Sf Datacloud Connect

What it does

When your agent uses it

• : user manages Data Cloud connections
• Connector metadata
• Tests a connection
• Browses source objects

Example prompts

• “/sf-datacloud-connect”

Requirements

• Compatibility (from SKILL.md): Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org

Workflow steps

7 steps, taken from the step headings in SKILL.md.

1. 1Classify readiness for connect work
2. 2Discover connector types
3. 3Inspect connections by type
4. 4Inspect a specific connection or uploaded schema
5. 5Test or create only after discovery
6. 6Start from curated example payloads for external connectors
7. 7Discover payload fields for unknown connector types

What it can do on your machine

Read from SKILL.md and the folder at commit 53c9956. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • sf
  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org

  From compatibility in the SKILL.md frontmatter.

Context cost

Sf Datacloud Connect loads about 1.9k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 530 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~119

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Jaganpro/sf-skills at commit 53c9956, republished under its MIT licence (© Jaganpro). 530 words, ~1,922 tokens.

name

sf-datacloud-connect

description

Salesforce Data Cloud Connect phase. TRIGGER when: user manages Data Cloud connections, connectors, connector metadata, tests a connection, browses source objects or databases, or sets up a new source system. DO NOT TRIGGER when: the task is about data streams or DLOs (use sf-datacloud-prepare), DMOs or identity resolution (use sf-datacloud-harmonize), retrieval/search (use sf-datacloud-retrieve), or STDM telemetry (use sf-ai-agentforce-observability).

compatibility

Requires an external community sf data360 CLI plugin and a Data Cloud-enabled org

license

MIT

metadata.version

1.0.0

metadata.author

Gnanasekaran Thoppae

metadata.phase

Connect

node ~/.claude/skills/sf-datacloud/scripts/diagnose-org.mjs -o <org> --phase connect --json

sf data360 connection connector-list -o <org> 2>/dev/null
sf data360 data-stream list -o <org> 2>/dev/null

sf data360 connection list -o <org> --connector-type SalesforceDotCom 2>/dev/null
sf data360 connection list -o <org> --connector-type REDSHIFT 2>/dev/null
sf data360 connection list -o <org> --connector-type SNOWFLAKE 2>/dev/null

sf data360 connection get -o <org> --name <connection> 2>/dev/null
sf data360 connection objects -o <org> --name <connection> 2>/dev/null
sf data360 connection fields -o <org> --name <connection> 2>/dev/null
sf data360 connection schema-get -o <org> --name <connection-id> 2>/dev/null

sf data360 connection test -o <org> --name <connection> --connector-type <type> 2>/dev/null
sf data360 connection create -o <org> -f connection.json 2>/dev/null

sf data360 connection create -o <org> -f examples/connections/ingest-api-connection.json 2>/dev/null
sf data360 connection schema-upsert -o <org> --name <connector-id> -f examples/connections/ingest-api-schema.json 2>/dev/null
sf data360 connection schema-get -o <org> --name <connector-id> 2>/dev/null

sf api request rest "/services/data/v66.0/ssot/connections/<id>" -o <org>

Connect task: <inspect / create / test / update>
Connector type: <SalesforceDotCom / REDSHIFT / SNOWFLAKE / SPUnstructuredDocument / IngestApi / ...>
Target org: <alias>
Commands: <key commands run>
Verification: <passed / partial / blocked>
Next step: <prepare phase or connector follow-up>

© Jaganpro, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files in skills/sf-datacloud-connect of Jaganpro/sf-skills.

• SKILL.md
• CREDITS.md
• LICENSE
• README.md
• examples/connections/heroku-postgres.json
• examples/connections/ingest-api-connection.json
• examples/connections/ingest-api-schema.json
• examples/connections/redshift.json
• examples/connections/sharepoint-unstructured.json
• examples/connections/snowflake-connection.json

Open the folder on GitHubat commit 53c9956