yt-preflight
Skill1 starsChanged 5 days agoMITView on GitHub
Run every pre-publish check on a YouTube upload in one pass - the title and thumbnail as a pairing, the script's opening hook, runtime, whether the title and first description lines contain the searches the video should win, whether the chapter timestamps will actually render, and drift from the creator's measured voice. Use for "check before I publish", "is this ready to upload", "preflight", "final check", or right after /yt-package and /yt-seo.
In this repository14 other files it gives its agents.
- yt-auditSkill
- yt-chaptersSkill
- yt-commentSkill
- yt-editSkill
- yt-packageSkill
- yt-planSkill
- yt-retentionSkill
- yt-scriptSkill
- yt-seoSkill
- yt-shortsSkill
- yt-sponsorSkill
- yt-testSkill
- yt-viralSkill
- yt-voiceSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Only --title is required. Each other flag adds its checks.
≈ “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
yt-preflight
Six checks live in five different skills, and the one that gets skipped is the chapters block that silently does not render. This runs all of them.
python3 preflight.py --title "I Tested 7 Thumbnail Styles for 30 Days" --thumb "ONE WON" \
--script script.txt --description description.txt --queries "thumbnail test;youtube ctr"Only --title is required. Each other flag adds its checks.
| stage | from | fails when |
| PACKAGE | ../yt-package/title.py | the pairing scores under 60 |
| HOOK | ../yt-script/hookscore.py | the script's first sentence scores WEAK |
| RUNTIME | 150 words a minute | never; it is information |
| QUERIES | /yt-seo's query test | warns when a query's words are missing from the title and first two description lines |
| CHAPTERS | YouTube's rules | the timestamps break 0:00-first, 3+, or 10s-minimum, so they will not render |
| VOICE | ../yt-voice/voice.py | the script drifted (only when ~/.claude/youtube/voice.json exists) |
Order of operations
/yt-script,/yt-package,/yt-seo,/yt-chaptersas normal.preflight.pywith everything.- FIX FIRST: fix item 1, run it again. READY: hand over the title, thumbnail text, description and chapters as copy-ready blocks, then the table.
What READY does not mean
Nothing checkable is wrong. It is not a view prediction: hookscore.py and
title.py are lints, and the README says how well the hook panel does and
does not separate hits from misses.
The gate
Nothing here publishes. This skill writes and you publish. Every output ends in a block the user copies, and the last line of every run is the question: ship it, or change 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.