Fivetran

What it does

When your agent uses it

• Implementing connector discovery
• Schema config parsing
• Any Fivetran API integration in the rocky-fivetran crate

Example prompts

• “/fivetran”

Requirements

• A credential in FIVETRAN_API_KEY
• A credential in FIVETRAN_API_SECRET

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Connector discovery — List all connectors in the destination group, filter by the configured schema_pattern prefix (e.g. src__*)
2. 2Schema config — Fetch per-connector, parse nested structure to get enabled tables
3. 3Sync detection — Compare succeeded_at against cursor timestamp
4. 4Caching — Cache connector list and schema configs in memory (5-min TTL) and Valkey (shared distributed cache)
5. 5Error handling — Fivetran API can return HTML on 5xx errors; handle non-JSON responses gracefully

What it can do on your machine

Read from SKILL.md and the folder at commit 0cb7c7b. 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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.fivetran.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • FIVETRAN_API_KEY
  • FIVETRAN_API_SECRET

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

Context cost

Fivetran loads about 914 tokens when it runs, and up to ~133k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 278 words of instructions outside code blocks.

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

~55

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

~914

With references · SKILL.md plus every file in references/, read only if the agent opens them

~133k

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 rocky-data/rocky at commit 0cb7c7b, republished under its Apache-2.0 licence (© rocky-data). 278 words, ~914 tokens.

name

fivetran

description

Fivetran REST API reference for Rocky's source adapter. Use when implementing connector discovery, schema config parsing, sync detection, pagination, or any Fivetran API integration in the rocky-fivetran crate.

Authorization: Basic base64({api_key}:{api_secret})

{
  "schemas": {
    "schema_name": {
      "enabled": true,
      "tables": {
        "table_name": {
          "enabled": true,
          "sync_mode": "SOFT_DELETE",
          "columns": {
            "column_name": {
              "enabled": true,
              "hashed": false
            }
          }
        }
      }
    }
  }
}

GET /v1/groups/{groupId}/connectors?cursor={next_cursor}&limit=100

{
  "code": "Success",
  "data": {
    "items": [...],
    "next_cursor": "eyJza..."
  }
}

{
  "code": "Success",
  "data": { ... }
}

© rocky-data, Apache-2.0. 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 1 other file (references) in engine/.claude/skills/fivetran of rocky-data/rocky.

• SKILL.md
• references/rest_api_collection.json

Open the folder on GitHubat commit 0cb7c7b