aidp-engineer-overview

Parse and summarize the JOB_REPORT.md produced by a prior migration run. Surfaces cell pass/fail/fix counts per task, lists the failing cells, and recommends a next-step skill (fixup-cell, resume, or all-clear). Use after any aidp-migrate-job run, or when the user asks "how did the migration go", "what failed", "did it pass".

Review a migrated .ipynb for correctness — NOT just "did it run". Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms, builtins shadowing, format downgrades. Outputs a structured Blockers / Important / Style / Good review report. Use after aidp-migrate-job completes, especially on the first few notebooks of a new workload before scaling out.

Guided full-job migration flow. Walks the user from "I want to migrate this Databricks job" through DAG → data check → migrate → status, asking before each phase. Composes aidp-build-dag, aidp-check-data, aidp-migrate-job, and migration-status. Use when the user wants the end-to-end guided experience instead of running individual phases manually.

Guided catalog migration flow. Extracts Databricks Unity Catalog / HMS metadata, previews the 18-rule DDL rewrite, then batched replay on AIDP. Asks before the destructive replay step. Use when the user wants to migrate the catalog layer (schemas + tables) with checkpoints, rather than running aidp-migrate-catalog directly.

Read a single Databricks notebook (.ipynb / .py / .scala source format) and produce a migration-readiness report — what it does, what it depends on, what risks the migrator will hit, which gotchas (from references/gotchas.md) will apply. Run before manually authoring an entry in a migration manifest, OR as a one-off "should we migrate this?" assessment. Read-only — does not modify the notebook and does not invoke the migrator.

Pre-migration data-availability scan. Reads a migration manifest, probes every spark.read.* / saveAsTable target on the AIDP cluster, reports OK / MISSING / EMPTY with remediation tips per category. Use before any aidp-migrate-job run, or whenever the user asks "is the data ready?", "pre-migration check", "what's missing on AIDP".

Consume an OCI Streaming stream from an AIDP notebook via Spark structured streaming (Kafka-compat). Use when the user mentions OCI Streaming, Kafka on OCI, stream pool, structured streaming, or wants to read Kafka messages into Spark. Auth is SASL/PLAIN with an OCI auth token. Pattern matches the official Oracle AIDP sample.

Read from Oracle Siebel CRM into a Spark DataFrame in an AIDP notebook via the AIDP `aidataplatform` Spark format handler. Use when the user mentions Siebel, Siebel CRM, S_CONTACT, S_ORG_EXT, or has a Siebel host/port. Auth is host/port + database name + user/password. Read-only.

About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.

Analyze Google Analytics 4 (GA4) data through Windsor.ai. Use when the user asks about their GA4 website or app analytics — sessions, users, new users, engagement, conversions/key events, bounce/engagement rate, pageviews, or breakdowns by channel, source/medium, campaign, landing page, device, country, or date. Do not use for advertising cost/ROAS (those live in the ad-platform connectors like Google Ads), other analytics products, or changing GA4 settings.

Analyze Google Merchant Center product feed and Shopping data through Windsor.ai. Use when the user asks about their Merchant Center product feed — product status, disapprovals and issues, availability, clicks, impressions, CTR, or price benchmarks by product, brand, or category. This connector is read-only — it has no write actions and cannot edit the product feed. Do not use for Google Ads Shopping campaign spend or ROAS (those live in the Google Ads connector), other platforms (e.g. Amazon), or fixing/updating feed data.

Prepare calibrated multi-camera data and train, evaluate, run inference, export, or quantize TAO Sparse4D 3D detection and tracking models. Includes 2D-to-3D geometric distillation with released LTT weights. Use for Sparse4D adaptation and temporal multi-camera perception workflows.

Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or DEFT loops. Trigger phrases include "single train run", "train then evaluate then export", "plain TAO training", "normal training", "no AutoML", "skip the loop". Routes through the per-model SKILL.md for action specifics and through `tao-launch-workflow` for platform/credentials/dataset intake.

Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval. Use for active-learning-style DINOv3 mining, not plain pretraining/fine-tuning (tao-train-dinov3) or AOI/PAS DEFT.

Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows. Use when an object detection workflow needs to mine a bijectively-assigned set of unique source images closest to target samples. Use global allocation when mining without class constraints. Use class_stratified when rare classes are specified.

Step 9 (done) of the Hostinger Headless flow. Verifies the live site, then hands over the URLs (hPanel success page, main site, WordPress/store admin, dashboard), opens the success page in the browser on a successful run, and gives a summary of what was built plus explicit next steps — how to log in to wp-admin and reset the password, how to manage content, and how to finish WooCommerce/store setup so it can take orders. Its final report format is also used whenever a run stops early.