ClaudeSuperPower
SubmitLog in

aidp-catalog-init

Skill

One-time AIDP catalog discovery that writes a cached, version-controllable .aidp/catalog.md grounding file (tables, columns, FK/join hints, value dictionaries). Use when the user says "/aidp-catalog-init", asks to "map/discover my lakehouse", set up data discovery, or before answering data questions

0Other

Install

git clone https://github.com/oracle-samples/oracle-aidp-samples.git ~/.claude/skills/aidp-catalog-init

What is aidp-catalog-init?

One-time AIDP catalog discovery that writes a cached, version-controllable .aidp/catalog.md grounding file (tables, columns, FK/join hints, value dictionaries). Use when the user says "/aidp-catalog-init", asks to "map/discover my lakehouse", set up data discovery, or before answering data questions when no catalog cache exists. Re-run with --refresh when the schema changes.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~94 tokens of context used while enabled, before you invoke anything

Documentation

README · ~4 min read

aidp-catalog-init — build the catalog grounding file

Walk the AIDP catalog tree and generate .aidp/catalog.md — the cached, user-editable grounding file that makes subsequent NL-to-SQL fast and accurate. Discovery is pure control-plane — no SQL, no compute (except optional --with-counts, which uses the bundled SQL helper). Self-contained: no aidp MCP required.

When to use

  • First-time setup, or --refresh after schema changes.

Engine — official aidp CLI (control-plane, no compute)

Preferred engine is the official Oracle aidp CLI; oci raw-request is the fallback when the CLI isn't installed. Both hit the same data-plane REST API with the same auth — see

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.

Skillssimilar to this one

All skills →

create-atomic-tool

Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a `BaseTool`", "make a calculator/searc

6.1K stars

create-atomic-context-provider

Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent d

6.1K stars

framework

Guide for the Atomic Agents Python framework — schemas, agents, tools, context providers, prompts, orchestration, and provider configuration. Use when code imports from `atomic_agents`, defines an `AtomicAgent`, `BaseTool`, or `BaseIOSchema`, or the user asks about multi-agent orchestration or LLM-p

6.1K stars

Plugins

All plugins →

receipts

A personal Claude Code impact report for justifying your usage to a manager or a self-review: what you shipped, which projects it went to, and each project's share of your usage. Reads your ~/.claude/projects transcripts and runs read-only git locally; only counts and project names are sent to write

32.8K stars

atomic-agents

Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and tool development. Features guided workflows, progressive-disclosure skills, and best practice validation.

6.1K stars

databases-on-aws

Expert database guidance for the AWS database portfolio. Design schemas, execute queries, handle migrations, and choose the right database for your workload.

844 stars