@thinkingai/ae-cli 6.0.30 → 6.0.31

package/skills/ae-analysis/references/update_id_cluster.md

@@ -1,36 +0,0 @@
-# analysis_audience +update_id_cluster (Update ID Cluster)
-
-> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
-
-Domain: **Cluster Management**
-
-## Use Cases
-- Update an existing ID cluster by re-uploading CSV file content as plain text.
-- The cluster is identified by `cluster_name`. The operation is asynchronous.
-
-## Commands
-```bash
-ae-cli analysis_audience +update_id_cluster --project_id <project_id> --cluster_name my_id_cluster --file_content "user_001
-user_002"
-ae-cli analysis_audience +update_id_cluster --dry-run
-```
-
-## Parameters
-| Parameter | Required | Description |
-|---|---|---|
-| `--project_id` / `-p` | Yes | Project ID |
-| `--cluster_name` | Yes | Cluster name to update |
-| `--file_content` | Yes | New CSV file content as plain text. No header row, UTF-8 encoding. Each row contains one user ID. Max 100MB. |
-| `--display_name` | No | Optional new display name |
-| `--remarks` | No | Optional new remarks (max 200 characters) |
-| `--main_column_name` | No | Optional new main column name for ID matching |
-
-## Return Value
-Returns `clusterId`, `uploadNum`, `userNum`, `unmatchedNum`, and `clusterName`.
-
-## Decision Rules
-- Use `+list_clusters` to confirm the cluster name before updating.
-- If file size exceeds 100MB, inform the user to upload directly via the web interface.
-
-## Recommended Chain
-- `+list_clusters` -> `+update_id_cluster`

package/skills/ae-analysis/references/update_id_tag.md

@@ -1,37 +0,0 @@
-# analysis_audience +update_id_tag (Update ID Tag)
-
-> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
-
-Domain: **Tag Management**
-
-## Use Cases
-- Update an existing ID tag by re-uploading CSV file content as plain text.
-- The tag is identified by `tag_name`. The operation is asynchronous.
-
-## Commands
-```bash
-ae-cli analysis_audience +update_id_tag --project_id <project_id> --tag_name vip_tag --file_content "user_001,gold
-user_002,silver"
-ae-cli analysis_audience +update_id_tag --dry-run
-```
-
-## Parameters
-| Parameter | Required | Description |
-|---|---|---|
-| `--project_id` / `-p` | Yes | Project ID |
-| `--tag_name` | Yes | Tag name to update |
-| `--file_content` | Yes | New CSV file content as plain text. No header row, UTF-8 encoding. Column 1: user ID. Column 2: tag value (optional). Example: user_001,gold_member. Max 100MB. |
-| `--display_name` | No | Optional new display name |
-| `--remarks` | No | Optional new remarks (max 200 characters) |
-| `--entity_id` | No | Entity ID to associate the tag with |
-| `--main_column_name` | No | Optional new main column name for ID matching |
-
-## Return Value
-Returns `clusterId`, `uploadNum`, `userNum`, `unmatchedNum`, and `clusterName` (tag name).
-
-## Decision Rules
-- Use `+list_tags` to confirm the tag name before updating.
-- If file size exceeds 100MB, inform the user to upload directly via the web interface.
-
-## Recommended Chain
-- `+list_tags` -> `+update_id_tag`

package/skills/ae-analysis/references/update_public_access_link.md

@@ -1,41 +0,0 @@
-# analysis +update_public_access_link (Update Public Access Link)
-
-> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
-
-Domain: **Dashboard management**
-
-## Use Cases
-- Update the access controls, remark, and effective time range of a public access link. Returns the updated link information.
-- Update the access controls, remark, and effective time range of a public access link.
-
-## Command
-```bash
-ae-cli analysis +update_public_access_link --project_id <project_id> --link_id 1 --access_controls '{}' --effective_at "2026-04-09 10:00:00" --expires_at "2026-04-10 10:00:00"
-ae-cli analysis +update_public_access_link --project_id <project_id> --company_id 1 --link_id 1 --access_controls '{}' --remark demo --effective_at "2026-04-09 10:00:00" --expires_at "2026-04-10 10:00:00"
-ae-cli analysis +update_public_access_link --dry-run
-```
-
-## Parameters
-| Parameter | Required | Description |
-|---|---|---|
-| `--project_id` / `-p` | Yes | Project ID |
-| `--company_id` | No | Optional company ID. If omitted, the company ID of the project is used. |
-| `--link_id` | Yes | Link ID |
-| `--access_controls` | Yes | Public access control JSON |
-| `--remark` | No | Optional remark. Maximum length: 200 characters |
-| `--effective_at` | Yes | Effective time. Format: yyyy-MM-dd HH:mm:ss |
-| `--expires_at` | Yes | Expiration time. Format: yyyy-MM-dd HH:mm:ss |
-
-## Decision Rules
-- On the first run, start with only the required parameters (`--project_id`,`--link_id`,`--access_controls`), and add optional parameters after confirming the path works.
-- Wrap JSON parameters in single quotes (for example `--access_controls '{}'`) to avoid shell escaping issues.
-- When dates/time ranges are involved, first verify with a short range, then gradually expand the range.
-- For cross-project troubleshooting, first confirm whether `--project_id` matches the current permissions and target environment.
-
-## Next Steps on Failure
-- If required parameters are missing, fall back to the smallest runnable command and fill them in first (focus on `--project_id`, `--link_id`, `--access_controls`).
-- If `Invalid JSON` appears, first verify with the smallest JSON structure (for example `{}` or `[]`), then add fields incrementally.
-- If the result after writing does not match expectations, immediately read back the corresponding list/get interface to compare before and after.
-
-## Recommended chaining
-- +list_public_access_links -> +update_public_access_link

package/skills/ae-analysis/references/update_report.md

@@ -1,35 +0,0 @@
-# analysis +update_report (Update Report)
-
-> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
-
-Domain: **Report Management**
-
-## Use Cases
-- Update an existing report's name, description, or QP (query parameter JSON).
-- At least one of `--report_name`, `--report_desc`, or `--qp` must be provided.
-- When updating `--qp`, also provide `--report_model` for QP validation.
-
-## Commands
-```bash
-ae-cli analysis +update_report --project_id <project_id> --report_id <report_id> --report_version <version> --report_name "New Name"
-ae-cli analysis +update_report --project_id <project_id> --report_id <report_id> --report_version <version> --qp '<qp_json>' --report_model 1
-ae-cli analysis +update_report --dry-run
-```
-
-## Parameters
-| Parameter | Required | Description |
-|---|---|---|
-| `--project_id` / `-p` | Yes | Project ID |
-| `--report_id` | Yes | Report ID to update |
-| `--report_version` | Yes | Current report version number. Retrieve via `+get_report_definition`. This name avoids Commander intercepting the global `--version` flag. |
-| `--report_name` | No | New report name. Omit to keep existing. |
-| `--report_desc` | No | New report description. Omit to keep existing. |
-| `--qp` | No | New QP JSON string. Omit to keep existing. When provided, also supply `--report_model`. |
-| `--report_model` | No | Analysis model type integer (e.g. 1=event, 2=retention). Required when `--qp` is provided. |
-
-## Decision Rules
-- Always call `+get_report_definition` first to retrieve the current `version` number before updating.
-- Omitting all of `report_name`, `report_desc`, and `qp` will cause an error.
-
-## Recommended Chain
-- `+list_reports` -> `+get_report_definition` (to get version) -> `+update_report`

package/skills/ae-analysis/references/update_tag.md

@@ -1,61 +0,0 @@
-# analysis_audience +update_tag (Update Tag)
-
-> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
-
-Domain: **Tag Management**
-
-## Use Cases
-- Prerequisite helper: first call `+get_tag_definition_schema` to get the structure, then call this tool.
-- When updating `definition`, metadata must be verified in the same session and `project_id`: first definition update in this session must call `analysis_meta +list_events` and `analysis_meta +list_properties`; later updates should reuse session-verified results first.
-- Update a user tag definition. Supports updating the display name, remark, type, and tag definition. Updating only the display name or remark does not trigger recomputation.
-
-## Required Prerequisites (MUST only when updating definition)
-- If this request includes `--definition`, you must first read and follow these reference docs:
-  - [`./get_tag_definition_schema.md`](./get_tag_definition_schema.md)
-  - [`./list_events.md`](./list_events.md)
-  - [`./list_properties.md`](./list_properties.md)
-- Do not submit a new `definition` until the above docs have been read and metadata has been verified: first definition update in this session for the same `project_id` must run metadata commands; if session-verified metadata already exists, reuse it first.
-
-## Prerequisite Call Chain (run only when updating definition)
-1. First determine `--type` (condition / metric / first_last / sql).
-2. Read `get_tag_definition_schema.md`, then call `ae-cli analysis_audience +get_tag_definition_schema --type <condition|metric|first_last|sql>` to obtain the structure progressively. Start with base mode; request `examples` only if base is insufficient; request `full` only for complex, ambiguous, or repeatedly failing definition updates.
-3. Read `list_events.md`. If this is the first definition update in the current session for this `project_id` (or metadata is not yet verified), call `ae-cli analysis_meta +list_events --project_id <project_id>`; otherwise, reuse the session-verified event metadata first.
-4. Read `list_properties.md`. If this is the first definition update in the current session for this `project_id` (or metadata is not yet verified), call `ae-cli analysis_meta +list_properties --project_id <project_id>`; otherwise, reuse the session-verified property metadata first.
-5. Build the new `definition` based on the schema + metadata, then run `+update_tag`.
-
-## Commands
-```bash
-ae-cli analysis_audience +update_tag --project_id <project_id> --tag_name demo --display_name "Demo v2"
-ae-cli analysis_audience +update_tag --project_id <project_id> --tag_name demo --type condition --definition '{}' --zone_offset 8
-ae-cli analysis_audience +update_tag --dry-run
-```
-
-## Parameters
-| Parameter | Required | Description |
-|---|---|---|
-| `--project_id` / `-p` | Yes | Project ID |
-| `--tag_name` | Yes | Tag name |
-| `--display_name` | No | New tag display name. Length: 1-80 |
-| `--remark` | No | New tag remark |
-| `--type` | No | New tag type. Supported values: condition, metric, first_last, sql |
-| `--definition` | No | New tag definition JSON. If provided, MUST call `+get_tag_definition_schema` first, then fill valid event/property names from metadata verified in the same `project_id` (first definition update queries `analysis_meta` metadata commands; later updates in the same session should reuse verified results first). |
-| `--zone_offset` | No | Optional time zone offset for tag computation. Valid range: -12 to 14 (supports decimals like 5.5). |
-
-## Decision Rules
-- If you are not updating `definition` (only updating `display_name`/`remark`), you can skip the schema and metadata prerequisite chain.
-- When updating `definition`, it cannot be written from experience alone; it must satisfy both the schema structure and the project's real metadata.
-- Use progressive schema loading: base first, examples only when needed, full only as a last resort. Do not request full schema for simple tag updates when the intent is clear.
-- Before calling `list_events` / `list_properties`, you must first read the corresponding reference docs. Query metadata on the first definition update in this session for the same `project_id`; after that, prefer reusing session-verified metadata.
-- For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--tag_name`) and add optional parameters after confirming the path works.
-- Wrap JSON parameters in single quotes (e.g. `--definition '{}'`) to avoid shell escaping issues.
-- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
-- Write operations keep confirmation prompts by default; for automation scenarios, reevaluate whether to use `--yes`.
-
-## Next Step on Failure
-- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--tag_name`).
-- If `Invalid JSON` appears, first check whether a schema-required field is missing, then verify whether event/property names come from the same `project_id`'s metadata query results.
-- If the result after writing is not as expected, immediately re-read the corresponding list/get interfaces and compare before and after.
-
-## Recommended Chain
-- +get_tag_definition_schema -> (first definition update or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +update_tag
-- +list_tags -> +get_tags_by_name -> +update_tag

package/skills/ae-analysis-intent/SKILL.md

@@ -1,132 +0,0 @@
----
-name: ae-analysis-intent
-description: TE data analysis skill for metric checks, report/dashboard queries, SQL analysis, funnel/retention/path analysis, user drilldown, detail queries, anomaly diagnosis, and alert configuration. Trigger this skill whenever the user asks to check data, analyze trends, explain metric changes, or export evidence. Always use ae-cli first; only fall back to te-mcp when ae-cli has no matching capability or repeatedly fails for confirmed non-parameter reasons.
----
-
-# TE Analysis Skill
-
-## Goals
-
-- Help users locate the correct data assets: events, properties, metrics, reports, dashboards, models.
-- Produce reproducible query results through command-driven execution first.
-- Provide trend interpretation, anomaly assessment, evidence, and actionable next steps.
-
-## Mandatory Rules
-
-1. **Tool priority**
-   - First priority: `ae-cli`.
-   - Second priority: `te-mcp`, only when ae-cli has no matching capability or repeatedly fails for confirmed non-parameter reasons.
-   - Builder validation errors, missing parameters, or `need_clarification` are not fallback reasons.
-
-2. **`project_id` gate**
-   - Confirm `project_id` before any project-scoped query.
-   - If the user does not provide it and no verified project context exists, ask first. Do not guess.
-
-3. **Ad-hoc analysis QP routing**
-   - For `event`, `retention`, `funnel`, and `prop_analysis`, use the matching QP builder first.
-   - Do not call `get_analysis_query_schema`, `list_events`, `list_properties`, `list_metrics`, or `get_metric` before these builders.
-   - Only call `query_adhoc` when the builder returns `status=generated`.
-   - If the builder returns `need_clarification`, `invalid_argument`, `unsupported_feature`, or `validation_error`, stop and ask/report the structured issue. Do not handcraft QP for these four models.
-   - For `distribution`, `attribution`, `heat_map`, `interval`, `path`, `rank_list`, and `sql`, use the legacy schema/metadata path before constructing QP.
-
-4. **Existing asset first**
-   - Before ad-hoc analysis, search existing reports/dashboards when the request could match a saved business asset.
-   - If a matching report/dashboard exists, query it instead of creating a redundant ad-hoc query.
-   - Skip this only when the user explicitly asks for custom ad-hoc exploration or the saved asset does not cover required filters/groupings.
-
-5. **Pre-check before write operations**
-   - For create/update actions, run with `--dry-run` first whenever possible.
-   - After a successful write, generate and return a resource link with `analysis_common +get_resource_url` when a resource ID is available.
-
-6. **Absolute contribution attribution**
-   - Mandatory: when attributing metric changes to dimensions, use absolute contribution decomposition. Do not judge the primary driver solely by relative change percentage.
-   - See `F. ABSOLUTE_CONTRIBUTION_ATTRIBUTION` in the `ae-analysis` skill for the full algorithm and workflow.
-   - Additive metrics: sort by `|delta_dim_i|`, not by `delta_dim_i / baseline`.
-   - Ratio metrics: separate rate effects from composition effects and report hierarchically.
-   - Self-check: verify that dimension contributions sum to approximately 100% before outputting.
-
-## Capability Routing Rules
-
-1. Check whether ae-cli has a matching command.
-2. If yes, execute with ae-cli.
-3. If ae-cli fails because of missing parameters, bad field types, bad time format, permissions, timeout, or invalid payload, fix and retry ae-cli first.
-4. Fall back to te-mcp only for command-not-found, not-supported/not-implemented, clear capability gap, or repeated non-parameter failures.
-5. When falling back, briefly state why ae-cli cannot satisfy the capability.
-
-## Common ae-cli Capability Map
-
-Command format:
-
-```bash
-ae-cli <service> +<command> [options]
-```
-
-### Project and resource
-
-- List projects: `ae-cli analysis_common +list_projects`
-- Generate resource link: `ae-cli analysis_common +get_resource_url -p <project_id> --resource_type <type> --resource_id <id>`
-
-### Metadata discovery
-
-- Event list: `ae-cli analysis_meta +list_events -p <project_id>`
-- Property list: `ae-cli analysis_meta +list_properties -p <project_id>`
-- Metric list: `ae-cli analysis_meta +list_metrics -p <project_id>`
-- Table columns: `ae-cli analysis +get_table_columns -p <project_id> --table_ref <hive.schema.table|schema.table|table>`
-
-### Report/dashboard queries
-
-- Report list: `ae-cli analysis +list_reports -p <project_id>`
-- Report definition: `ae-cli analysis +get_report_definition -p <project_id> -r <report_id>`
-- Report data: `ae-cli analysis +query_report_data -p <project_id> --report_ids '[<report_id>]'`
-- Dashboard list: `ae-cli analysis +list_dashboards -p <project_id>`
-- Dashboard detail: `ae-cli analysis +query_dashboard_detail -p <project_id> -d <dashboard_id>`
-- Dashboard report data: `ae-cli analysis +query_dashboard_report_data -p <project_id> -d <dashboard_id>`
-
-### Ad-hoc analysis
-
-Builder-supported models:
-
-- Event QP builder: `ae-cli analysis +build_event_analysis_qp ...`
-- Retention QP builder: `ae-cli analysis +build_retention_analysis_qp ...`
-- Funnel QP builder: `ae-cli analysis +build_funnel_analysis_qp ...`
-- Property analysis QP builder: `ae-cli analysis +build_prop_analysis_qp ...`
-- Execute query: `ae-cli analysis +query_adhoc -p <project_id> --model_type <model_type> --qp '<builder_qp>'`
-
-Legacy/manual models:
-
-- Schema: `ae-cli analysis +get_analysis_query_schema --model_type <distribution|attribution|heat_map|interval|path|rank_list|sql>`
-- Execute query: `ae-cli analysis +query_adhoc -p <project_id> --model_type <model_type> --qp '<manual_qp>'`
-
-### Drilldown and details
-
-- User drilldown: `ae-cli analysis +drilldown_users ...`
-- User event sequence: `ae-cli analysis +drilldown_user_events ...`
-- Entity details: `ae-cli analysis +query_entity_details ...`
-- Event details: `ae-cli analysis +query_event_details ...`
-
-## Standard Execution Flow
-
-1. Clarify scope: KPI, model type, time window, dimensions, filters, and comparison baseline.
-2. Confirm `project_id`.
-3. Search existing reports/dashboards if the request may map to a saved business asset.
-4. If a matching asset exists, query report/dashboard data.
-5. If no existing asset is used:
-   - `event` / `retention` / `funnel` / `prop_analysis`: builder -> `query_adhoc`
-   - `distribution` / `attribution` / `heat_map` / `interval` / `path` / `rank_list` / `sql`: schema/metadata -> handcrafted QP -> `query_adhoc`
-6. For anomalies, slice by channel/version/time/cohort first, then drill down to users and event chains when needed.
-   - Strictly apply absolute contribution decomposition: compute each dimension's absolute delta and contribution share, then sort by absolute delta magnitude.
-7. Return conclusion, key evidence, likely causes, limitations, and next actions.
-
-## Output Requirements
-
-- Put the core conclusion first.
-- Include key data points: time, dimension, metric, value, and comparison baseline.
-- Explain trend or anomaly causes with confidence level or validation needs.
-- Provide actionable next-step recommendations.
-- Do not dump raw tables only.
-- If data, definitions, or permissions are insufficient, explicitly state the limitation and ask for the missing input.
-- Attribution output requirements:
-  - State the metric's total change in absolute and percentage terms in the core conclusion.
-  - List dimension contributions sorted by absolute delta descending; each dimension shows dimension value, absolute delta, contribution share, and relative change.
-  - Focus the conclusion on dimensions with the largest contribution share, not the largest relative change.
-  - Self-check that all dimension contribution shares sum to approximately 100%; flag the result if deviation exceeds 5 percentage points.

package/skills/ae-metadata/references/metadata_input_file_upload.md

@@ -1,29 +0,0 @@
-# metadata input-file upload
-
-> Capability endpoint: `POST /api/cli/metadata/v1/input-files` · Domain: `metadata`.
-
-## Use Cases
-
-- Upload a local CSV file before `metadata data-table csv-write`.
-- Get an `input_file_id` such as `ifile_<32 lowercase hex>`.
-
-## Command
-
-```bash
-ae-cli metadata input-file upload --project-id <project_id> --purpose data_table.csv --file <local_file> --yes
-ae-cli metadata input-file upload --project-id <project_id> --purpose data_table.csv --file <local_file> --dry-run
-```
-
-## Parameters
-
-| Parameter | Required | Description |
-|---|---|---|
-| `--project-id` / `-p` | Yes | Numeric project ID. |
-| `--purpose` | Yes | Input-file purpose. Use `data_table.csv` for data table CSV imports. |
-| `--file` | Yes | Local file path to upload. |
-
-## Decision Rules
-
-- Run `--dry-run` first to verify the gateway URL and multipart fields.
-- Use the returned `input_file_id` in CSV data-table write or create-and-bind commands.
-- This is a write command; non-dry-run execution requires `--yes`.