Softsync Records logo

Softsync Records

Organization
Softsync-Lab
softsync-records

Find, create, update, merge, delete and restore records such as companies, contacts, deals and tasks, and chart them. Use when the user names a company, person or deal, wants to add or change one, clean up duplicates, or count and chart their data.

Overview

PublisherSoftsync-Lab
Repositorysoftsync-skills-hub
Skill namesoftsync-records
Stars
91
Forks
0
Bundled files
3
LicenseMIT
Links
  • 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.

  • 3 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 Records AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Softsync-Lab/softsync-skills-hub/tree/main/skills/softsync-records
  4. 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.
2

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-records .claude/skills/softsync-records
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Softsync Records 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 Records 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 Records 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.

Records

Records are the rows of workspace tables: companies, contacts, deals, tasks and any custom objects.

Start here

  1. Call describe_workspace_schema to learn the tables, their fields and the groups you can see.
  2. Name tables and fields by their apiName (snake_case), never by display label.
  3. System fields are __system_created_at, __system_updated_at and __system_created_by. The double underscore is required.
  4. Most features have one tool for reading (such as groups) and one for changing (such as manage_groups). Say what to do with action, and send only the fields that action uses.

Finding records

  • search_records: exact filters on fields (equals, contains, greater than, empty…) with sort and paging. Use it for "deals in negotiation" or "contacts at Acme".
  • semantic_search_records: search by meaning when the user describes something loosely.
  • get_record_by_id: the full record once you have its id.
  • query_records_by_view: the records a saved view shows, with that view's filters and sort.
  • get_related_record_ids: records linked to one record, such as the contacts at a company.
  • get_record_activity: what changed on a record, when and by whom. Use it to answer "what happened?" instead of guessing.
  • get_record_moves: which statuses a record may move to next, and which moves need a comment.

Creating and changing records

  • record_creation: create one or many records, across tables in one call. Records in the same call can link to each other through _ref. Pick a duplicate-detection field per table so existing records are matched instead of duplicated.
  • update_record: change fields on specific records. Send only the fields that change.
  • update_field_on_records: set the same values on many records. For "all of them", get the ids first with find_matching_record_ids.
  • manage_records with action add_to_group or remove_from_group: change which group records appear in.
  • A status move that needs a comment is refused without one; pass comment with the update.

Time on records

manage_timers with action start starts your timer on a record and stop stops it and logs the time. get_timer shows what is running. You have one timer: starting another stops the running one and keeps its time.

Cleaning up

  • check_duplicate_records: find likely duplicates in a table so the user can review them.
  • manage_records with action merge: fold duplicates into one record. The service chooses the survivor, and a merge cannot be undone.
  • manage_records with action delete: move records to the Bin. Action restore brings them back within 30 days.

Numbers and charts

  • record_statistic: one count, sum, average or ratio, optionally split by a field — "how many open deals per stage?".
  • generate_analytics: several chart datasets at once. Both return data, not pictures. To keep a chart on a group's Reports page, use manage_dashboards with action add_chart.
  • For forecasts and trends use generate_analytics: a period with compareTo for "this quarter vs last", forecast on a bar chart over time for "where will we land", asOf for "what did the pipeline look like on 1 March", a bridge for "what moved the pipeline this month", and reached / days_in_value for stage conversion and time in each stage.
  • A weighted pipeline needs a probability per deal: if the deals table has none, offer to add a number field (filled from the stage) and a formula field multiplying value by probability, then sum it.

Rules

  • Never invent ids. Look records, people and groups up first and use the ids that come back.
  • A relation field takes record ids; a person field takes workspace member ids.
  • Say what you are about to change before a bulk update, a merge or a delete, and wait for the user to agree.

More detail

Read these when the task needs them:

  • searching-records: Filters, operators, sorting, related-record filters and counting, with good and bad examples.
  • resolving-records: Turning a company or person into every linked record id before reading their messages or acting on them.
  • writing-records: Creating and updating records without duplicates, linking them, enriching them and formatting each field kind.

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 Records AI skill do?

Find, create, update, merge, delete and restore records such as companies, contacts, deals and tasks, and chart them. Use when the user names a company, person or deal, wants to add or change one, clean up duplicates, or count and chart their data.

Why use Softsync Records on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Softsync-Lab/softsync-skills-hub/tree/main/skills/softsync-records. 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 Records?

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 Records?

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

Is the Softsync Records 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇