yt-audit
Skill3 starsChanged 34 days agoMITView on GitHub
Audit a YouTube channel from its recent videos and metrics (packaging, hooks, rhythm) and end in one fix. For 'audit my channel', 'why not growing'.
5 other projects use a version of this, 5 of them edited.
Adopted by
Most recently taken up by
- utillayer/youtube-agent-skilledited, first seen Nov 8, 2026
- swayamdhawan/youtube-agentedited, first seen Oct 15, 2026
- ahmedsakri/youtube-agent-proedited, first seen Oct 15, 2026
- nessalazne/youtube-agent-skilledited, first seen Sep 23, 2026
- Jakeschincariol/youtube-agent-skilledited, first seen Sep 16, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 5
- Jakeschincariol/youtube-agent-skill★ 4772% same
- utillayer/youtube-agent-skill★ 1024% same
- nessalazne/youtube-agent-skill★ 558% same
- ahmedsakri/youtube-agent-pro★ 158% same
- swayamdhawan/youtube-agent★ 072% same
Wrote their own version · 0
None found.
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 repository50 other files it gives its agents.
- automationsSkill
- commentsSkill
- hooksSkill
- ig-auditSkill
- ig-captionSkill
- ig-carouselSkill
- ig-dmSkill
- ig-humanSkill
- ig-profileSkill
- ig-reelSkill
- ig-storySkill
- ig-viralSkill
- inboxSkill
- linkedin-comment-drafterSkill
- linkedin-content-plannerSkill
- linkedin-employee-advocacySkill
- linkedin-engager-analyticsSkill
- linkedin-hook-extractorSkill
- linkedin-humanizerSkill
- linkedin-interviewerSkill
- linkedin-post-writerSkill
- linkedin-profile-optimizerSkill
- linkedin-reply-handlerSkill
- linkedin-repurposerSkill
- linkedin-thread-monitorSkill
- naver-ai-citeSkill
- naver-draftsSkill
- naver-engageSkill
- naver-keywordsSkill
- naver-postSkill
- performance-reviewSkill
- publishSkill
- repurposeSkill
- schedule-weekSkill
- setupSkill
- threadsSkill
- troubleshootSkill
- voice-profileSkill
- yt-benchmarkSkill
- yt-chaptersSkill
- yt-commentSkill
- yt-editSkill
- yt-packageSkill
- yt-planSkill
- yt-retentionSkill
- yt-scriptSkill
- yt-seoSkill
- yt-shortsSkill
- yt-uploadSkill
- yt-viralSkill
The file
We split this skill into the rules it gives an agent
6 rules. 2 are common, 0 are distinctive, and 4 are very specific to this project.
2
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 15
Never invent a number, a result or a source.
- Very specific: line 22
Call get_insights on each of the last ten (the link works as id): views, likes and comments.
- Very specific: line 24
If a call answers workspace_required, show the workspaces it lists, ask which one, and pass workspaceId.
- Very specific: line 33
The last ten titles, as a set: Read them as a list, the way the channel page shows them.
- Very specific: line 36
Upload rhythm: Not frequency: CONSISTENCY.
- Common: line 45
Never open an audit with praise you do not mean, and never end one with a list of twenty things.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Adapted from Jakeschincariol/youtube-agent-skill (MIT). Not affiliated with the original author.
yt-audit
An audit that lists twenty problems is a way of avoiding the one that matters. This ends in ONE fix. Use it for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.
Before you write
- Read
~/.uplika/<workspace-slug>/voice.mdif it exists. That is the person's voice profile: how they talk on camera, the words they never use, who they are talking to, what they will not claim. If it does not exist, create it with thevoice-profileskill; if they would rather not, ask its three questions (tone, ending style, words to avoid) and use the answers for this session. - Never invent a number, a result or a source. If a figure would strengthen it and you do not have one, ask for it or write the line without it.
With Uplika connected
The input is the person's own connected channel instead of a pasted URL.
- Find the YouTube account in
list_accounts, then calllist_channel_postswith itsaccountId. Each item'stextis the title, a blank line, then the description;timestampis the upload date;thumbnailUrlis the thumbnail image;permalinkis the link. - Call
get_insightson each of the last ten (the link works asid): views, likes and comments. Null means YouTube did not report it, not zero. - What Uplika cannot see: impressions, click-through rate and retention. Ask the person for those from YouTube Studio, or send them to
yt-retentionwith the export. - If a call answers
workspace_required, show the workspaces it lists, ask which one, and passworkspaceId. A channel that is not connected: https://uplika.com/dashboard/connections, or use the steps without Uplika. Other errors:get_helpwith the code. youtube_quota_exhaustedfromlist_channel_posts, ornoteCodeyoutube_quota_exhaustedfromget_insights(it answers without numbers that day): Uplika's daily YouTube limit, which everyone on Uplika shares, ran out: stop and do not repeat the call, tell the person when it refills (resetsAt, or the time in the message), and do not ask them to reconnect, because it is not their account (faq:youtube-daily-limit). Audit with what you have, or pick it up after that time.
Without Uplika
The person pastes the channel URL or the last ten titles with their views. When a shell is available, yt-dlp --flat-playlist -J "<channel url>/videos" lists the recent uploads with their titles and view counts.
What to look at, in this order
- The last ten titles, as a set. Read them as a list, the way the channel page shows them. Do they promise different things? Run them through
../yt-package/scripts/title.py. A channel where every title is the same shape has a format problem, not a title problem. - The thumbnails, at feed size. Shrink them. What survives? If three of them are unreadable at that size, that is the fix and nothing else matters yet. With Uplika, download each
thumbnailUrland look at it small if you can view images; otherwise ask the person for screenshots of the channel page. - The first fifteen seconds of the three most recent. Transcribe them and score with
../yt-script/scripts/hookscore.py. This is where most channels lose. When a shell is available,yt-dlp --skip-download --write-auto-subs --sub-langs ko --convert-subs srt "<video link>"gets YouTube's captions (use the video's language code). Korean openings get a rank-only score markedKorean: heuristic, not calibrated. - Upload rhythm. Not frequency: CONSISTENCY. Six videos in one week and then nothing for a month is worse than one a fortnight forever. With Uplika, the
timestampof each video is the rhythm. - The retention shape, if they can export it.
yt-retention.
What to hand back
- The single biggest fix, named, with what to do this week.
- Three things that are already working, so they do not break them. Be specific; "your energy is good" is not an observation.
- What NOT to do yet, and why.
Never open an audit with praise you do not mean, and never end one with a list of twenty things.
The gate
Nothing here publishes. This skill writes and the person publishes. Every output ends in a block they copy, and the last line of every run is the question: ship it, or change it?
Tools
list_accounts: the YouTube account idlist_channel_posts: the last videos with title, description, date, thumbnail and linkget_insights: views, likes and comments per videoget_help: the answer for an error code
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.

