agentleFS
utillayerutillayer/youtube-agent-skill/skills/yt-comment/SKILL.md

yt-comment

Skill10 starsChanged 28 days agoMITView on GitHub

Sort a video's comments by which deserve an answer, then draft short replies in the creator's voice. Use for "reply to my comments", "handle my comment section", "someone asked X", or a pasted comment thread.

5 other projects use a version of this, 4 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 1 is common, 5 are distinctive, and 1 is very specific to this project.

  • 1

    Common

    Most of the 5 edited versions we read keep these.

  • 5

    Distinctive

    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
  1. Distinctive:

    Treat it as part of the video, not as admin.

    line 12
  2. Very specific:

    Read ~/.claude/youtube/voice.md if it exists.

    line 16
  3. Distinctive:

    Never make up a fact, a number or a promise.

    line 18
  4. Distinctive:

    Put every comment in one of four groups and give the counts before writing a word:

    line 22
  5. Common:

    Corrections: If they are right, say so plainly and thank them.

    line 25
  6. Distinctive:

    Bait: Do not reply. Say so and move on.

    line 29
  7. Distinctive:

    Never promise a video that has not been agreed.

    line 37

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

yt-comment

The first hours of comments decide whether a thread turns into a conversation other viewers read. Treat it as part of the video, not as admin.

Before you start

  1. Read ~/.claude/youtube/voice.md if it exists. If not, ask for three of the creator's videos and write it. Replies are in their voice, not yours.
  2. Never make up a fact, a number or a promise.

Sort first

Put every comment in one of four groups and give the counts before writing a word:

  1. Questions. Answer them. Repeated ones are the next video ideas - list them.
  2. Corrections. If they are right, say so plainly and thank them. Never argue a fact you cannot check.
  3. Praise. Reply to a few, briefly, with something specific from what they wrote. A wall of identical "thanks!" reads as automated because it is.
  4. Bait. Do not reply. Say so and move on. No comebacks, however tempting.

Each reply

  • Under 30 words. A long reply in a thread is an essay nobody asked for.
  • Answer in the first sentence.
  • A question back only if it is a real one.
  • Emoji only if the creator uses them in their own replies.
  • Never promise a video that has not been agreed.

Pin and heart

Name the one comment to pin and why: the question most viewers also have, not the nicest comment. Heart freely; it costs nothing and people see it.

Before you hand it over

This skill drafts; you publish. End with the copy-ready block and one question: post it as is, or another pass?

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.