AE Data Integration

Cross-skill collaboration

When remaining work is outside this skill's scope, or a necessary prerequisite needs another capability, follow the collaboration protocol. Choose from the skills available in this run by capability, preserve verified context, and continue the remaining task. Reuse this protocol if already loaded.

Turn local/offline files and Feishu sheet / Bitable (多维表格) URLs into AE data through one fixed pipeline of four submodules: Source → Tracking plan → Transform → Sink. A file or sheet is never uploaded merely because it is present: its business meaning is understood, confirmed once by a human, and only then ingested. The tracking plan is generated and confirmed before ingestion (data governance shift-left) — see references/tracking-plan.md.

Two entrances lead here: the AE Agent dialog (attach / plus-button upload) and ae-cli. Two sink paths exist: RESTful API for one-time/small loads (current phase), and LogBus / DataX for recurring/high-volume loads (next phase). Source and Sink are pluggable — adding one does not change the main pipeline.

Mandatory safety rules

• Treat file paths, receiver endpoints, APPIDs, mappings, generated artifacts, and raw rows as sensitive.
• Do not print source values while inspecting. Summarize types, ratios, counts, warnings, and fingerprints only.
• Inspect samples are bounded but still sensitive. Summarize them; never paste raw sample values into a chat summary.
• Do not invent account IDs, distinct IDs, event times, event names, projects, APPIDs, receivers, or timezones.
• value_mapping and random_pool are explicit user decisions. Never invent them.
• Never auto-fill a missing time for track/track_* rows. A missing time on user-profile rows may be filled with the current time only by setting missing_time: 'now' and only after the user explicitly confirms it.
• The mapping's fill-in options (missing_time: 'now', account_id_value/distinct_id_value, random_pool, exclude_columns, value_mapping) record a decision the user has already made; they are never to make a validation failure disappear. When convert quarantines rows, present the failure first — the error code, the row count, its share of the total, and which events or time ranges are affected — and state the consequence in the user's terms ("3,000 events would carry a time that is not when they happened"). Only after the user has seen that may one of these options be set. When the evidence is insufficient, report the batch as not passed and pending customer data; never shrink the upload scope to manufacture a pass.
• Do not read or send an AE access token or CLI token to /sync_json. The receiver request uses only APPID and UE data.
• Never execute data-integration upload until the user has seen the target, mapping, valid/quarantined counts, batches, and dry-run and has explicitly confirmed that upload.
• A blocked manifest requires a second, explicit clean-subset decision. Never add --allow-clean-subset implicitly.
• If a batch times out or loses the network, treat that batch as unknown. Stop. Ask the user to verify receiver/AE data before the user chooses --resume-from; never resume automatically.
• Local analysis stays local. AE Agent attachment is a separate, confirmed branch with a 50 MB per-file limit.
• data-integration upload is not idempotent — every execution submits to the receiver again. Never re-run it just to inspect a response; read the first run's saved JSON output instead. --dry-run previews the request only, never the receiver's real response.

When to use / When NOT to use

Use this skill when the user wants to bring a local data file (CSV/TSV/TXT/JSON/JSONL/XLS/XLSX) or a Feishu sheet / Bitable (多维表格) URL into AE, or analyze a local file without uploading.

This skill also produces a tracking-plan draft (source_type: data) as a governance prerequisite; that draft is an input to ae-generate-tracking-plan, not a substitute for its five-phase platform plan.

Workflow

Walk the four submodules in order. Each submodule is its own reference; follow it and come back here for the next step.

1. Source — business identification. A source is either a local file — read references/source-inspect.md — or an online document URL. Feishu sheet links read references/lark-sheet-source.md, and Bitable (多维表格 / /base/) links read references/lark-bitable-source.md; each self-checks the lark-cli environment (installed, logged in, has access) and snapshots the document to a local file (XLSX for sheets, JSONL for Bitable) before rejoining this step. Other online documents (Tencent Docs / DingTalk / WPS / Google Sheets / Notion) have no CLI read path — read references/manual-export-source.md, which has the user export the file themselves, then rejoins this step. Profile every file fully, infer its business meaning using business-doc / user-prompt priors, then pick a branch via references/ue-routing.md: UE ingestion, dimension routing (references/dimension-routing.md), or local analysis.
2. Reuse check. If the profile is ue_eligible, read references/reuse.md and match the recommended mapping against the handoff index. reuse searches the current directory's .ae-cli/data-integration/ upward, then ~/.ae-cli/data-integration/, so a package written elsewhere is still found. A match proposes a frozen package; after one explicit confirmation, run the returned transform.mjs command and jump to Sink (step 5). No match → continue.
3. Tracking plan. Read references/tracking-plan.md. The plan is generated from the mapping (plan --mapping), so confirm the recommended mapping's key system fields with the user first — mode, #account_id/#distinct_id, #time + timezone, #event_name, #ip/#uuid (see references/transform.md steps 1–5) — then generate the event/property plan and get a single explicit confirmation from the user before touching data. The plan is a separate, required deliverable from the transform mapping: a user who supplies a column→field mapping directly has not completed this step, so build the plan from the confirmed mapping anyway. user_set still requires a plan (no events; every property becomes a user property). This step runs for every file: a second or later file merges its new events and properties into the existing project plan (tracking-plan.md step 4) — an existing plan is never a reason to skip it.
4. Transform. Read references/transform.md. Map columns to AE system fields and properties, convert, and quarantine dirty rows per references/ue-mapping.md.
5. Sink — upload. Read references/sink-upload.md. Resolve the destination, dry-run, confirm, then upload per references/sync-json-upload.md. receiver_accepted is not persistence: after a ~1-minute ingestion delay, verify the data landed with ae-cli (tracking live-data list / tracking ingest summary / tracking ingest-error list) rather than telling the user to check the console.
6. Handoff. Read references/handoff.md. Export the reusable package (pipeline descriptor + frozen mappings + stage executors + docs) and a shareable zip; in the completion response, state the absolute zip path, the package directory, and the one-line way to run the next same-shape file.

Error handling

When a step fails, classify the failure before acting — see references/error-handling.md. A quarantined row, a ragged line, and a disk-full are three different problems with three different responses: match on the error code, never retry a parse failure by guessing the encoding, and never report a program failure as a data problem.

Local analysis branch

When UE prerequisites fail, the file is an aggregate/analytical table, or the user wants analysis rather than ingestion, use references/local-analysis.md instead of the ingest pipeline.

Optional AE Agent attachment handoff

Offer this only when the user asks to continue in AE Agent. Explain that the file leaves the local machine and ask for explicit privacy confirmation.

• Reject files over 50 MB; suggest local analysis or user-controlled splitting.
• Read the ae-agent +add-attachment reference before calling it.
• Dry-run first, show file name/type/size, and wait for confirmation.
• Then run ae-cli agent +add-attachment --file '<path>'.
• Return the attachment result, a copyable analysis prompt, and directions to open AE Agent.
• Do not create or execute an Agent conversation.

Completion response

State which submodules ran, source fingerprint and selected data set, the tracking plan status, generated artifact paths, mapping confidence, valid/quarantined counts, and upload/attachment status. Keep facts separate from recommendations and clearly state whether persistence was verified.