softsync-lab/softsync-skills-hub/softsync-records

Claude Code and agent skill by softsync-lab/softsync-skills-hub

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

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.

Install

npx vskill@latest install softsync-lab/softsync-skills-hub/softsync-records

SKILL.md

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.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/softsync-lab/softsync-skills-hub/softsync-records/badge)](https://verified-skill.com/skills/softsync-lab/softsync-skills-hub/softsync-records)

Something wrong with this skill or its page? Tell us.