favstash-ai-video-editing-skills
AGENTS.md54 starsChanged 36 days agoApache-2.0View on GitHub
Ten skills in four stages of the short-form loop. For a user-requested installation, follow INSTALL_FOR_AGENTS.md. Each skill installs as its own folder, so it must work alone: keep its helpers, assets and links inside its own folder and name other skills instead of linking into them. Styles carry only their look and its builder; everything shared belongs in edit-video. FavStash tools describe their own parameters; don't copy API details into the skills. Run npm test, npm run validate and git…
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 31,700 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 repository11 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- find-ideasSkill
- write-scriptSkill
- edit-videoSkill
- adaptive-glassSkill
- breakout-cardSkill
- motion-effectsSkill
- paper-gridSkill
- product-motion-adsSkill
- text-over-footageSkill
- publish-and-analyzeSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 1 is common, 0 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 21
Run npm test, npm run validate and git diff --check after changes.
- Common: line 23
Keep creator footage, credentials, renders and private research out of Git.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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
FavStash creator skills
Ten skills in four stages of the short-form loop. For a user-requested installation, follow INSTALL_FOR_AGENTS.md.
| Stage | Skill | Use it to |
| 1 · Research | find-ideas | Find proven references and choose the next idea |
| 2 · Script | write-script | Write one or more hooks to test, one shared body and the editor brief |
| 3 · Edit | edit-video | Cut, caption, sound, motion graphics, safe areas and review: the base for every edit |
| 3 · Edit, style | adaptive-glass, paper-grid, breakout-card, product-motion-ads, text-over-footage | Add exactly one finished look on top of edit-video |
| 3 · Edit, effects | motion-effects | Add named motion effects (kinetic hook, gravity drop, orbit, vertigo, rewind and 28 more) to any edit |
| 4 · Publish & learn | publish-and-analyze | Export, cover, variants, scheduling after approval and results |
Each skill installs as its own folder, so it must work alone: keep its helpers,
assets and links inside its own folder and name other skills instead of linking
into them. Styles carry only their look and its builder; everything shared belongs
in edit-video. FavStash tools describe their own parameters; don't copy API
details into the skills.
Run npm test, npm run validate and git diff --check after changes.
Keep creator footage, credentials, renders and private research out of Git. Preserve existing edit folders and source media. Publishing requires approval for the exact export, caption, destination and time; editing alone does not authorize it.
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.