agentleFS
gokulsvisiongokulsvision/Crewm8-Social-Media-Manager-Skill-Graph/skills/engagement/comment-reply/SKILL.md

comment-reply

Skill17 starsChanged 7 months agoMITView on GitHub

Draft replies to comments on the brand's own posts and value-add comments on other accounts' posts — non-promotional, brand-voice consistent, and engagement-driving.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Review all new comments: Every 2-4 hours during active posting windows.

    line 55
  2. Distinctive:

    Add a follow-up question, additional context, or validation

    line 66
  3. Distinctive:

    NEVER promotional in someone else's replies

    line 74
  4. Distinctive:

    Add insight, ask a thoughtful question, share a relevant experience

    line 75
  5. Distinctive:

    If the brand had no product, would this still be a good comment?

    line 82
  6. Distinctive:

    All new comments on brand posts have replies

    line 117
  7. Distinctive:

    No troll/spam comments have been engaged

    line 120
  8. Distinctive:

    Read drafted replies. If you replaced the brand name with a random person, would these still be good comments?

    line 131

≈ “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 Reply

Draft replies that make people feel heard on your own posts and make the brand visible in other people's feeds. The comment section is where community is built — one thoughtful reply is worth more than a generic "thanks!"

Purpose

Commenting on other accounts is the highest-leverage growth tactic for small teams. It's free, it's visible, and it builds relationships. On your own posts, every reply is a signal to the algorithm that people are talking about your content.

When to Use

  • Daily engagement routine
  • High-value accounts posted something worth engaging with
  • Trending post in the space where brand comment adds visibility
  • Founder building in public and peers are engaging
  • Someone shared or reposted the brand's content

Inputs Required

  • Comments on brand's own posts (since last check)
  • Target accounts for outbound engagement (10-15 per session)
  • Brand voice guide
  • Platform

Quick Reference

Reply TypeGoalToneMax Length
Reply to own post commentAcknowledge, add value, continue conversationWarm, conversational1-3 sentences
Value-add on others' postsShow expertise, be visible, be helpfulInsightful, non-promotional2-4 sentences
Thank-you for share/shoutoutExpress genuine gratitudeWarm, specific1-2 sentences
Disagreement / debateDisagree respectfully, add perspectiveProfessional, curious2-4 sentences

Procedure

Part A: Replying to comments on brand posts

  1. Review all new comments. Every 2-4 hours during active posting windows.
  2. Categorize:
    • Positive/affirming: reply with warmth + follow-up thought
    • Question: answer directly and thoroughly
    • Disagreement: acknowledge their point, add perspective, no defensiveness
    • Spam/troll: do not engage (escalate to crisis-respond)
    • Low-effort ("nice! "great post"): short reply + question to extend conversation
  3. Draft replies:
    • Acknowledge their specific point (not generic "thanks!")
    • Add a follow-up question, additional context, or validation
    • Match energy of their comment

Part B: Engaging on other accounts' posts

  1. Identify 10-15 target accounts for the session: high-value accounts in niche, other founders building in public, potential customers, trending posts.
  2. Draft value-add comments:
    • NEVER promotional in someone else's replies
    • Add insight, ask a thoughtful question, share a relevant experience
    • Be specific: reference something they actually said
    • 2-4 sentences. Long enough to add value, short enough to be read.
  3. Quality check:
    • Would this comment make someone curious about who wrote it?
    • Does it add to the conversation or just take up space?
    • If the brand had no product, would this still be a good comment?

Output Format

# Comment Replies: [Date]

## Replies on Brand Posts

### Post: [Title truncated]
**Commenter:** @handle
**Comment:** "[Their text]"
**Reply:** "[Drafted reply]"
**Type:** [Acknowledgment / Question answer / Debate]

---

## Comments on Other Accounts

### Account: @handle
**Their post:** [Topic]
**Our comment:** "[Drafted comment]"
**Strategy:** [Building authority / Engaging peer / Supporting community]

---

## Daily Summary
- Brand comments replied: [N]
- Other accounts engaged: [N] of [N] target
- Unreplied (flagged): [N]

Done Criteria

The skill is complete when:

  1. All new comments on brand posts have replies
  2. 10-15 target accounts have been identified for engagement
  3. Value-add comments are drafted (non-promotional)
  4. No troll/spam comments have been engaged

Pitfalls

  • Generic replies: "Thanks!" "Great point!" — looks automated
  • Self-promotional comments on other accounts (quickest way to get blocked)
  • Arguing with trolls
  • Over-commenting on one account (looks like a fan account)

Verification

Read drafted replies. If you replaced the brand name with a random person, would these still be good comments? Comments should be valuable as COMMENTS, not as brand positioning.

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.