agentleFS
Othmane-KhadriOthmane-Khadri/YALC-the-GTM-operating-system/.claude/skills/answer-linkedin-comments/SKILL.md

answer-linkedin-comments

Skill298 starsChanged 6 months agoMITView on GitHub

Reply to comments on a LinkedIn post via Unipile — drafts thread-aware replies grounded in the user's voice and the conversation context, then sends on approval. Use when the user says 'answer comments on my post', 'reply to LinkedIn comments', 'respond to engagement on this post', 'draft replies to commenters', or 'answer the LinkedIn thread'. Side-effecting — calls Unipile to read + post replies.

  • Reads credentials

The file

Files
SKILL.md

Answer LinkedIn Comments

I'll wrap linkedin:answer-comments. Take a post URL, fetch comments via Unipile, draft replies in the user's voice, ask for approval, and send on yes.

When This Skill Applies

  • "answer comments on my post"
  • "reply to LinkedIn comments"
  • "respond to engagement on this post"
  • "draft replies to commenters"
  • "answer the LinkedIn thread"

NOT this skill (use scrape-post-engagers instead):

  • "scrape the engagers off this post" — that produces a result set; this skill produces replies.

NOT this skill (use personalize-message instead):

  • "draft a DM to this commenter" — DM is one-to-one; this skill is for the public thread.

Workflow

Step 0 — Ask for the LinkedIn post URL

"What's the LinkedIn post URL with comments to answer?"

Step 1 — Validate URL

Step 2 — Shell out to draft

cd ~/Desktop/gtm-os && set -a && source .env.local && set +a && \
  npx tsx src/cli/index.ts linkedin:answer-comments --url <url> --draft-only

(Verify exact flag via --help. The skill always drafts first, then asks before sending.)

Step 3 — Render the drafts

Show each comment + its drafted reply.

Step 4 — Ask for approval per comment OR bulk

"Send all? (yes / approve some / cancel)"

Step 5 — Shell out to send (if approved)

npx tsx src/cli/index.ts linkedin:answer-comments --url <url> --approved <ids>

Step 6 — Render send result

Notes

  • Replies use the brand voice from ~/.gtm-os/brand-voice.yaml if present; otherwise defaults to a neutral conversational tone.
  • The CLI never auto-sends without --approved. Drafts always render to chat first.
  • Skips comments from the post author themselves (no self-replies).

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.