agentleFS
Sign inStart free
Ootto-AIOotto-AI/claude-content-skills/skills/comment-responder/SKILL.md

comment-responder

Skill417 starsChanged 3 months agoMITView on GitHub

Turn every comment into a lead on autopilot. Claude watches your new comments, posts a friendly public reply (never a link), and DMs the commenter your lead magnet / resource — then logs them as a lead. Use when the user says "auto reply to comments", "DM everyone who comments", "comment to DM", "lead magnet automation", "turn comments into leads", "auto-respond", or "capture leads from a reel".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Only promise what you deliver: if the CTA says "comment WORD → I'll DM it," the DM must actually send.

    line 45
  2. Distinctive:

    No match → defer to a human, don't auto-reply with a guess.

    line 46

≈ “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.

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

Comment Responder — every comment becomes a lead

Post a reel with a "comment WORD and I'll send it" CTA, and this runs the back half for you: it detects each new comment, replies publicly (warm, link-free), and slides the resource into the commenter's DMs — so you wake up to a list of leads instead of a pile of "sent you a DM 🙌" you have to do by hand.

When to use

Any reel/post with a keyword CTA ("comment SKILLS / BREAKDOWN / SETUP …"). Set the rule once; it handles every commenter the same way, 24/7.

What you'll need

The keyword(s) people will comment, the public reply (no link), and the DM (the link/resource lives here). Optional: the specific post to scope it to.

Instructions

Define one rule per CTA — it slots straight into the Ootto comment monitor's auto_responses.json:

You are my comment-to-lead responder. For the post with this CTA, create a rule:
- match_text: ["KEYWORD", common typos]   (optionally match_media_id: ["<post id>"] to scope it)
- reply:  a warm, LINK-FREE public reply  (e.g. "🙌 just sent it to your DMs — check 📩")
- dm:     the deliverable WITH the link/resource  (this is where the link goes — never the public reply)
Then: for each NEW comment that matches, post the reply + send the dm, and log the commenter as a lead.
Rules: ONE link, in the DM only. If a comment doesn't match any rule, defer it to me (don't guess).

The honesty + safety rules (built in):

  • The public reply NEVER contains a link — the link goes in the DM only (platforms suppress link-y comments).
  • Only promise what you deliver: if the CTA says "comment WORD → I'll DM it," the DM must actually send.
  • No match → defer to a human, don't auto-reply with a guess.

Runs unattended: point it at a scheduled runner (e.g. a cron / GitHub Action) so it replies + DMs even while you sleep, and every lead is captured in one place.

Pairs with: reel-builder ends the reel on a keyword CTA → this turns the comments that CTA earns into DMs + leads.

Built by Ootto — the AI autopilot that connects your tools once and runs the busywork for you, automatically. Book a demo →

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.

Check your setup, free