video-editing
AGENTS.md4 starsChanged 4 months agoMITView on GitHub
This repository contains portable agent skills for arbitrary video analysis and editing.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 33,315 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository5 other files it gives its agents.
- analyze-video-editingSkill
- find-brollSkill
- make-product-videoSkill
- record-agent-browser-demoSkill
- video-editingSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 1 is common, 4 are distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 5
Keep each skill under skills/<skill-name>/ with a valid SKILL.md.
- Very specific: line 6
Keep SKILL.md concise and move detailed material into directly linked references/.
- Common: line 8
Never commit source media, generated renders, API keys, transcripts containing private material, or machine-specific absolute paths.
- Distinctive: line 9
Keep analysis evidence distinct from editorial interpretation.
- Distinctive: line 10
Treat semantic audio output as a hypothesis when it conflicts with spectrogram, loudness, or source-separation evidence.
- Distinctive: line 11
Test scripts on synthetic media before publishing.
- Distinctive: line 12
Prefer deterministic review artifacts and validation reports over claims that a render “looks right.”
≈ “Common” is an estimate: at least 1 in 5 of the 42,283 AGENTS.md 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
Repository guidance
This repository contains portable agent skills for arbitrary video analysis and editing.
- Keep each skill under
skills/<skill-name>/with a validSKILL.md. - Keep
SKILL.mdconcise and move detailed material into directly linkedreferences/. - Inspect real command and API payloads before writing parsers.
- Never commit source media, generated renders, API keys, transcripts containing private material, or machine-specific absolute paths.
- Keep analysis evidence distinct from editorial interpretation.
- Treat semantic audio output as a hypothesis when it conflicts with spectrogram, loudness, or source-separation evidence.
- Test scripts on synthetic media before publishing.
- Prefer deterministic review artifacts and validation reports over claims that a render “looks right.”
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.

