Msp Skills Concierge

Organization

Servosity

msp-skills-concierge

Use when the user has msp-skills installed and wants help choosing or installing connectors - it reads the live catalog, learns their PSA/RMM/backup/security/billing stack, recommends the connectors that fit, and installs only the ones they approve. Trigger phrases: `recommend which connectors I should install`, `which msp-skills connector for my stack`, `set up the right connectors for me`, `concierge`, `msp-skills concierge`, `what connectors should I install`, `pick connectors for my MSP`, `using everything you know about me, recommend connectors`.

Overview

Publisher	Servosity
Repository	`msp-skills`
Skill name	`msp-skills-concierge`
Stars	68
Forks	14
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by Servosity on GitHub. Read the source before you install it.

Installation

Install the Msp Skills Concierge AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Servosity/msp-skills/tree/main/skills/_meta
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Servosity/msp-skills.git /tmp/msp-skills
mkdir -p .claude/skills
cp -r /tmp/msp-skills/skills/_meta .claude/skills/msp-skills-concierge

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Msp Skills Concierge in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Msp Skills Concierge on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Msp Skills Concierge is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

msp-skills Concierge

The concierge recommends which msp-skills connectors fit the user's stack and installs only the ones they approve. It has no binary of its own; it reads the live catalog and drives each connector's own installer.

The magic prompt

This is the moment this skill exists for. When the user says something like:

You have msp-skills installed. Using everything you know about me and how I work, recommend which connectors I should install - and install the ones I approve.

run the workflow below.

Workflow

1. Fetch the LIVE catalog

Always read the catalog from the source of truth on main, never a copy bundled in this skill (a bundled copy rots):

bash
curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/catalog.json

If that fetch fails (offline, network error, non-200), fall back to the local repo copy at catalog.json in the repository root if one is present. If neither the live fetch nor a local copy is available, say so plainly and STOP - do not guess at a connector list from memory.

The catalog's skills[] array gives you, per connector: name, system, status, vendor, category, tagline (when present), description, the install one-liner (install_skill_one_liner), and the per-agent wire-up doc path (install_mcp_doc). A connector may carry markdown_only: true (a meta-skill like this one) - never recommend a markdown-only entry as a connector.

2. Learn the user's stack

If the conversation or context already names the user's tools (their PSA, RMM, backup, security, or billing vendors), use what you already know - do not re-ask. Only if the stack is genuinely unknown, ask AT MOST 2-3 short questions, for example:

Which PSA do you run? (HaloPSA, ConnectWise, Autotask, ...)
Which RMM, and which backup/BCDR tool?
Any security or billing tools you'd want your AI to reach (e.g. M365 security, Pax8)?

Keep it to one short message. Do not interrogate.

3. Match stack to catalog and present a shortlist

Match the named vendors and categories against the catalog. Rank by relevance (exact vendor match first, then same-category, then adjacent). Present a shortlist as a table:

Connector	What it answers	Verification
(name)	(the connector's tagline - the question it answers)	(honest badge, see below)

State the verification badge HONESTLY from the catalog data:

If the connector's live_verified.status is verified, write Live-verified plus the date.
Otherwise write Awaiting live verification - passes every mechanical gate.

Never inflate a badge. "Awaiting live verification" is the truthful state for most connectors and it is not a weakness - it is the signal MSP feedback closes.

When the catalog or the corpus at https://raw.githubusercontent.com/Servosity/msp-skills/main/docs/llms-full.txt carries an instead-of / just-say example for a connector, include ONE per recommendation so the user sees the concrete payoff (for example: instead of exporting three reports and pivoting them in Excel, just say "Which clients had backup-failure tickets last quarter?").

4. Install only what the user approves

Wait for the user to approve specific connectors. Install ONLY those. For each approved connector:

On macOS / Linux, run its own installer:

bash
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/<slug>/install.sh)

On Windows, run the PowerShell installer instead:

powershell
iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/<slug>/install.ps1 | iex

After each install, print the per-agent wire-up pointer so the user can connect the connector to their agent: the connector's mcp-install.md at https://github.com/Servosity/msp-skills/blob/main/skills/<slug>/mcp-install.md.

5. Receipts, not claims

After each install, prove the binary is present by running its version command and REPORTING the output verbatim:

bash
<slug>-cli --version

If the user has already configured the connector's credentials per its README, also run its health check and report the output:

bash
<slug>-cli doctor

Never claim a connector is "working" or "shipped" on the strength of an install alone. The binary being present is a receipt that it installed; closure is the USER actually running it against their tenant. Report what the commands returned and let the user judge.

6. Refuse-by-design

Never install a connector the user did not explicitly approve.
Never write, store, echo, or transmit credentials anywhere - the user enters their own credentials following each connector's README.
If the catalog fetch fails and there is no local copy, say so and stop. Do not improvise a connector list.
Never recommend or install a markdown_only entry as a connector.

Frequently asked questions

What does the Msp Skills Concierge AI skill do?

Why use Msp Skills Concierge on TypingMind?

Because you install it once and use it with any model. Msp Skills Concierge is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Msp Skills Concierge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Servosity/msp-skills/tree/main/skills/_meta. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Msp Skills Concierge?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Msp Skills Concierge?

As many as you like. As long as a model supports skills, you can use Msp Skills Concierge with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Msp Skills Concierge AI skill free?

Yes. It is published on GitHub by Servosity under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Autoreview

openclaw

OrganizationPopular

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Channel Message Flows

openclaw

OrganizationPopular

Use when running QA Lab channel message flow evidence.

Claw Score

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawdtributor

Clawtributor PRs here, last week or another window: discover conversation refs, recheck GitHub, rank by impact.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

msp-skills Concierge

The magic prompt

Workflow

1. Fetch the LIVE catalog

2. Learn the user's stack

3. Match stack to catalog and present a shortlist

4. Install only what the user approves

5. Receipts, not claims

6. Refuse-by-design

Frequently asked questions

Related AI Skills

Set up your own AI workspace now