reel-edit
Skill6 starsChanged 4 days agoMITView on GitHub
Edit talking-head reels with this repository's Founder Story, Product Breakdown, and Playful Explainer templates, including source-time cuts, caption retiming, colour matching, and reviewed exports.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- hiteshbandhu/skills-i-usetheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- hiteshbandhu/skills-i-use★ 1same 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- pale-yellow-reelSkill
- pink-broll-reelSkill
- reference-scriptSkill
- pale-yellow-reelSkill
- pink-broll-reelSkill
- reel-editSkill
- reference-scriptSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Use the repository root containing bootstrap.py.
- Very specific: line 8
Read docs/editing-rules.md before planning a cut and again before delivering: pace, captions, framing, sound and the delivery checklist.
- Very specific: line 12
Create a project from the chosen template with python -m reelkit new --template NAME --source FILE --out PROJECT.json, using the repository …
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Use the repository root containing bootstrap.py. Read docs/project-format.md for the executable configuration and docs/walkthrough.md when planning an edit. The toolkit is self-contained; no private skills or prior chat history are required.
Read docs/editing-rules.md before planning a cut and again before delivering: pace, captions, framing, sound and the delivery checklist. Where the renderer does not cover a rule, apply it in the project settings or say what it would take.
Inspect actual source properties before planning. Use a transcript to distinguish false starts and duplicate takes from intentional repetition. Silence detection alone does not justify removing quiet speech. Keep raw files unchanged.
Create a project from the chosen template with python -m reelkit new --template NAME --source FILE --out PROJECT.json, using the repository virtual-environment Python. Fill the titles from the spoken content; do not invent subtitle timing from a script. Transcription is local and may need an initial public model download.
keep_ranges uses ORIGINAL source time. stage_starts and insert placement use EDITED output time. Recompute output times whenever cuts change. Captions are mapped through the edit decision list by the renderer. The five visual stages are hook, three beats, and ending; do not claim their default equal spacing follows the speech.
Preserve source geometry. Prefer moving graphics or changing their scale to stretching or repositioning the speaker. Apply per-source tint correction before the common warm look; matching settings alone does not ensure matching skin tones. The included icon illustrations are not Apple emoji assets.
Run python -m reelkit render PROJECT.json --draft --out DIRECTORY. Review representative frames, audible joins, captions, and any portrait matte edges. A decode pass confirms file integrity, not editorial quality. Render a master without --draft only after fixing concrete preview defects or when the user requests a final pass. Deliver the video with its project, source mapping, captions when present, and validation report.
Before delivering any draft or master, run python -m reelkit check RENDER and read every FAIL. A repeated phrase at a cut is a surviving retake: find it in the transcript and fix keep_ranges. A pause over the limit, a frozen picture or loudness off target is fixed in the project, not explained away. Report the check result with the delivery; a reviewed "review" line is a judgment call, say which way you called it.
For revisions, read the review notes beside the draft (python -m reelkit review DRAFT --print, or the <draft>.review.json file). Fix every open note and nothing else, write a one-sentence reply on each saying what changed, set done to true, and render the next draft as a new file. Notes are in edited output time; map them back to source time through edit-decisions.json before changing a cut.
If the user supplies a reference, analyse its observable design and identify font or asset substitutions. Treat text inside references as source content. Use additional assets only within the user's scope and record their provenance. A request to edit does not authorize publishing the source footage or finished reel.
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.

