agentleFS
itqanlabitqanlab/agent-toolkit/.agents/skills/zernio-ops/SKILL.md

zernio-ops

Skill1 starsChanged 3 days agoMITView on GitHub

Run several Zernio workspaces from one MCP server, so the agent can post, schedule and read analytics across every social account at once. Triggers: 'connect my Zernio', 'add a Zernio workspace', 'which Zernio accounts are connected', 'is my Zernio key working', 'post this through Zernio', 'set up the zernio hub', 'zernio'. Zernio ties each API key to one workspace, and an MCP entry sends one key, so a normal setup sees one workspace at a time. This plugin ships one MCP server that holds every key and sends each call to the workspace that owns the account. Keys stay in one local file and never pass through the conversation. Works on macOS, Windows and Linux.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the person to sign in to Zernio and make an API key in that workspace's settings.

    line 48
  2. Very specific:

    Run node scripts/setup.mjs status again.

    line 53
  3. Distinctive:

    Ask them to restart the agent.

    line 54
  4. Distinctive:

    Never: ask for a key in the chat, print the keys file, or put a key in an MCP config or a repository.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Zernio

Two scripts. scripts/zernio-hub.mjs is the MCP server. scripts/setup.mjs sets up the keys and checks them. Both read the keys through lib/store.mjs, the toolkit's shared credential store.

Why this exists

Zernio is a social media API. Each Zernio API key belongs to one workspace, and each workspace has its own connected accounts. Many people end up with several workspaces, for example one per brand, or one per pair of accounts on a free plan.

An MCP entry sends one fixed key, so it can only ever see one workspace. The usual workaround is one MCP entry per workspace, which means one copy of every tool per workspace and keys sitting in the MCP config.

The hub is one MCP server in front of all of them. It exposes Zernio's own tools once, adds an optional workspace argument to each, and sends every call to the right workspace. Nothing in it fixes how many workspaces there are: one key line is one workspace, whether that is one or thirty.

Who you are doing this for

Assume the person has never opened a terminal. You run the commands; they never do. They do two things by hand, because only they can: connect their social accounts in the Zernio dashboard, and paste each API key into a file so it never passes through the conversation.

Before anything else: check the dependencies

sh scripts/setup-deps.sh --check

Non-zero exit means Node is missing or too old. sh scripts/setup-deps.sh (Windows: .\scripts\setup-deps.ps1) prints the right install command for that machine and asks before running it.

Set up the keys

node scripts/setup.mjs status

That prints the keys file and, for each workspace, whether its key works and which accounts it can see. It never prints a key.

To add a workspace:

  1. Ask the person to sign in to Zernio and make an API key in that workspace's settings.
  2. Pick a short name for the workspace: a letter (a, b) or a word (brand, client_2). Ask the person if they have a naming habit already. Run node scripts/setup.mjs add <name>. That writes an empty ZERNIO_KEY_<NAME>= line.
  3. Give them the file path on its own line, and ask them to paste the key right after the = sign.
  4. Run node scripts/setup.mjs status again. A rejected key gets a plain message about what to do.
  5. Ask them to restart the agent. The MCP server reads the keys only when it starts.

The keys file is <store root>/credentials/zernio.env. The store root is AGENT_TOOLKIT_HOME when that is set, otherwise .itqan-agent-toolkit in the home folder. It is the same store every toolkit skill uses, mode 600 on macOS and Linux. A good status run records the workspace names (never the keys) under zernio in state/setup.json.

Never ask for a key in the chat, print the keys file, or put a key in an MCP config or a repository.

Using the tools

The tools are Zernio's own: accounts_list, posts_create, analytics_get_analytics, call_tool, and the rest. Each one takes an extra optional workspace, the name in lowercase.

  • accounts_list with no workspace lists every workspace and its accounts. Call it first. The account ids it returns are what the other tools need.
  • Any call with an account_id goes to the workspace that owns that account. You do not need to pass workspace. This also works inside call_tool, where the real arguments sit one level down.
  • A call with neither (for example profiles_list) needs workspace. Without it the hub stops and says so, instead of guessing.

Things that are easy to get wrong

  • A new key needs a restart. Adding a line to the keys file does nothing to a server that is already running.
  • A Zernio "success" is not proof the post went out as intended. Check the post on the platform itself.
  • Do not retry a failed publish blindly. Some platforms publish even when the call returns an error. List the posts first and look.
  • On Zernio's free plan, an extra workspace is a separate signup. Inviting a member into an existing team shares its account limit, so it does not add free slots.

What this cannot do

It does not connect social accounts. That is a login in the Zernio dashboard, and only the person can do it.

It adds nothing to Zernio's own tools. It forwards them. What a tool can do, and the exact arguments it takes, comes from Zernio and changes when Zernio changes it. Read the tool's own schema, not a copy of it.

Updates

This skill is versioned. Its version is metadata.version in the header of this file. CHANGELOG.md in this folder lists what changed in each version, newest first.

To check for a newer version, open the address on the Latest: line of CHANGELOG.md and compare its top version with the installed one. If the newer one is ahead, read every entry between the two and tell the user what changed before anything is updated. A Breaking section means the user has to do something. To update, reinstall the skill from its source repository, the same way it was installed.

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.