Softsync Messages

Organization

Softsync-Lab

softsync-messages

Read emails, notes and saved meeting summaries linked to records, search them by content, answer from the workspace's own help articles, and send a text. Use when the user asks what was said, agreed or sent — "what did Acme reply?", "summarise our last call" — asks a how-to or policy question, or wants to text someone.

Overview

Publisher	Softsync-Lab
Repository	`softsync-skills-hub`
Skill name	`softsync-messages`
Stars	91
Forks	0
Bundled files	2
License	MIT
Links	Skill source Repository

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.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Softsync-Lab on GitHub. Read the source before you install it.

Installation

Install the Softsync Messages 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/Softsync-Lab/softsync-skills-hub/tree/main/skills/softsync-messages
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/Softsync-Lab/softsync-skills-hub.git /tmp/softsync-skills-hub
mkdir -p .claude/skills
cp -r /tmp/softsync-skills-hub/skills/softsync-messages .claude/skills/softsync-messages

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

Use it in TypingMind

Enable Softsync Messages 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 Softsync Messages 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 Softsync Messages 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.

Messages

Messages are everything the workspace has received or written about its records: synced emails, notes and notifications.

Which tool

About a company or person ("last week's emails with Acme"): resolve them to record ids, then query_messages with those ids and a time window. See the finding-messages reference for the exact sequence.
By topic, with no company or person named ("emails about the renewal"): semantic_search_messages. Never use it as a fallback when query_messages finds nothing for a company or person — similar text is not proof it is about them.
Full text of one message: get_message_by_id after finding it.
Calendar events ("my meetings this week", "when did we last meet Acme?"): use calendar_events (action list) from the meetings skill, not query_messages.
Meeting summaries: a summary someone saved to a record is a note on that record. Find it with query_messages on the record. Recordings that were never saved to a record stay in the desktop app and cannot be reached from here.
How many ("how many emails have we exchanged with Acme?"): get_message_statistics counts messages linked to a record or person.
How-to and policy questions ("what is our refund policy?", "how do I reset the router?"): search_knowledge finds the passages in the workspace's own articles and guides. Quote them and name the source; do not answer from memory. When drafting a reply to a customer, set audience to public so only what the help center already shows customers is used.

Sending a text

send_message sends a text (SMS) to a contact (toRecordId) or a phone number (to). It shows on the contact's timeline like an email.
To answer a text conversation in a shared inbox, reply there instead (shared inbox skill), so the answer stays in the same thread.
A text reaches a real phone and cannot be recalled. Show the exact text and recipient and wait for a clear yes. Pass a clientRef of your own so a retry never sends twice.
People who replied STOP are skipped; say so if the result reports it rather than claiming it was sent.

Rules

Resolve a company or person to its record id first (see the records skill), then filter messages by that id.
You only see messages linked to records you can access. Say so if something the user expects is missing, rather than claiming it does not exist.
Never guess a message id.

More detail

Read these when the task needs them:

finding-messages: The required call sequence for "what did we discuss with Acme?" and when topic search is the wrong tool.
resolving-records: Turning a company or person into every linked record id before reading their messages or acting on them.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Softsync Messages AI skill do?

Why use Softsync Messages on TypingMind?

Because you install it once and use it with any model. Softsync Messages 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 Softsync Messages in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Softsync-Lab/softsync-skills-hub/tree/main/skills/softsync-messages. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Softsync Messages?

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 Softsync Messages?

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

Is the Softsync Messages AI skill free?

Yes. It is published on GitHub by Softsync-Lab under the MIT 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

Agent Builder

shareAI-lab

OrganizationPopular

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or…

Changelog Generator

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns…

Agent Authentication

Agent skill for authentication - invoke with $agent-authentication

Agent Tdd London Swarm

ruvnet

CommunityPopular

Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Messages

Which tool

Sending a text

Rules

More detail

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now