aidp-credentials

Build a high-level Snowflake to AIDP migration plan and present it for approval. States which objects can migrate and which cannot with a brief reason for each, applies user-supplied restrictions such as excluded databases or size caps, derives dependency order so views follow their base tables, and lists the Silver and Gold job stubs. Use after an estate assessment, or when the user asks what can be migrated, in what order, why something is excluded, or wants to see the migration plan.

Router, runbook and shared rules for migrating a Snowflake estate onto Oracle AI Data Platform (AIDP). Read this first whenever the user mentions migrating, moving, assessing, inventorying or cloning Snowflake databases, schemas, tables, views or warehouses onto AIDP, asks to "run the migration" or "start from zero", or asks what a Snowflake migration would involve. Carries the FIXED twelve-step order of operations and the rules that apply at every step; adds no API surface of its own.

Dev mode. Run the entire Snowflake-to-AIDP migration pipeline against a built-in emulated estate and an emulated AIDP — no credentials, no network, nothing real is touched. Use when the user wants to understand what the migrator does before pointing it at a real account, wants a training walkthrough, or asks "show me how this works" / "demo mode" / "dev mode". Produces every real artifact plus DEMO.md, a narrated walkthrough of the lessons.

First-run setup for the Snowflake to AIDP migrator. Finds or creates the one migration config file (snowmig-config.yaml), reads every field back with secrets masked, verifies Snowflake authentication by password, key-pair, programmatic access token or SSO, verifies the AIDP end, then smoke-tests the connection and reports the account, region, role and warehouse. Use the first time the migrator runs on a machine, or when any other stage fails with an authentication, connection or "no config found" error.

Map Snowflake warehouses onto AIDP Spark compute clusters and produce a sizing and cost proposal. Inventories every warehouse with its size, multi-cluster scaling policy and auto-suspend, pulls observed credit consumption from ACCOUNT_USAGE where permitted, and proposes worker counts and autoscale ceilings per warehouse. Use when the user asks about compute sizing, warehouse equivalence, cluster shapes, credits, or what the migration will cost.

Generate the table-creation script for a Standard AIDP catalog as an executable notebook, locally and offline. --upload is a dry run and is refused with --execute; the structure itself is created by the snowmig_01_structure workflow at S10. The script creates schemas, then tables, then views in dependency order, prints per-object progress with elapsed time so a long run stays visible, and verifies each object individually at the end. This script creates structure only and copies no data - every table arrives with zero rows; rows are copied only by the snowmig_02_copy_schema job, when the operator runs it. Use when the user has explicitly asked for a Standard catalog, or wants the migration delivered as a runnable script rather than executed straight from the CLI.

Provision the migration environment inside AIDP for the prod flow - the workspace (name auto-translated to the simplest safe charset), the migration-assets compute cluster, optional cluster libraries from requirements-aidp.txt, the backup-snowflake-migration/ workspace folder holding the data-migration scripts and the plan artifacts, and the migration jobs (discover, structure, reconcile, plus one copy job per schema of the approved plan, each passing its schema as a task parameter). Use when the user wants to set up AIDP for the migration, upload the migration scripts, create the migration workspace or cluster, or wire the migration jobs. Dry-run by default.

Create the medallion architecture on Oracle AI Data Platform - registering an EXTERNAL catalog of source type SNOWFLAKE by default, and generating Spark SQL for schemas, tables and views from an approved Snowflake plan only when the user has explicitly asked for a Standard catalog. This stage copies no data - rows are copied only by the snowmig_02_copy_schema job, when the operator runs it. Use when the user asks to create the medallion structure, soft clone, shallow clone, create the target catalog, or deploy the target schema.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。