From oracle-ai-data-platform-workbench-spark-connectors
First-time setup. Use when the user wants to install/upload the AIDP Spark connectors helper package into their AIDP workspace, or has just installed this plugin and asks "how do I set it up", "first-time setup", "install the helpers", "bootstrap aidp connectors". Drives the AIDP MCP tools to push the helper package to /Workspace/Shared/ and runs a sanity import.
How this skill is triggered — by the user, by Claude, or both
Slash command
/oracle-ai-data-platform-workbench-spark-connectors:aidp-connectors-bootstrapThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
- The user just installed the plugin and asks "how do I set this up?", "what's the first step?", "install the helpers".
aidp-connectors-bootstrap — first-time setup of the helper package in AIDPModuleNotFoundError: No module named 'oracle_ai_data_platform_connectors'./Workspace/Shared/oracle_ai_data_platform_connectors/scripts/oracle_ai_data_platform_connectors/ exists in the user's AIDP workspace, populated from the plugin's local scripts/ directory.examples/00_bootstrap_helpers.ipynb once and it printed BOOTSTRAP OK.scripts/ directory on diskThe plugin lives wherever the user installed it. Common locations:
~/.claude/plugins/<marketplace>/oracle-ai-data-platform-workbench-spark-connectors/scripts/oracle_ai_data_platform_connectors/claude --plugin-dir <path>.Run find ~/.claude/plugins -type d -name oracle_ai_data_platform_connectors 2>/dev/null (or the platform equivalent) to discover it. Confirm with the user before uploading.
Use the AIDP MCP tools:
mcp__aidp__create_directory(
workspace_id="<user's workspace id>",
path="/Workspace/Shared/oracle_ai_data_platform_connectors"
)
mcp__aidp__create_directory(
workspace_id=...,
path="/Workspace/Shared/oracle_ai_data_platform_connectors/scripts"
)
(If the workspace_id isn't already known from the conversation, ask the user.)
For each .py file under the local scripts/oracle_ai_data_platform_connectors/, upload to the matching path under /Workspace/Shared/oracle_ai_data_platform_connectors/scripts/. Use mcp__aidp__upload_file (or the equivalent in this MCP server).
The package layout to preserve:
oracle_ai_data_platform_connectors/
├── __init__.py
├── auth/{__init__,wallet,dbtoken,oci_config,user_principal,secrets}.py
├── jdbc/{__init__,oracle,hive}.py
├── rest/{__init__,fusion,epm,essbase}.py
└── streaming/{__init__,kafka}.py
Upload examples/00_bootstrap_helpers.ipynb to Shared/connectors-tests/00_bootstrap_helpers.ipynb via mcp__aidp__nb_save_file. Then mcp__aidp__nb_create_session against the user's chosen cluster (typically tpcds), and mcp__aidp__nb_execute_code for each cell. The final cell prints BOOTSTRAP OK if everything works.
Tell the user:
aidp-atp) and supply that connector's env vars / Vault secrets.Once the package is published to PyPI, this skill should pivot to telling the user to run %pip install oracle-ai-data-platform-connectors in any AIDP cell instead of uploading. Until v1.0 ships, the Workspace-upload path above is the only way.
/Workspace/Shared/ without confirming the path with the user (in case they have an existing convention)./Workspace/Shared/. The helper package is code-only.examples/00_bootstrap_helpers.ipynbREADME.mdProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Searches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
npx claudepluginhub ahmedawan-oracle/claude-code-plugins --plugin oracle-ai-data-platform-workbench-spark-connectors