agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/.claude/skills/log-discord-forum-posts/SKILL.md

log-discord-forum-posts

Skill63 starsChanged 2 days agoMITView on GitHub

Going through a Discord forum for posts worth answering. A log play (docs/useCases/discord/forumPosts.md): Find a forum in a server, list its posts, read the ones that look right, and tell the owner which are worth answering and why: someone asking for help with something the owner has built or knows, a question nobody answered yet, a problem log solves. This page reads and sends nothing; answering one is [serverReply](serverReply.md).

The file

Files
SKILL.md

Going through a Discord forum for posts worth answering

This is the log play discord/forumPosts. Before anything else, call the log MCP tool getGuide({ useCase: "discord/forumPosts" }): it returns this page and makes it the session's play, so every log tool's answer says which step you are on and a send with no play loaded is refused (rules 157, 158). Then follow the steps in order.

Draft every message from that person's own thread and matt's real replies (voice with no text, search), never from memory, and never send two that read alike (sameAsSent).

Find a forum in a server, list its posts, read the ones that look right, and tell the owner which are worth answering and why: someone asking for help with something the owner has built or knows, a question nobody answered yet, a problem log solves. This page reads and sends nothing; answering one is serverReply.

How the owner asks for it: "look at the <server> forum and find the one about <problem>", "go through the forum in <server> and tell me which posts to respond to", "list the posts in <server> #<forum>", "find posts in <server> asking for help with <thing>"

Run it from a fresh context

Say: "go on docs/useCases/discord/forumPosts.md for <server>, looking for <what>". The agent reads this page and runs the steps.

The steps

#StepToolDone when
1Find the server's forumsdiscordChannels { account, server: "<server>" }the forum and media channels, with their tags; when the owner named the forum, that one
2List the forum's posts, newest activity firstdiscordPosts { account, channel: "<server> #<forum>", limit: 50 }each post's title, author, tags, replies, open or closed, and opening message
3When the owner is looking for one subject, search the server for it toodiscordSearch { account, server: "<server>", query: "<words>", channel: "<server> #<forum>" }the posts whose replies mention it, not only their titles
4Read each post that looks right, text onlydiscordRead { account, channel: "<server> #<forum> > <post title>", limit: 50, noMedia: true }what was asked, what was answered, and whether the owner already wrote there
5Tell the owner which posts are worth answeringthe reply to the ownereach one named as "<server> #<forum> > <title>", who asked, when, what they need, whether anyone answered, and why it fits

What to know

  • Judge from the list first. The opening message, tags and reply count come with every post in step 2, so open only the ones that could fit. A closed or locked post can't be answered.
  • Worth answering means someone asked something the owner can really help with, nobody has solved it, and it's recent enough that they're still there. A post where the owner already wrote is the owner's; say so instead of suggesting it.
  • Search reaches the replies. A post's title can hide what it's about; step 3 finds posts where the subject comes up anywhere in them.
  • Name every post. "<server> #<forum> > <post title>", never its id. discordPosts keeps each post's name, so discordRead finds it straight after.
  • Nothing is sent from this page. To answer one, follow serverReply with the post as the channel.
  • What each part of a server is: the discordServers skill in the discord guide.

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.