agentleFS
uplikauplika/uplika-plugin/skills/comments/SKILL.md

comments

Skill3 starsChanged 33 days agoMITView on GitHub

Read replies on your posts, sort them into answer, hide, idea, ignore, draft replies in your voice, and send after approval.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use analytics.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    analytics

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this for "check my comments", "reply to the comments on yesterday's post", or a weekly comment round.

    line 8
  2. Very specific:

    If a call answers workspace_required, the account has more than one workspace: show the names it lists, ask which one, and pass that …

    line 12
  3. Very specific:

    Read the thread with list_replies (nested replies included.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 9 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

Comments

Use this for "check my comments", "reply to the comments on yesterday's post", or a weekly comment round.

Procedure

If a call answers workspace_required, the account has more than one workspace: show the names it lists, ask which one, and pass that workspaceId on every later call in this session.

  1. Find the post: a link or id from the person goes straight to open_post (text, replies and metrics in one call). Without one, list_posts (posts made through Uplika) or list_channel_posts (everything on the channel, including posts written in the app) and let them pick.
  2. Read the thread with list_replies (nested replies included; truncated means it stopped early).
  3. Sort every reply into four groups and show them as a short table:
    • Answer: questions and comments that deserve a reply.
    • Hide: spam, abuse, scams. Hiding keeps it out of sight and can be undone.
    • Idea: a question or objection worth a post of its own. Collect these for the person.
    • Ignore: thanks, emoji, chatter.
  4. Draft replies for the Answer group. Read ~/.uplika/<workspace-slug>/voice.md first if it exists; if not, keep replies short and plain, and offer the voice-profile skill. Never invent facts, prices or promises; when the answer needs something only the person knows, ask.
  5. Show the drafts and the hide list. Send only what the person approves:
    • reply with the post id and replyTo (the reply id) to nest under that comment; wait: true to confirm it is live.
    • hide_reply for the Hide group.
    • delete_reply only when the person explicitly asks to delete; it cannot be undone and reaches different things per channel (read the features table in list_platforms). Prefer hiding.
  6. Report what was sent, hidden and collected as ideas.

Channel notes

  • What each channel allows (hiding, deleting, nested replies) is in the features table of list_platforms. On a Facebook Page the Page's own comment is deleted instead of hidden.
  • Threads reply approval: when the account holds replies for approval, approve_reply with the account id and no reply id lists the queue; approving makes a reply public. Ask before approving.
  • Naver Blog comments go through the person's Chrome extension; if a response carries bridge, follow bridge.nextStep (see the troubleshoot skill).
  • Direct messages are the inbox skill. Automatic replies (comment-to-DM, keyword replies, AI replies) are the automations skill.

Tools

  • open_post: one post with its replies and metrics
  • list_posts: posts made through Uplika
  • list_channel_posts: everything on the channel
  • list_replies: the reply thread under a post
  • reply: send an approved reply
  • hide_reply: hide (or unhide) a reply
  • delete_reply: delete a reply for good, only on explicit request
  • approve_reply: Threads held replies (list the queue, approve or ignore)
  • list_platforms: which comment actions each channel supports

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.