@thinkingai/ae-cli 1.0.3 → 1.0.18

package/skills/{te-audience/references/create-cluster.md → ae-analysis/references/create_cluster.md}

@@ -1,37 +1,40 @@
 # analysis_audience +create_cluster (Create Cluster)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Cluster Management**
 
 ## Use Cases
 - Prerequisite helper: first call `+get_cluster_definition_schema` to obtain the `definition` structure, then call this tool.
-- When building a real `definition`, you must supplement it with real project metadata: first call `analysis_meta +list_events` and `analysis_meta +list_properties`, then fill in event names/property names.
+- When building a real `definition`, metadata must be verified in the same session and `project_id`: first build in this session must call `analysis_meta +list_events` and `analysis_meta +list_properties`; later calls should reuse the session-verified results first.
 - Create a user cluster definition. Supports the condition and sql cluster types. Returns cluster information without cluster members.
 
 ## Required Prerequisites (MUST)
 - Before constructing `--definition`, you must first read and follow these reference docs:
-  - [`./get-cluster-definition-schema.md`](./get-cluster-definition-schema.md)
-  - [`../../te-meta/references/list-events.md`](../../te-meta/references/list-events.md)
-  - [`../../te-meta/references/list-properties.md`](../../te-meta/references/list-properties.md)
-- Do not generate the final `definition` until the above docs have been read and the prerequisite commands have been run.
+  - [`./get_cluster_definition_schema.md`](./get_cluster_definition_schema.md)
+  - [`./list_events.md`](./list_events.md)
+  - [`./list_properties.md`](./list_properties.md)
+- Do not generate the final `definition` until the above docs have been read and metadata has been verified: first build in this session for the same `project_id` must run metadata commands; if session-verified metadata already exists, reuse it first.
 
 ## Prerequisite Call Chain (Required for Building Definition)
-1. Read `get-cluster-definition-schema.md` to understand the input and output structure of `+get_cluster_definition_schema`.
-2. Obtain the schema structure (by cluster type):
+1. Read `get_cluster_definition_schema.md` to understand the input and output structure of `+get_cluster_definition_schema`.
+2. Obtain the schema progressively (by cluster type). Start with base mode:
    `ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition`
-3. Read `list-events.md` to understand the parameters and return structure of `+list_events`.
-4. Get the event list (for `event_name` and other fields):
-   `ae-cli analysis_meta +list_events --project_id 1`
-5. Read `list-properties.md` to understand the parameters and return structure of `+list_properties`.
-6. Get the property list (for property filters, grouping, and comparison fields):
-   `ae-cli analysis_meta +list_properties --project_id 1`
+   Request `--response_mode examples` only if base is insufficient; request `--response_mode full` only for complex, ambiguous, or repeatedly failing definition construction.
+3. Read `list_events.md` to understand the parameters and return structure of `+list_events`.
+4. Get the event list (for `event_name` and other fields): if this is the first definition build 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.
+5. Read `list_properties.md` to understand the parameters and return structure of `+list_properties`.
+6. Get the property list (for property filters, grouping, and comparison fields): if this is the first definition build 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.
 7. Build `definition` based on the schema + metadata, then call `+create_cluster`.
 
 ## Commands
 ```bash
-ae-cli analysis_audience +create_cluster --project_id 1 --cluster_name demo --display_name demo --definition '{}'
-ae-cli analysis_audience +create_cluster --project_id 1 --cluster_name demo --display_name demo --type condition --definition '{}' --zone_offset 8 --entity_id 1001
+ae-cli analysis_audience +create_cluster --project_id <project_id> --cluster_name demo --display_name demo --definition '{}'
+ae-cli analysis_audience +create_cluster --project_id <project_id> --cluster_name demo --display_name demo --type condition --definition '{}' --zone_offset 8 --entity_id 1001
 ae-cli analysis_audience +create_cluster --dry-run
 ```
 
@@ -42,14 +45,15 @@ ae-cli analysis_audience +create_cluster --dry-run
 | `--cluster_name` | Yes | Cluster name. Must start with a letter and contain only letters, digits, and underscores. Length: 1-80 |
 | `--display_name` | Yes | Cluster display name. Length: 1-80 |
 | `--type` | No | Cluster type. Supported values: condition and sql. Default: condition |
-| `--definition` | Yes | Cluster definition JSON. MUST call `+get_cluster_definition_schema` first to learn the exact structure, then use `analysis_meta +list_events` / `analysis_meta +list_properties` to fill valid event/property names from the target project. |
+| `--definition` | Yes | Cluster definition JSON. MUST call `+get_cluster_definition_schema` first to learn the exact structure, then fill valid event/property names from metadata verified in the same `project_id` (first build queries `analysis_meta` metadata commands; later builds in the same session should reuse verified results first). |
 | `--zone_offset` | No | Optional time zone offset for cluster computation. Valid range: -12 to 14 (supports decimals like 5.5). If the user does not specify a timezone, omit this parameter. When a timezone is specified, call get_project_config first to check whether the project supports time zones (timeZoneEnabled) and available values (availableTimeZones). |
 | `--entity_id` | No | Optional entity ID for cluster definition. Use list_entities to query available entities. |
 
 ## Decision Rules
 - `definition` cannot be written from experience alone: it must satisfy both the schema structure and the project's real metadata (events and properties).
 - Determine `--type` first, then fetch the schema for the corresponding `--cluster_type`; do not mix condition/sql structures.
-- Before calling `list_events` / `list_properties`, you must first read their reference docs to avoid misuse of parameters or misreading return fields.
+- Use progressive schema loading: base first, examples only when needed, full only as a last resort. Do not request full schema for simple cluster creation when the intent is clear.
+- Before calling `list_events` / `list_properties`, you must first read their reference docs to avoid misuse of parameters or misreading return fields. Query metadata on the first build 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`, `--cluster_name`, `--display_name`, `--definition`) 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.
@@ -61,5 +65,5 @@ ae-cli analysis_audience +create_cluster --dry-run
 - 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_cluster_definition_schema -> analysis_meta +list_events -> analysis_meta +list_properties -> +create_cluster
+- +get_cluster_definition_schema -> (first build or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +create_cluster
 - +list_clusters -> +get_clusters_by_name -> +update_cluster

package/skills/{te-analysis/references/create-dashboard.md → ae-analysis/references/create_dashboard.md}

@@ -1,6 +1,6 @@
 # analysis +create_dashboard (create dashboard)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Dashboard Management**
 
@@ -12,9 +12,9 @@ Domain: **Dashboard Management**
 
 ## Commands
 ```bash
-ae-cli analysis +create_dashboard --project_id 1 --dashboard_name demo
-ae-cli analysis +create_dashboard --project_id 1 --dashboard_name demo --space_id 1 --folder_id 1 --initial_report_id 1 --note_title demo --note_content demo --note_style '{}'
-ae-cli analysis +create_dashboard --project_id 1 --dashboard_name demo --dry-run
+ae-cli analysis +create_dashboard --project_id <project_id> --dashboard_name demo
+ae-cli analysis +create_dashboard --project_id <project_id> --dashboard_name demo --space_id 1 --folder_id 1 --initial_report_id 1 --note_title demo --note_content demo --note_style '{}'
+ae-cli analysis +create_dashboard --project_id <project_id> --dashboard_name demo --dry-run
 ```
 
 ## Parameters

package/skills/{te-meta/references/create-metric.md → ae-analysis/references/create_metric.md}

@@ -1,6 +1,6 @@
 # analysis_meta +create_metric (Create Metric)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Metadata Query**
 
@@ -12,23 +12,23 @@ Domain: **Metadata Query**
 
 ## MUST Prerequisites
 - Before constructing `--events` / `--params`, you must first read and follow these reference documents:
-  - [`../../te-analysis/references/get-analysis-query-schema.md`](../../te-analysis/references/get-analysis-query-schema.md)
-  - [`./list-events.md`](./list-events.md)
-  - [`./list-properties.md`](./list-properties.md)
+  - [`./get_analysis_query_schema.md`](./get_analysis_query_schema.md)
+  - [`./list_events.md`](./list_events.md)
+  - [`./list_properties.md`](./list_properties.md)
 - Do not generate the final `events` / `params` until the document review and prerequisite command calls above are complete.
 
 ## Prerequisite Call Chain (Required for Constructing events/params)
 1. Determine `--model_type` first (`event` / `retention`).
-2. Read `get-analysis-query-schema.md`, then call `ae-cli analysis +get_analysis_query_schema --model_type <event|retention>` to get the structure.
-3. Read `list-events.md`, then call `ae-cli analysis_meta +list_events --project_id 1` to get available events.
-4. Read `list-properties.md`, then call `ae-cli analysis_meta +list_properties --project_id 1` to get available properties.
+2. Read `get_analysis_query_schema.md`, then call `ae-cli analysis +get_analysis_query_schema --model_type <event|retention>` to get the structure.
+3. Read `list_events.md`, then call `ae-cli analysis_meta +list_events --project_id <project_id>` to get available events.
+4. Read `list_properties.md`, then call `ae-cli analysis_meta +list_properties --project_id <project_id>` to get available properties.
 5. Build `events` / `params` from the schema + metadata, then call `+create_metric`.
-6. If an accessible URL must be returned, apply resource-link completion according to the unified `te-common` constraints (call `analysis_common +get_resource_url`).
+6. If an accessible URL must be returned, apply resource-link completion according to the unified skill constraints (call `analysis_common +get_resource_url`).
 
 ## Commands
 ```bash
-ae-cli analysis_meta +create_metric --project_id 1 --name demo --display_name demo --model_type event --events '[]' --params '{}'
-ae-cli analysis_meta +create_metric --project_id 1 --name demo --display_name demo --remark demo --model_type event --events '[]' --params '{}'
+ae-cli analysis_meta +create_metric --project_id <project_id> --name demo --display_name demo --model_type event --events '[]' --params '{}'
+ae-cli analysis_meta +create_metric --project_id <project_id> --name demo --display_name demo --remark demo --model_type event --events '[]' --params '{}'
 ae-cli analysis_meta +create_metric --dry-run
 ```
 

package/skills/{te-analysis/references/create-or-update-dashboard-note.md → ae-analysis/references/create_or_update_dashboard_note.md}

@@ -1,6 +1,6 @@
 # analysis +create_or_update_dashboard_note (Maintain Dashboard Note)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Dashboard management**
 
@@ -10,8 +10,8 @@ Domain: **Dashboard management**
 
 ## Command
 ```bash
-ae-cli analysis +create_or_update_dashboard_note --project_id 1 --dashboard_id 1 --note_title demo
-ae-cli analysis +create_or_update_dashboard_note --project_id 1 --dashboard_id 1 --note_id 1 --note_title demo --description demo --ui_config '{}'
+ae-cli analysis +create_or_update_dashboard_note --project_id <project_id> --dashboard_id 1 --note_title demo
+ae-cli analysis +create_or_update_dashboard_note --project_id <project_id> --dashboard_id 1 --note_id 1 --note_title demo --description demo --ui_config '{}'
 ae-cli analysis +create_or_update_dashboard_note --dry-run
 ```
 

package/skills/{te-meta/references/create-project-mark-time.md → ae-analysis/references/create_project_mark_time.md}

@@ -1,6 +1,6 @@
 # analysis_meta +create_project_mark_time (Create Project Date Marker)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Project Configuration**
 
@@ -10,8 +10,8 @@ Domain: **Project Configuration**
 
 ## Command
 ```bash
-ae-cli analysis_meta +create_project_mark_time --project_id 1 --marked_at '2026-04-09 10:00' --content demo
-ae-cli analysis_meta +create_project_mark_time --project_id 1 --marked_at '2026-04-09 10:00' --zone_offset 8 --content demo --is_visible 1
+ae-cli analysis_meta +create_project_mark_time --project_id <project_id> --marked_at '2026-04-09 10:00' --content demo
+ae-cli analysis_meta +create_project_mark_time --project_id <project_id> --marked_at '2026-04-09 10:00' --zone_offset 8 --content demo --is_visible 1
 ae-cli analysis_meta +create_project_mark_time --dry-run
 ```
 

package/skills/{te-analysis/references/create-public-access-link.md → ae-analysis/references/create_public_access_link.md}

@@ -1,6 +1,6 @@
 # analysis +create_public_access_link (create public access link)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Dashboard Management**
 
@@ -11,8 +11,8 @@ Domain: **Dashboard Management**
 
 ## Commands
 ```bash
-ae-cli analysis +create_public_access_link --project_id 1 --resource_type dashboard --resource_id 1 --access_controls '{}' --effective_at "2026-04-09 10:00:00" --expires_at "2026-04-10 10:00:00"
-ae-cli analysis +create_public_access_link --project_id 1 --company_id 1 --resource_type dashboard --resource_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 +create_public_access_link --project_id <project_id> --resource_type dashboard --resource_id 1 --access_controls '{}' --effective_at "2026-04-09 10:00:00" --expires_at "2026-04-10 10:00:00"
+ae-cli analysis +create_public_access_link --project_id <project_id> --company_id 1 --resource_type dashboard --resource_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 +create_public_access_link --dry-run
 ```
 

package/skills/{te-analysis/references/create-report.md → ae-analysis/references/create_report.md}

@@ -1,6 +1,6 @@
 # analysis +create_report (Create Report)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Report management**
 
@@ -11,22 +11,22 @@ Domain: **Report management**
 
 ## Mandatory prerequisites (MUST)
 - Before constructing `--analysis_query`, you must first read and follow these reference documents:
-  - [`./get-analysis-query-schema.md`](./get-analysis-query-schema.md)
-  - [`../../te-meta/references/list-events.md`](../../te-meta/references/list-events.md)
-  - [`../../te-meta/references/list-properties.md`](../../te-meta/references/list-properties.md)
+  - [`./get_analysis_query_schema.md`](./get_analysis_query_schema.md)
+  - [`./list_events.md`](./list_events.md)
+  - [`./list_properties.md`](./list_properties.md)
 - Do not generate the final `analysis_query` until the documentation review and prerequisite command calls are complete.
 
 ## Prerequisite call chain (required for constructing analysis_query)
 1. First determine `--model_type`.
-2. Read `get-analysis-query-schema.md`, then call `ae-cli analysis +get_analysis_query_schema --model_type <model_type>` to get the structure.
-3. Read `list-events.md`, then call `ae-cli analysis_meta +list_events --project_id 1`.
-4. Read `list-properties.md`, then call `ae-cli analysis_meta +list_properties --project_id 1`.
+2. Read `get_analysis_query_schema.md`, then call `ae-cli analysis +get_analysis_query_schema --model_type <model_type>` to get the structure.
+3. Read `list_events.md`, then call `ae-cli analysis_meta +list_events --project_id <project_id>`.
+4. Read `list_properties.md`, then call `ae-cli analysis_meta +list_properties --project_id <project_id>`.
 5. Build `analysis_query` from the schema + metadata, then call `+create_report`.
 
 ## Command
 ```bash
-ae-cli analysis +create_report --project_id 1 --report_name demo --model_type event --analysis_query '{}'
-ae-cli analysis +create_report --project_id 1 --report_name demo --model_type event --analysis_query '{}' --description demo --cache_seconds 8 --query_duration_ms 8 --dashboard_ids '[]'
+ae-cli analysis +create_report --project_id <project_id> --report_name demo --model_type event --analysis_query '{}'
+ae-cli analysis +create_report --project_id <project_id> --report_name demo --model_type event --analysis_query '{}' --description demo --cache_seconds 8 --query_duration_ms 8 --dashboard_ids '[]'
 ae-cli analysis +create_report --dry-run
 ```
 

package/skills/{te-analysis/references/create-result-cluster.md → ae-analysis/references/create_result_cluster.md}

@@ -1,6 +1,6 @@
 # analysis +create_result_cluster (create result cluster)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Model Analysis**
 
@@ -13,9 +13,9 @@ Domain: **Model Analysis**
 
 ## Mandatory Prerequisites (MUST)
 - Before building `--qp` and the various drilldown parameters, you must first read and follow the following reference docs:
-  - [`./query-adhoc.md`](./query-adhoc.md)
-  - [`./query-report-data.md`](./query-report-data.md)
-  - [`./query-dashboard-report-data.md`](./query-dashboard-report-data.md)
+  - [`./query_adhoc.md`](./query_adhoc.md)
+  - [`./query_report_data.md`](./query_report_data.md)
+  - [`./query_dashboard_report_data.md`](./query_dashboard_report_data.md)
 - `qp`, `drilldown_date`, `drilldown_groups`, `event_index`, `retention_days`, `funnel_step`, and other parameters must come from real analysis results and must not be guessed.
 - Do not create a result cluster until the upstream query and result reread have been completed.
 
@@ -27,8 +27,8 @@ Domain: **Model Analysis**
 
 ## Commands
 ```bash
-ae-cli analysis +create_result_cluster --project_id 1 --cluster_name demo --model_type event --qp '{}'
-ae-cli analysis +create_result_cluster --project_id 1 --cluster_name demo --display_name demo --model_type event --qp '{}' --zone_offset 8 --drilldown_date 2026-04-08 --drilldown_groups '[]' --event_index 8 --is_lost true --retention_days 8 --is_churned_user true --funnel_step 8 --interval demo --distribution_bucket 8 --compare_index 8 --include_total true --relation_val demo
+ae-cli analysis +create_result_cluster --project_id <project_id> --cluster_name demo --model_type event --qp '{}'
+ae-cli analysis +create_result_cluster --project_id <project_id> --cluster_name demo --display_name demo --model_type event --qp '{}' --zone_offset 8 --drilldown_date 2026-04-08 --drilldown_groups '[]' --event_index 8 --is_lost true --retention_days 8 --is_churned_user true --funnel_step 8 --interval demo --distribution_bucket 8 --compare_index 8 --include_total true --relation_val demo
 ae-cli analysis +create_result_cluster --dry-run
 ```
 

package/skills/{te-audience/references/create-tag.md → ae-analysis/references/create_tag.md}

@@ -1,33 +1,33 @@
 # analysis_audience +create_tag (Create Tag)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **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 obtain the structure, then call this tool.
-- When building a real `definition`, you must supplement it with real project metadata; at minimum, first call `analysis_meta +list_events` and `analysis_meta +list_properties`.
+- When building a real `definition`, metadata must be verified in the same session and `project_id`: first build in this session must call `analysis_meta +list_events` and `analysis_meta +list_properties`; later calls should reuse the session-verified results first.
 - Create a user tag definition. Supports the condition, metric, first_last, and sql tag types. Returns the new tag ID without tag members.
 
 ## Required Prerequisites (MUST)
 - Before constructing `--definition`, you must first read and follow these reference docs:
-  - [`./get-tag-definition-schema.md`](./get-tag-definition-schema.md)
-  - [`../../te-meta/references/list-events.md`](../../te-meta/references/list-events.md)
-  - [`../../te-meta/references/list-properties.md`](../../te-meta/references/list-properties.md)
-- Do not generate the final `definition` until the above docs have been read and the prerequisite commands have been run.
+  - [`./get_tag_definition_schema.md`](./get_tag_definition_schema.md)
+  - [`./list_events.md`](./list_events.md)
+  - [`./list_properties.md`](./list_properties.md)
+- Do not generate the final `definition` until the above docs have been read and metadata has been verified: first build in this session for the same `project_id` must run metadata commands; if session-verified metadata already exists, reuse it first.
 
 ## Prerequisite Call Chain (Required for Building Definition)
 1. First determine `--type` (condition / metric / first_last / sql).
-2. Read `get-tag-definition-schema.md` to understand the return structure of `+get_tag_definition_schema`.
-3. Call `ae-cli analysis_audience +get_tag_definition_schema` to obtain the schema.
-4. Read `list-events.md`, then call `ae-cli analysis_meta +list_events --project_id 1` to get available events.
-5. Read `list-properties.md`, then call `ae-cli analysis_meta +list_properties --project_id 1` to get available properties.
+2. Read `get_tag_definition_schema.md` to understand the return structure of `+get_tag_definition_schema`.
+3. Call `ae-cli analysis_audience +get_tag_definition_schema --type <condition|metric|first_last|sql>` to obtain the schema progressively. Start with base mode; request `examples` only if base is insufficient; request `full` only for complex, ambiguous, or repeatedly failing definition construction.
+4. Read `list_events.md`. If this is the first definition build 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.
+5. Read `list_properties.md`. If this is the first definition build 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.
 6. Build `definition` based on the schema + metadata, then call `+create_tag`.
 
 ## Commands
 ```bash
-ae-cli analysis_audience +create_tag --project_id 1 --tag_name demo --display_name demo --definition '{}'
-ae-cli analysis_audience +create_tag --project_id 1 --tag_name demo --display_name demo --type condition --definition '{}' --zone_offset 8 --entity_id 1001
+ae-cli analysis_audience +create_tag --project_id <project_id> --tag_name demo --display_name demo --definition '{}'
+ae-cli analysis_audience +create_tag --project_id <project_id> --tag_name demo --display_name demo --type condition --definition '{}' --zone_offset 8 --entity_id 1001
 ae-cli analysis_audience +create_tag --dry-run
 ```
 
@@ -38,13 +38,14 @@ ae-cli analysis_audience +create_tag --dry-run
 | `--tag_name` | Yes | Tag name. Must start with a letter and contain only letters, digits, and underscores. Length: 1-80 |
 | `--display_name` | Yes | Tag display name. Length: 1-80 |
 | `--type` | No | Tag type. Supported values: condition, metric, first_last, sql |
-| `--definition` | Yes | Tag definition JSON. MUST call `+get_tag_definition_schema` first, then fill valid event/property names from `analysis_meta` metadata commands in the same `project_id`. |
+| `--definition` | Yes | Tag definition JSON. MUST call `+get_tag_definition_schema` first, then fill valid event/property names from metadata verified in the same `project_id` (first build queries `analysis_meta` metadata commands; later builds 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). If the user does not specify a timezone, omit this parameter. When a timezone is specified, call get_project_config first to check whether the project supports time zones (timeZoneEnabled) and available values (availableTimeZones). |
 | `--entity_id` | No | Optional entity ID for tag definition. Use list_entities to query available entities. |
 
 ## Decision Rules
 - `definition` cannot be written from experience alone: it must satisfy both the schema structure and the project's real metadata.
-- Before calling `list_events` / `list_properties`, you must first read the corresponding reference docs to avoid misuse of parameters or misreading return fields.
+- Use progressive schema loading: base first, examples only when needed, full only as a last resort. Do not request full schema for simple tag creation when the intent is clear.
+- Before calling `list_events` / `list_properties`, you must first read the corresponding reference docs to avoid misuse of parameters or misreading return fields. Query metadata on the first build 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`, `--display_name`, `--definition`) 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.
@@ -56,5 +57,5 @@ ae-cli analysis_audience +create_tag --dry-run
 - 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 -> analysis_meta +list_events -> analysis_meta +list_properties -> +create_tag
+- +get_tag_definition_schema -> (first build or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +create_tag
 - +list_tags -> +get_tags_by_name -> +update_tag

package/skills/{te-meta/references/create-virtual-event.md → ae-analysis/references/create_virtual_event.md}

@@ -1,6 +1,6 @@
 # analysis_meta +create_virtual_event (Create Virtual Event)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Metadata Query**
 
@@ -16,22 +16,22 @@ Domain: **Metadata Query**
 
 ## MUST Prerequisites
 - Before constructing `--events` / `--filter`, you must first read and follow these reference documents:
-  - [`../../te-analysis/references/get-filter-schema.md`](../../te-analysis/references/get-filter-schema.md)
-  - [`./list-events.md`](./list-events.md)
-  - [`./list-properties.md`](./list-properties.md)
+  - [`./get_filter_schema.md`](./get_filter_schema.md)
+  - [`./list_events.md`](./list_events.md)
+  - [`./list_properties.md`](./list_properties.md)
 - Do not generate the final `events` / `filter` until the document review and prerequisite command calls above are complete.
 
 ## Prerequisite Call Chain (Required for Constructing events/filter)
-1. Read `get-filter-schema.md`, then call `ae-cli analysis +get_filter_schema` to get the filter structure.
-2. Read `list-events.md`, then call `ae-cli analysis_meta +list_events --project_id 1` to get available events.
-3. Read `list-properties.md`, then call `ae-cli analysis_meta +list_properties --project_id 1` to get properties available for filtering.
+1. Read `get_filter_schema.md`, then call `ae-cli analysis +get_filter_schema` to get the filter structure.
+2. Read `list_events.md`, then call `ae-cli analysis_meta +list_events --project_id <project_id>` to get available events.
+3. Read `list_properties.md`, then call `ae-cli analysis_meta +list_properties --project_id <project_id>` to get properties available for filtering.
 4. Build `events` / `filter` from the schema + metadata, then call `+create_virtual_event`.
 5. Example events JSON: `[{"eventName":"purchase"},{"eventName":"add_to_cart"}]`
 
 ## Commands
 ```bash
-ae-cli analysis_meta +create_virtual_event --project_id 1 --event_name ta@demo --event_desc demo --events '[{"eventName":"purchase"}]'
-ae-cli analysis_meta +create_virtual_event --project_id 1 --event_name ta@demo2 --event_desc demo --remark demo --events '[{"eventName":"add_to_cart"}]' --filter '{}' --override true
+ae-cli analysis_meta +create_virtual_event --project_id <project_id> --event_name ta@demo --event_desc demo --events '[{"eventName":"purchase"}]'
+ae-cli analysis_meta +create_virtual_event --project_id <project_id> --event_name ta@demo2 --event_desc demo --remark demo --events '[{"eventName":"add_to_cart"}]' --filter '{}' --override true
 ae-cli analysis_meta +create_virtual_event --dry-run
 ```
 

package/skills/{te-meta/references/create-virtual-property.md → ae-analysis/references/create_virtual_property.md}

@@ -1,6 +1,6 @@
 # analysis_meta +create_virtual_property (Create Virtual Property)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Metadata Query**
 
@@ -18,22 +18,22 @@ Domain: **Metadata Query**
 
 ## Mandatory Prerequisites (MUST)
 - Before building `--sql_expression` / `--related_events`, you must first read and follow the reference docs below:
-  - [`./list-properties.md`](./list-properties.md)
-  - [`./list-events.md`](./list-events.md) (only when `sql_event_relation_type=relation_by_setting`)
+  - [`./list_properties.md`](./list_properties.md)
+  - [`./list_events.md`](./list_events.md) (only when `sql_event_relation_type=relation_by_setting`)
 - Do not submit the final SQL and event-association configuration until the above docs have been read and the prerequisite commands have been run.
 
 ## Prerequisite Call Chain (required for building SQL and relations)
-1. Read `list-properties.md`, then run `ae-cli analysis_meta +list_properties --project_id 1` to get the available properties.
+1. Read `list_properties.md`, then run `ae-cli analysis_meta +list_properties --project_id <project_id>` to get the available properties.
 2. Use `--table_type` to determine the SQL field source (event or user scope).
 3. Write `--sql_expression` using only fields confirmed in the previous step; the expression must conform to Trino syntax.
-4. If `--sql_event_relation_type=relation_by_setting`, read `list-events.md`, then run `ae-cli analysis_meta +list_events --project_id 1` to get the available events and build `--related_events`.
+4. If `--sql_event_relation_type=relation_by_setting`, read `list_events.md`, then run `ae-cli analysis_meta +list_events --project_id <project_id>` to get the available events and build `--related_events`.
 5. Call `+create_virtual_property` to create the virtual property.
 6. Example `sql_expression`: `property_a + property_b` or `CASE WHEN status = 1 THEN 'active' ELSE 'inactive' END`.
 
 ## Command
 ```bash
-ae-cli analysis_meta +create_virtual_property --project_id 1 --property_name '#vp@demo' --table_type event --select_type string --sql_expression 'event_name' --sql_event_relation_type relation_default
-ae-cli analysis_meta +create_virtual_property --project_id 1 --property_name '#vp@demo' --property_desc demo --table_type event --select_type string --sql_expression "CASE WHEN status = 1 THEN 'active' ELSE 'inactive' END" --sql_event_relation_type relation_by_setting --related_events '[{"eventName":"purchase"}]' --property_remark demo
+ae-cli analysis_meta +create_virtual_property --project_id <project_id> --property_name '#vp@demo' --table_type event --select_type string --sql_expression 'event_name' --sql_event_relation_type relation_default
+ae-cli analysis_meta +create_virtual_property --project_id <project_id> --property_name '#vp@demo' --property_desc demo --table_type event --select_type string --sql_expression "CASE WHEN status = 1 THEN 'active' ELSE 'inactive' END" --sql_event_relation_type relation_by_setting --related_events '[{"eventName":"purchase"}]' --property_remark demo
 ae-cli analysis_meta +create_virtual_property --dry-run
 ```
 

package/skills/{te-meta/references/delete-project-mark-times.md → ae-analysis/references/delete_project_mark_times.md}

@@ -1,6 +1,6 @@
 # analysis_meta +delete_project_mark_times (Delete Project Mark Times)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Project Configuration**
 
@@ -9,7 +9,7 @@ Domain: **Project Configuration**
 
 ## Commands
 ```bash
-ae-cli analysis_meta +delete_project_mark_times --project_id 1 --mark_time_ids '[]'
+ae-cli analysis_meta +delete_project_mark_times --project_id <project_id> --mark_time_ids '[]'
 ae-cli analysis_meta +delete_project_mark_times --dry-run
 ```
 

package/skills/{te-meta/references/delete-track-items.md → ae-analysis/references/delete_track_items.md}

@@ -1,6 +1,6 @@
 # analysis_meta +delete_track_items (Delete Track Program Items)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Project Configuration**
 
@@ -10,7 +10,7 @@ Domain: **Project Configuration**
 
 ## Command
 ```bash
-ae-cli analysis_meta +delete_track_items --project_id 1 --delete_data '{}'
+ae-cli analysis_meta +delete_track_items --project_id <project_id> --delete_data '{}'
 ae-cli analysis_meta +delete_track_items --dry-run
 ```
 

package/skills/{te-analysis/references/drilldown-user-events.md → ae-analysis/references/drilldown_user_events.md}

@@ -1,6 +1,6 @@
 # analysis +drilldown_user_events (Single-User Event Sequence Drilldown)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Model analysis**
 
@@ -16,22 +16,22 @@ Domain: **Model analysis**
 
 ## Mandatory prerequisites (MUST)
 - Before constructing `--user_id` / `--event_names` / `--target_dates`, you must first read and follow these reference documents:
-  - [`./drilldown-users.md`](./drilldown-users.md)
-  - [`../../te-meta/references/list-events.md`](../../te-meta/references/list-events.md)
-  - [`../../te-meta/references/list-properties.md`](../../te-meta/references/list-properties.md) (only when passing `--properties`)
+  - [`./drilldown_users.md`](./drilldown_users.md)
+  - [`./list_events.md`](./list_events.md)
+  - [`./list_properties.md`](./list_properties.md) (only when passing `--properties`)
 - `user_id` must come from the `+drilldown_users` result; `event_names` / `target_dates` must come from the previous drilldown context or the actual result and must not be guessed.
 - Do not execute single-user event sequence drilldown until the upstream drilldown and result readback are complete.
 
 ## Prerequisite call chain (required for executing single-user event drilldown)
 1. First execute `+drilldown_users` and obtain the target user and drilldown context.
 2. Confirm the `user_id`, candidate events, and target discrete time points from the previous step result.
-3. If additional property display is needed, first call `analysis_meta +list_properties --project_id 1` to verify property names.
+3. If additional property display is needed, first call `analysis_meta +list_properties --project_id <project_id>` to verify property names.
 4. Call `+drilldown_user_events` to query the event sequence.
 
 ## Command
 ```bash
-ae-cli analysis +drilldown_user_events --project_id 1 --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]'
-ae-cli analysis +drilldown_user_events --project_id 1 --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]' --zone_offset 8 --use_cache true --page_num 1 --page_size 100
+ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]'
+ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]' --zone_offset 8 --use_cache true --page_num 1 --page_size 20
 ae-cli analysis +drilldown_user_events --dry-run
 ```
 
@@ -55,7 +55,7 @@ ae-cli analysis +drilldown_user_events --dry-run
 | `--entity_value` | No | Optional entity value for multi-entity scenarios |
 | `--use_cache` | No | Whether to use cache. Default: true |
 | `--page_num` | No | Start page number, default 1 |
-| `--page_size` | No | Page size, default 100 |
+| `--page_size` | No | Page size, default 20, max 50 |
 | `--timeout_minutes` | No | Query timeout in minutes |
 
 ## Decision Rules

package/skills/{te-analysis/references/drilldown-users.md → ae-analysis/references/drilldown_users.md}

@@ -1,6 +1,6 @@
 # analysis +drilldown_users (drill down analysis results to users)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Model Analysis**
 
@@ -15,9 +15,9 @@ Domain: **Model Analysis**
 
 ## Mandatory Prerequisites (MUST)
 - Before building `--qp` and the drilldown positioning parameters, you must first read and follow the following reference docs:
-  - [`./query-adhoc.md`](./query-adhoc.md)
-  - [`./query-report-data.md`](./query-report-data.md)
-  - [`./query-dashboard-report-data.md`](./query-dashboard-report-data.md)
+  - [`./query_adhoc.md`](./query_adhoc.md)
+  - [`./query_report_data.md`](./query_report_data.md)
+  - [`./query_dashboard_report_data.md`](./query_dashboard_report_data.md)
 - `qp`, `drilldown_date`, `drilldown_groups`, `event_index`, `retention_days`, `funnel_step`, and other parameters must come from real analysis results and must not be guessed.
 - Do not execute user drilldown until the upstream query and result reread have been completed.
 
@@ -29,8 +29,8 @@ Domain: **Model Analysis**
 
 ## Commands
 ```bash
-ae-cli analysis +drilldown_users --project_id 1 --model_type event --qp '{}'
-ae-cli analysis +drilldown_users --project_id 1 --model_type retention --qp '{}' --drilldown_date 2026-04-08 --drilldown_groups '[]' --event_index 8 --is_lost true --retention_days 8 --is_churned_user true --funnel_step 8 --interval demo --distribution_bucket 8 --compare_index 8 --include_total true --relation_val demo
+ae-cli analysis +drilldown_users --project_id <project_id> --model_type event --qp '{}'
+ae-cli analysis +drilldown_users --project_id <project_id> --model_type retention --qp '{}' --drilldown_date 2026-04-08 --drilldown_groups '[]' --event_index 8 --is_lost true --retention_days 8 --is_churned_user true --funnel_step 8 --interval demo --distribution_bucket 8 --compare_index 8 --include_total true --relation_val demo --limit 10 --offset 0
 ae-cli analysis +drilldown_users --dry-run
 ```
 
@@ -49,17 +49,20 @@ ae-cli analysis +drilldown_users --dry-run
 | `--retention_days` | No | Retention interval in days from the analysis result, for example 7 for day-7 retention. If model_type is 'retention', the retention_days must not be null. |
 | `--is_churned_user` | No | For funnel analysis, true queries churned users for the step and false queries converted users. Default: false |
 | `--funnel_step` | No | Funnel step number from the analysis result starting from 1. If model_type is 'funnel', the funnel_step must not be null. |
-| `--interval` | No | Interval |
+| `--interval` | No | Interval used for interval analysis |
 | `--distribution_bucket` | No | Distribution bucket index from the analysis result |
 | `--compare_index` | No | Comparison index used in comparison analysis scenarios |
 | `--include_total` | No | Whether to query users from the total row. Default: false |
 | `--relation_val` | No | Relation value used in relation analysis scenarios |
 | `--use_cache` | No | Whether to use cache. Default: true |
+| `--limit` | No | Optional limit. Default: 20, maximum: 50. |
+| `--offset` | No | Optional offset. Default: 0. |
 | `--timeout_minutes` | No | Query timeout in minutes. If the query exceeds this time, it will be cancelled automatically. |
 
 ## Decision Rules
 - Drilldown positioning parameters must come from upstream analysis results and must not be fabricated.
 - `qp` must not be rewritten or "simplified"; it should remain consistent with the source analysis.
+- For pagination, use `--limit` and `--offset` together. Default limit is 20.
 - For the first run, it is recommended to pass only the required parameters (`--project_id`, `--model_type`, `--qp`) and add optional parameters after confirming the chain works.
 - Wrap JSON parameters in single quotes (for example `--qp '{}'`, `--drilldown_groups '{}'`) to avoid shell escaping issues.
 - When dates/time ranges are involved, validate with a short range first and then expand gradually.