/tools/davinci-resolve-mcp-server-samuelgursky/), VectCutAPI (CapCut/Jianying API) (https://agentcut.dev/tools/vectcutapi-capcut-jianying-api/), ffmpeg-skill (https://agentcut.dev/tools/ffmpeg-skill/) Save as: auto-captions.md Sources and credit: Netflix Timed Text Style Guide (English USA) (https://partnerhelp.netflixstudios.com/hc/en-us/articles/217350977-English-USA-Timed-Text-Style-Guide): Line length and reading speed limits ~~~~markdown Create captions for the timeline "[TIMELINE NAME]". 1. Use the app's own transcription if this tool supports it, otherwise transcribe the dialogue track locally and build an SRT. 2. Caption rules: - max [42] characters per line, max 2 lines (vertical video: 1 line, max 28) - reading speed under 20 characters per second - each caption on screen between 0.8 and 6 seconds - never split a name, a number and its unit, or an adjective and its noun across lines 3. Correct these names and terms exactly as written: [Name One, Brand Two, Product Three]. 4. Import the captions as a caption or subtitle track, not as burned in graphics. 5. Apply the style: [font], [size], white text, [outline or box], bottom center, inside the title safe area. 6. List the 5 captions you are least sure about with timecodes so I can check them. ~~~~ --- ## 3. Long video to Shorts, with a review step When to use it: You want an agent to pull vertical clips from a podcast, webinar or long YouTube video and you want to approve picks before anything renders. Works with: podcli (https://agentcut.dev/tools/podcli/), n8n: Viral clips from YouTube with Gemini + FFmpeg (https://agentcut.dev/tools/n8n-viral-clips-gemini-ffmpeg/), VectCutAPI (CapCut/Jianying API) (https://agentcut.dev/tools/vectcutapi-capcut-jianying-api/), OpenChatCut (https://agentcut.dev/tools/openchatcut/), ffmpeg-skill (https://agentcut.dev/tools/ffmpeg-skill/) Save as: long-to-shorts.md ~~~~markdown Source: [FILE OR TIMELINE]. Goal: [5] vertical clips, each [20 to 45] seconds. 1. Transcribe the source with word timestamps. 2. Find moments that work with no context, start with a strong first line in the first 2 seconds, and end on a finished thought. 3. Give me a table: start, end, length, first line, last line, one sentence on why it works. Give me [8] options so I can choose. 4. Wait for my picks. 5. For each pick: cut frame accurate, reframe to 1080x1920 keeping the speaker's face in the upper third, add one line captions kept out of the bottom 20% of the frame. 6. Name files `short__.mp4` and give me a list with a suggested title for each. Do not promise views. Just tell me why each clip might hold attention. ~~~~ --- ## 4. Batch export every deliverable from one timeline When to use it: A client needs the same edit in several formats and you are tired of setting up each render by hand. Works with: DaVinci Resolve MCP Server (samuelgursky) (https://agentcut.dev/tools/davinci-resolve-mcp-server-samuelgursky/), DaVinci Resolve MCP (440+ tools) (https://agentcut.dev/tools/davinci-resolve-mcp-440-tools/), MCP Bridge for Adobe Premiere Pro (https://agentcut.dev/tools/mcp-bridge-for-adobe-premiere-pro/), Premiere Pro MCP (PPMCP) (https://agentcut.dev/tools/premiere-pro-mcp-ppmcp/), aftr (https://agentcut.dev/tools/aftr/), ffmpeg-skill (https://agentcut.dev/tools/ffmpeg-skill/) Save as: batch-export.md ~~~~markdown Set up renders for the timeline "[TIMELINE NAME]". Do not start rendering until I confirm. Deliverables: 1. Master: [ProRes 422 HQ], source resolution and fps, stereo audio. Name: [PROJECT]_master_[DATE].mov 2. YouTube: H.264, 1920x1080, source fps, high bitrate. Name: [PROJECT]_youtube.mp4 3. Social square: 1080x1080, center framed. Name: [PROJECT]_1x1.mp4 4. Vertical: 1080x1920, use the "Vertical" timeline if it exists, otherwise ask me. Name: [PROJECT]_9x16.mp4 5. Audio only: WAV 48 kHz 24 bit. Name: [PROJECT]_mix.wav Steps: - Add each one to the render queue with the exact settings above and the output folder [PATH]. - Show me a table of the queued jobs with codec, resolution, fps and file name. - After I say go, render, then report each file's size and duration and flag any that do not match the timeline duration. ~~~~ --- ## 5. Organize and rename footage into bins When to use it: You just imported a shoot and want bins by day, camera and type, plus clean clip names, before you start cutting. Works with: EditAssist (MCP) (https://agentcut.dev/tools/editassist-mcp/), Jumper (MCP for footage search) (https://agentcut.dev/tools/jumper-mcp/), DaVinci Resolve MCP Server (samuelgursky) (https://agentcut.dev/tools/davinci-resolve-mcp-server-samuelgursky/), MCP Bridge for Adobe Premiere Pro (https://agentcut.dev/tools/mcp-bridge-for-adobe-premiere-pro/), FCPXML MCP (https://agentcut.dev/tools/fcpxml-mcp/) Save as: organize-media.md ~~~~markdown In the project "[PROJECT NAME]" media pool or bin "[IMPORT BIN]": 1. Read the metadata of every clip: file name, date, camera or device, resolution, fps, duration, has audio. 2. Propose a bin structure first, for example: 01_VIDEO / / 02_AUDIO / 03_GRAPHICS 04_MUSIC 05_STILLS 99_CHECK (anything you are not sure about) 3. Propose new clip names in the form [DAY]_[CAMERA]_[SCENE or subject]_[NUMBER], for example D1_A_Interview_003. Show me a sample of 10 before and after. 4. Rename the clip names inside the project only. Never rename, move or delete files on disk. 5. Flag clips that do not match the project fps or that have no audio when the others do. 6. Report how many clips went into each bin. ~~~~ --- ## 6. Build a lower third in After Effects When to use it: You want a clean, editable name and title animation built inside your After Effects project by an agent, with controls you can change later. Works with: After Effects MCP (Engine Room) (https://agentcut.dev/tools/after-effects-mcp-engine-room/), AE MCP Bridge (https://agentcut.dev/tools/ae-mcp-bridge/), mcp-aftereffects (Kumo Productions) (https://agentcut.dev/tools/mcp-aftereffects-kumo-productions/), AE-MCP (70+ tools) (https://agentcut.dev/tools/ae-mcp-70-tools/), After Effects MCP (HeroicSwan) (https://agentcut.dev/tools/after-effects-mcp-heroicswan/) Save as: ae-lower-third.md ~~~~markdown In the open After Effects project, create a new comp "LT_Name_Title", 1920x1080, [29.97] fps, 6 seconds. Build: 1. A thin accent bar (shape layer, [accent color hex]) at the bottom left, inside the title safe area (at least 96 px from the left and bottom edges). 2. Text layer "NAME" in [font], 54 px, near black or white depending on [light or dark] background. 3. Text layer "Title or role" in the same font, 32 px, 70% opacity, 8 px under the name. 4. Animation in: bar scales X from 0 to 100% over 10 frames, name slides 24 px from the left and fades in over 12 frames starting at frame 4, title follows 4 frames later. Easy ease out on all entrance keyframes. 5. Hold until 1 second before the end, then animate out in reverse over 8 frames. 6. Add a Null or controller layer with Slider and Color controls for accent color, bar width and text offset, and link them with expressions. 7. Put the text layers in Essential Graphics so the name and title can be edited from Premiere. Before you start, list the layers you will create. After you finish, render one frame at 1 second and at 3 seconds so I can check it. ~~~~ --- ## 7. Turn a comp into a reusable motion template When to use it: You have an After Effects comp you reuse a lot and want an agent to turn its text, colors and timing into controls. Works with: After Effects MCP (Engine Room) (https://agentcut.dev/tools/after-effects-mcp-engine-room/), AE MCP Bridge (https://agentcut.dev/tools/ae-mcp-bridge/), Plainly Videos MCP (official) (https://agentcut.dev/tools/plainly-videos-mcp-official/), mcp-aftereffects (Kumo Productions) (https://agentcut.dev/tools/mcp-aftereffects-kumo-productions/) Save as: motion-template.md ~~~~markdown Comp: "[COMP NAME]". Make it a template that someone who does not know After Effects can use. 1. List every text layer, color, image and timing value in the comp and tell me which ones you suggest exposing as controls. 2. After I confirm, add a "CONTROLS" null with Slider, Color, Checkbox and Point controls for those values, and connect them with expressions. Use clear names like "Accent color" and "Hold seconds". 3. Make text layers auto size their background boxes with sourceRectAtTime so long words do not break the design. 4. Add the chosen controls to the Essential Graphics panel in a logical order: text first, colors second, timing last. 5. Test with a very short text and a very long text and tell me if anything breaks. 6. Do not export the .mogrt. Tell me when it is ready and I will export it. ~~~~ --- ## 8. Relink, conform and rename after a handoff When to use it: Media went offline after moving drives or you received a project from another editor and file names do not match. Works with: DaVinci Resolve MCP Server (samuelgursky) (https://agentcut.dev/tools/davinci-resolve-mcp-server-samuelgursky/), DaVinci Resolve MCP (440+ tools) (https://agentcut.dev/tools/davinci-resolve-mcp-440-tools/), MCP Bridge for Adobe Premiere Pro (https://agentcut.dev/tools/mcp-bridge-for-adobe-premiere-pro/), FCPXML MCP (https://agentcut.dev/tools/fcpxml-mcp/), EditAssist (MCP) (https://agentcut.dev/tools/editassist-mcp/) Save as: conform-rename.md ~~~~markdown Project: "[PROJECT NAME]". New media location: [FOLDER PATH]. 1. List every offline or missing clip with its old path, file name, duration and timecode. 2. Search the new folder for matches by file name first, then by duration plus start timecode if the names changed. 3. Show me a table: offline clip, proposed match, how you matched it (name, or duration plus timecode), confidence. 4. Relink only the high confidence matches after I confirm. Leave the rest offline and mark them in a bin "99_UNMATCHED". 5. Do not transcode, copy or move files on disk. 6. Report how many clips you relinked and how many are still offline. ~~~~ --- ## 9. Loudness and audio cleanup pass When to use it: Your mix is uneven between voices, music and effects and you need it ready for YouTube or a client spec. Works with: Wasserman's Unofficial DaVinci MCP (https://agentcut.dev/tools/wasserman-s-unofficial-davinci-mcp/), Video & Audio Editing MCP (https://agentcut.dev/tools/video-audio-editing-mcp/), ffmpeg-skill (https://agentcut.dev/tools/ffmpeg-skill/), Kinocut (formerly mcp-video) (https://agentcut.dev/tools/kinocut-formerly-mcp-video/) Save as: loudness-pass.md ~~~~markdown File or timeline: [NAME]. Target: [YouTube about -14 LUFS integrated, true peak -1 dBTP] or [client spec]. 1. Measure integrated loudness, loudness range and true peak, and report them. 2. Measure dialogue and music separately if they are on separate tracks. 3. Propose changes before applying them: dialogue level, music ducking under dialogue (how many dB), limiter settings. 4. After I confirm, apply them non destructively (track or clip gain, or a new export, never overwrite the source). 5. Measure again and show before and after numbers side by side. 6. List any spots where dialogue is still hard to hear, with timecodes. ~~~~ --- ## 10. Plan an n8n workflow that clips and captions new uploads When to use it: You want new long videos to turn into captioned clip drafts automatically, and you want the agent to design the workflow before building it. Works with: n8n: Viral clips from YouTube with Gemini + FFmpeg (https://agentcut.dev/tools/n8n-viral-clips-gemini-ffmpeg/), Zvid n8n video workflows (https://agentcut.dev/tools/zvid-n8n-workflows/), VideoBGRemover n8n templates (official) (https://agentcut.dev/tools/videobgremover-n8n-templates-official/) Save as: n8n-clip-pipeline.md ~~~~markdown Design an n8n workflow (I run [self hosted n8n with FFmpeg installed / n8n cloud]) that: 1. Triggers when a new video lands in [Google Drive folder / YouTube channel / S3 bucket]. 2. Gets a transcript with word timestamps. 3. Picks [3] candidate clips of 20 to 45 seconds that work without context. 4. Cuts them with FFmpeg, reframes to 9:16 and burns one line captions. 5. Saves the clips to [folder] and sends me a message in [Slack or email] with the links and the first line of each clip. 6. Never posts anything publicly. A human approves every clip. First give me the node list in order, what each node does, and which credentials I need. Point out which steps need self hosted n8n. Only after I approve, write the workflow JSON I can import. ~~~~