agentleFS
Sign inStart free
uplikauplika/uplika-plugin/skills/setup/SKILL.md

setup

Skill3 starsChanged 33 days agoMITView on GitHub

Check that Uplika is connected: list accounts, send the person to connect channels, check the Naver extension. Use first in a new session.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this at the start of a session, when the person asks whether Uplika is connected, or when any other skill finds no accounts.

    line 8
  2. Very specific:

    If the answer is workspace_required, the account has more than one workspace.

    line 13
  3. Very specific:

    If the list is empty, no channel is connected in that workspace.

    line 14
  4. Very specific:

    When the person asks what a channel can do, call list_platforms and read its features table and rules.

    line 17
  5. Very specific:

    Call get_help with the error code and pass its answer and link on.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 171 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

Setup

Use this at the start of a session, when the person asks whether Uplika is connected, or when any other skill finds no accounts.

Procedure

  1. Call list_accounts. Sign-in differs by agent. In Claude Code the plugin's tools stay hidden until the server is authorized: Claude Code marks the server as needing authentication and offers an authenticate tool for it. Call that tool (or ask the person to run /mcp and pick Authenticate), give the person the URL it returns, and when they approve in the browser the real tools appear in the same session without a restart. If the browser could not reach the localhost callback, ask for the full callback URL and pass it to complete_authentication. In Codex and Hermes the first tool call opens the approval screen; in OpenClaw it opens at openclaw mcp login uplika. Tell the person to sign in (or sign up), pick the workspace and the channels, and press Allow. Then call list_accounts again.
  2. If the answer is 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.
  3. If the list is empty, no channel is connected in that workspace. Send the person to https://uplika.com/dashboard/connections, wait until they say it is done, then call list_accounts again.
  4. Show what is connected: channel, handle, status. Only active accounts publish. For any other status (expired, revoked) say which account and send them to the same connections page to reconnect.
  5. If a Naver Blog or Naver Clip account is connected, call bridge_status. Those posts are written by the Uplika extension in the person's own Chrome. If it is offline, say that posts will wait in the queue until that Chrome is open, and show the wake command from the response for their system only if they want to run it.
  6. When the person asks what a channel can do, call list_platforms and read its features table and rules. Do not answer from memory.

Installed twice

A server the person added earlier by hand needs nothing done. Claude Code hides the plugin's copy of a server it already has (claude mcp list then shows only the old uplika), and Codex merges entries with the same name. Leave it: removing it only means approving once more.

The tools do show up twice when Uplika arrives two other ways, for example the claude.ai connector (claude.ai uplika) next to this plugin, or a hand-added server under another name. Then ask the person to turn one off in /mcp, or to remove the extra entry by its name:

  • Claude Code: claude mcp remove <name>
  • Codex: codex mcp remove <name>

When something fails

Call get_help with the error code and pass its answer and link on. reconsent_required, feature_in_review and account_disconnected go to the troubleshoot skill.

Tools

  • list_accounts: what is connected, and the call to make first (in Claude Code only after the server is authorized)
  • bridge_status: whether the Naver extension (Naver Blog and Naver Clip) is online
  • list_platforms: channel rules, status and the features table
  • get_help: the answer for an error code

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