instagram-reel-editor
Skill27 starsChanged 8 months agoApache-2.0View on GitHub
Edits raw travel footage into polished Instagram Reels (9:16, 1080×1920) with cinematic color grading, beat-synced cuts, text overlays, transitions, and background music. Use when the user mentions editing a reel, travel reel, Instagram video, cutting footage, travel clips, reel from footage, or provides folders with destination subfolders and optional shared _music or _fonts.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- hash-anmol/skillstheir own version, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- hash-anmol/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- webapp-testingSkill
- env-hubSkill
- mcp-builderSkill
- mintlify-docs-updaterSkill
- reviewSkill
- shipSkill
- skill-creatorSkill
- specSkill
- internal-commsSkill
- ml-failure-auditSkill
- changelog-generatorSkill
- algorithmic-artSkill
- canvas-designSkill
- remotionSkill
- slack-gif-creatorSkill
- ab-test-setupSkill
- copywritingSkill
- humanizerSkill
- instagram-postingSkill
- marketing-ideasSkill
- seo-auditSkill
- claude-for-legalSkill
- contract-review-risk-scoringSkill
- doc-coauthoringSkill
- docxSkill
- legal-work-pluginSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- pm-skillsSkill
- resume-tailoringSkill
- last30daysSkill
- brand-guidelinesSkill
- excalidrawSkill
- frontend-designSkill
- open-designSkill
- theme-factorySkill
- web-artifacts-builderSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 95
When the user provides a footage folder, follow this sequence:
- Distinctive: line 114
Ask the user to confirm or override.
- Distinctive: line 122
Run the main editor script:
- Very specific: line 136
Use present_files to deliver the final .mp4 to the user.
- Distinctive: line 146
Read both scripts fully before executing.
- Distinctive: line 173
If the root folder contains multiple destination subfolders, ask the user:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Instagram Reel Editor
Transforms raw travel footage folders into cinematic Instagram Reels (9:16 vertical, 1080×1920px). Each destination folder becomes a standalone reel with music, text overlays, and cinematic effects.
Requirements: ffmpeg, Python 3, and moviepy>=2.0. The agent should be able to run shell commands, write files, and present output files to the user.
Folder Contract
The user provides a root folder following this structure:
travel-project/
├── bali/ ← destination folder (one reel per folder)
│ ├── clip1.mp4
│ ├── clip2.MOV
│ └── ...
├── tokyo/
│ └── ...
├── _music/ ← shared background music (randomly selected per reel)
│ ├── track1.mp3
│ └── track2.wav
└── _fonts/ ← shared fonts for text overlays
└── Montserrat-Bold.ttfRules:
- Destination folders = any folder NOT starting with
_ _music/= shared pool; one track randomly selected per destination_fonts/= font(s) for text overlays; use first.ttfor.otffound- Supported clip formats:
.mp4,.mov,.MOV,.MP4,.avi,.mkv
Reel Spec (Instagram Standard)
| Property | Value |
| Resolution | 1080 × 1920 px (9:16 vertical) |
| FPS | 30 fps |
| Duration | 15–60 seconds (target: 30s) |
| Audio | Stereo, 44.1kHz, normalized to -14 LUFS |
| Format | H.264 MP4, AAC audio |
| Text safe zone | 250px top and bottom margins |
Cinematic Style Reference (Instagram Travel Reels 2024–2025)
Based on current trends from top travel creators (@muradosmann, @expertvagabond, @thewanderinglens):
Pacing:
- Hook clip: 1.5–2.5s (most dramatic or beautiful moment)
- Middle clips: 2–4s each
- Outro clip: 3–5s with fade to black
- Total clips: 8–15 clips for a 30s reel
Transitions (in order of current popularity):
xfade=fade– clean dissolve (universal)xfade=wipeleft/wiperight– directional wipexfade=slideleft/slideright– motion slidexfade=circlecrop– cinematic circle reveal- Cut on beat (no transition filter) – high energy sections
Color Grading Presets (choose by destination mood):
warm_golden– Bali, Morocco, Mexico (warm shadows, lifted highlights)cool_teal– Iceland, Norway, mountains (teal shadows, orange skin)moody_dark– night scenes, jungles (crushed blacks, high contrast)bright_airy– beaches, Europe cities (lifted whites, soft pastels)cinematic– default universal preset (slight S-curve, vignette, mild desaturation)
Text Overlay Style:
- Location title: uppercase, bold, white, centered, 80–100px
- Subtitle (optional): regular weight, 40px, 60% opacity
- Appear: fade in at 0.5s, hold, fade out at clip end
- Position: lower third (1400–1600px from top on 1920 tall canvas)
- Drop shadow: 3px offset, 70% black
Audio:
- Fade music in over 1s at start
- Duck music to 20% if original clip has loud audio
- Fade out music over 2s before end
Execution Workflow
When the user provides a footage folder, follow this sequence:
Step 1: Scan and Inventory
python3 /path/to/scripts/scan_footage.py --root <project_root>Outputs a JSON inventory: clip paths, durations, resolutions, has_audio flags.
Step 2: Determine Mood & Preset
Infer the mood from the destination folder name:
bali,mexico,marrakech,portugal,italy→warm_goldeniceland,norway,patagonia,alaska,swiss→cool_tealtokyo,ny,berlin,singapore(night/urban) →moody_darksantorini,maldives,amalfi,greece→bright_airy- anything else →
cinematic(safe default)
Ask the user to confirm or override.
Step 3: Select Music
Randomly select one track from _music/. If _music/ is empty or missing, proceed without music and notify the user.
Step 4: Generate the Reel
Run the main editor script:
python3 /path/to/scripts/build_reel.py \
--clips-dir <destination_folder> \
--music <selected_track> \
--font <font_path> \
--preset <mood_preset> \
--location-name "<Destination Name>" \
--output <output_path>Step 5: Present Output
Use present_files to deliver the final .mp4 to the user.
Report: duration, clips used, music track, preset applied, any clips skipped.
Scripts
See scripts/scan_footage.py — scans project root, returns JSON inventory.
See scripts/build_reel.py — main editor: clips → reel pipeline.
Read both scripts fully before executing. They are self-contained and handle all ffmpeg subprocess calls.
Error Handling
| Issue | Action |
| Clip has no video stream | Skip it, log warning |
| Clip is portrait but low-res | Upscale with padding |
| Clip is landscape | Crop to 9:16 (center crop by default) |
_music/ missing | Build reel silently, note "no music" in report |
_fonts/ missing | Fall back to ffmpeg built-in font (DejaVu) |
| Clip shorter than 1s | Skip it |
| Total footage under 10s | Warn user, use all clips, extend with slow-mo |
Output Naming
<destination-name>_reel_<YYYYMMDD>.mp4
Example: bali_reel_20250414.mp4
Multi-Destination Mode
If the root folder contains multiple destination subfolders, ask the user:
"I found [N] destinations: [list]. Should I edit all of them, or start with one?"
Process them sequentially, one reel per destination.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

