@thinkingai/ae-cli 1.0.3 → 1.0.15

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

@@ -0,0 +1,51 @@
+# analysis_meta +generate_track_program (Generate Tracking Plan)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Project Configuration**
+
+## Use Cases
+- Generate a tracking plan from structured business context. This AI generation flow is different from save_track_items: save_track_items persists explicitly provided plan items, while this tool requests AI generation and saves the generated result asynchronously.
+- Users should check the in-site message center for final results.
+
+## CRITICAL: Pre-execution Check
+**Before calling this command, you MUST:**
+1. Call `+get_track_program` first to check if a tracking plan already exists.
+2. If the tracking plan is empty/missing, proceed directly with `+generate_track_program`.
+3. If the tracking plan already exists, STOP and warn the user: "A tracking plan already exists. Generating a new one will trigger a merge operation. Do you want to continue?" Wait for user confirmation before proceeding.
+
+## Commands
+```bash
+ae-cli analysis_meta +generate_track_program --project_id <project_id> --form_data '{}'
+ae-cli analysis_meta +generate_track_program --dry-run
+```
+
+## Parameters
+| Parameter             | Required | Description                                                                                                                                                                                                                                                                                                                                                                            |
+|-----------------------|----------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `--project_id` / `-p` | Yes      | Project ID                                                                                                                                                                                                                                                                                                                                                                             |
+| `--form_data`         | Yes      | Structured business context JSON object. Optional fields: account_system, revenue_model, core_gameplay, currency_system, main_entries, language, predefinedEvent (array of event names like install, start, close), developmentCarrier (array of platforms like Android, iOS, Unity, Cocos, Douyin Mini Game, WeChat Mini Game). All fields can be customized based on business needs. |
+
+## Decision Rules
+- **CRITICAL: Always call `+get_track_program` first to check existing tracking plan before generating.**
+- First run should only pass the required parameters (`--project_id`, `--form_data`).
+- Wrap JSON arguments in single quotes (for example `--form_data '{}'`) to avoid shell escaping issues.
+- This is an asynchronous operation; check in-site message center for generation results.
+- For cross-project troubleshooting, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Next Steps After Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill them in (focus on `--project_id` and `--form_data`).
+- If `FORM_DATA_REQUIRED_FIELDS_MISSING` occurs, ensure all required fields are provided: account_system, revenue_model, core_gameplay, currency_system, main_entries, language.
+- If `Invalid JSON` occurs, validate with the smallest JSON structure first.
+
+## Agent Response Flow
+**After successful command execution, the agent MUST inform the user in English:**
+1. The command has been submitted successfully
+2. It's running asynchronously in the background
+3. Check the TE page inbox/notifications for the generation results
+
+Example response: "Command submitted successfully. The tracking plan generation is running asynchronously. Please check your TE inbox for the results once it completes."
+
+## Recommended Chaining
+- **+get_track_program (check existing) -> +generate_track_program (if empty or user confirms) -> (check message center) -> +get_track_program (verify result)**
+- +get_project_config -> +get_track_program -> +generate_track_program

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

@@ -0,0 +1,43 @@
+# analysis_meta +generate_track_sdk_sample (Generate SDK Sample Files)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Project Configuration**
+
+## Use Cases
+- Generate SDK sample files based on the current tracking plan and requested SDK types. This flow is asynchronous and users should check in-site messages for final downloadable results.
+- Useful for developers who need SDK integration code samples based on the tracking plan.
+
+## Commands
+```bash
+ae-cli analysis_meta +generate_track_sdk_sample --project_id <project_id> --sdk_type '["android-java","ios-swift"]'
+ae-cli analysis_meta +generate_track_sdk_sample --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--sdk_type` | Yes | SDK types as JSON array. Allowed values: android-java, server-php, ios-swift, server-python, web-js, server-java, server-nodejs, wechat-miniapp, harmonyos-arkts, android-kotlin, unity-csharp, cocos-creator-ts, server-go, server-cpp, ios-objc. |
+
+## Decision Rules
+- First run should only pass the required parameters (`--project_id`, `--sdk_type`).
+- Wrap JSON arguments in single quotes (for example `--sdk_type '["android-java"]'`) to avoid shell escaping issues.
+- This is an asynchronous operation; check in-site message center for downloadable SDK sample results.
+- For cross-project troubleshooting, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Next Steps After Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill them in (focus on `--project_id` and `--sdk_type`).
+- If `SDK_TYPE_INVALID` occurs, verify that all SDK types are from the allowed values list: android-java, server-php, ios-swift, server-python, web-js, server-java, server-nodejs, wechat-miniapp, harmonyos-arkts, android-kotlin, unity-csharp, cocos-creator-ts, server-go, server-cpp, ios-objc.
+- If `Invalid JSON` occurs, validate with the smallest JSON array first (for example `["android-java"]`).
+
+## Agent Response Flow
+**After successful command execution, the agent MUST inform the user in English:**
+1. The command has been submitted successfully
+2. It's running asynchronously in the background
+3. Check the TE page inbox/notifications for the final downloadable results
+
+Example response: "Command submitted successfully. The SDK sample generation is running asynchronously. Please check your TE inbox for the download link once it completes."
+
+## Recommended Chaining
+- +get_track_program -> +generate_track_sdk_sample -> (check message center for download)

package/skills/{te-analysis/references/get-alert.md → ae-analysis/references/get_alert.md}

@@ -1,6 +1,6 @@
 # analysis +get_alert (view alert definition)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Metadata Lookup**
 
@@ -9,7 +9,7 @@ Domain: **Metadata Lookup**
 
 ## Commands
 ```bash
-ae-cli analysis +get_alert --project_id 1 --alert_id 1
+ae-cli analysis +get_alert --project_id <project_id> --alert_id 1
 ae-cli analysis +get_alert --dry-run
 ```
 

package/skills/{te-analysis/references/get-alert-definition-schema.md → ae-analysis/references/get_alert_definition_schema.md}

@@ -1,6 +1,6 @@
 # analysis +get_alert_definition_schema (Get Alert Definition Schema)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Metadata queries**
 

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

@@ -0,0 +1,61 @@
+# analysis +get_analysis_query_schema (Get Analysis Query Schema)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Model schema queries**
+
+> **CRITICAL - Step-by-Step Execution (BLOCKING)**
+>
+> **You MUST execute these steps in order. Do NOT skip any step.**
+>
+> | Step | Command | When to proceed |
+> |------|---------|-----------------|
+> | **Step 1 (MANDATORY)** | `--model_type <type>` **without `--segments`** | Always execute first. Review result. |
+> | **Step 2 (OPTIONAL)** | Add `--segments 'filter_group'` | Only if Step 1 result lacks filter/groupBy structures AND you need them |
+> | **Step 3 (OPTIONAL)** | Add `--segments 'examples'` | Only if Step 1+2 insufficient for multi-metric, time comparison, formulas |
+>
+> **WRONG:** `ae-cli analysis +get_analysis_query_schema --model_type distribution --segments 'examples'` ← **Never start here!**
+> **RIGHT:** `ae-cli analysis +get_analysis_query_schema --model_type distribution` → review → add segments if needed
+
+## Pre-call Checklist (Execute in Order)
+
+1. ✓ **Step 1 completed?** → Review core schema
+2. ✓ **Gap identified?** → Justify need (e.g., "need filter_group structure")
+3. ✓ **Justified?** → Call again with specific segment
+
+**Rule**: Uncertain → execute Step 1 first.
+
+## Command (Execute in Order)
+
+```bash
+# Step 1: ALWAYS START HERE (no segments)
+ae-cli analysis +get_analysis_query_schema --model_type event
+
+# Step 2: Only after Step 1, if filter/groupBy needed
+ae-cli analysis +get_analysis_query_schema --model_type event --segments 'filter_group' --include_core false
+
+# Step 3: Only after Step 1/2, for complex scenarios
+ae-cli analysis +get_analysis_query_schema --model_type event --segments 'examples' --include_core false
+
+# Follow-up request (already have core from earlier step in same session)
+ae-cli analysis +get_analysis_query_schema --model_type event --segments 'examples' --include_core false
+```
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--model_type` | Yes | Model type: event, retention, funnel, distribution, sql, interval, path, attribution, prop_analysis, rank_list, heat_map |
+| `--segments` | No | `core` (default), `filter_group`, `calctype`, `aggregatetype`, `examples`, `full`. Empty → core only. |
+| `--include_core` | No | Default: true. Set false for follow-up requests when core already retrieved. |
+
+## 场景分级
+
+| 场景 | 参数 | 执行顺序 |
+|---|---|---|
+| 简单 | 不传 `--segments` | **Step 1** - 单事件、单指标、无过滤、无分组 |
+| 中等 | `--segments 'filter_group'` | **Step 2** - 有过滤或分组，需先完成 Step 1 |
+| 复杂 | `--segments 'examples'` | **Step 3** - 多指标、时间对比、自定义公式，需先完成 Step 1 |
+
+## Next Steps on Failure
+- Verify model type and segment compatibility (e.g., aggregatetype not for funnel/path/interval/sql)

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

@@ -0,0 +1,53 @@
+# analysis_audience +get_cluster_definition_schema (Get Cluster Definition Schema)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Schema Query**
+
+## Use Cases
+- Support tool positioning: the current command provides the structure definition (schema) and should be used as a prerequisite step.
+- Recommended sequence: first call this schema tool to get the structure, then verify metadata in the same session and `project_id` (first build/update calls `analysis_meta +list_events` / `analysis_meta +list_properties`; later calls should reuse session-verified results first), and finally create or update clusters.
+- Get the cluster definition schema. Supports cluster type + response mode + condition subtype.
+
+## Commands
+```bash
+ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis_audience +get_cluster_definition_schema --cluster_type sql
+ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition --response_mode base
+ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition --response_mode examples --condition_subtype behavior_seq
+ae-cli analysis_audience +get_cluster_definition_schema --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--cluster_type` | Yes | Cluster type. Supported values: condition and sql |
+| `--response_mode` | No | Schema response mode. Supported values: `base`, `examples`, `full`. Default: `base`. |
+| `--condition_subtype` | No | Only effective when `--cluster_type condition`. Supported values: `core`, `behavior_seq`, `all`. Default: `core`. |
+
+## Progressive Loading Strategy
+- Use the smallest response that can solve the current task. Large schemas consume context and can make the follow-up definition construction less reliable.
+- Start with `--response_mode base` or omit `--response_mode` for simple condition clusters and SQL clusters.
+- Request `--response_mode examples` only when the base schema is not enough to build or validate the target `definition`.
+- Request `--response_mode full` only for complex, ambiguous, or repeatedly failing definition construction. Do not use `full` by default.
+- For normal condition clusters, use the default `--condition_subtype core`.
+- Use `--condition_subtype behavior_seq` only when the user specifically needs behavior sequence conditions.
+- Use `--condition_subtype all` only when comparing condition subtypes or when the exact subtype cannot be determined after reading the user request. Avoid `all` for simple creation/update tasks.
+- For clear SQL cluster requests, call `--cluster_type sql` with base mode first.
+
+## Decision Rules
+- `--cluster_type` must be explicitly set to `condition` or `sql`.
+- Prefer `--response_mode base` first; request `examples` only when needed; request `full` only as a last resort.
+- `--condition_subtype` should only be passed for `condition` schemas.
+- It is recommended to run `--dry-run` first to inspect the request mapping before making the actual call.
+- The current command returns only structure constraints; it does not guarantee that the field values are available in the target project. Event names and property names must be confirmed again with `analysis_meta` metadata interfaces.
+- Before calling `analysis_meta +list_events` / `analysis_meta +list_properties`, first read their reference docs to confirm the parameter and return-field meanings. Query metadata on the first build/update in this session for the same `project_id`; after that, prefer reusing session-verified metadata.
+
+## Next Step on Failure
+- If reading fails, first verify whether the object ID exists and belongs to the current project.
+- If the schema does not match expectations, confirm whether the correct schema interface was used (filter/groupby/query/tag/cluster).
+
+## Recommended Chain
+- First read: [`./get_cluster_definition_schema.md`](./get_cluster_definition_schema.md) -> [`./list_events.md`](./list_events.md) -> [`./list_properties.md`](./list_properties.md)
+- +get_cluster_definition_schema -> (first build/update in session or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +create_cluster
+- +get_cluster_definition_schema -> (first build/update in session or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +update_cluster

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

@@ -0,0 +1,69 @@
+# analysis_audience +get_clusters_by_name (Locate Clusters by Name)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Cluster Management**
+
+## Use Cases
+- Get cluster definition details in batch by cluster name. Returns complete cluster information for matched clusters, including IDs, names, display names, types, status, user counts, and refresh status.
+
+## Commands
+```bash
+ae-cli analysis_audience +get_clusters_by_name --project_id <project_id> --names '["demo"]'
+ae-cli analysis_audience +get_clusters_by_name --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--names` | Yes | List of cluster names (JSON array). Exact-name matching is used; unmatched clusters are ignored automatically. |
+
+## Decision Rules
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--names`) and add optional parameters after confirming the path works.
+- `--names` must be passed as a JSON array (e.g. `--names '["cluster_a","cluster_b"]'`).
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Enum Codebook (Asset Definition Interpretation Only)
+
+When interpreting cluster `definition` for users, if operator enum codes appear, use the following complete `calcuSymbol` mapping instead of outputting raw codes only.
+
+| Code | Meaning | Applicable Types |
+|---|---|---|
+| `C00` | equals | all |
+| `C000` | equals empty string | string |
+| `C01` | not equals | all |
+| `C010` | not equals empty string | string |
+| `C02` | less than | number |
+| `C020` | less than or equal | number |
+| `C03` | greater than | number |
+| `C030` | greater than or equal | number |
+| `C04` | has value | all |
+| `C05` | no value | all |
+| `C06` | range | number/date |
+| `C060` | date range | date |
+| `C07` | contains | string |
+| `C08` | does not contain | string |
+| `C09` | true | bool |
+| `C10` | false | bool |
+| `C11` | regex match | string |
+| `C12` | regex does not match | string |
+| `C13` | relative to current time | date/datetime |
+| `C14` | relative to event time | date/datetime |
+| `C15` | element exists | array |
+| `C16` | element does not exist | array |
+| `C17` | element position | array |
+| `C18` | no value | array |
+| `C19` | has value | array |
+| `C20` | belongs to cluster | cluster/tag (`tableType="2"`) |
+| `C21` | does not belong to cluster | cluster/tag (`tableType="2"`) |
+| `C22` | object exists that satisfies condition | array |
+| `C23` | no object satisfies condition | array |
+| `C24` | all objects satisfy condition | array |
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--names`).
+- If reading fails, first verify whether the object ID exists and belongs to the current project.
+
+## Recommended Chain
+- +list_clusters -> +get_clusters_by_name -> +update_cluster

package/skills/{te-analysis/references/get-filter-schema.md → ae-analysis/references/get_filter_schema.md}

@@ -1,6 +1,6 @@
 # analysis +get_filter_schema (get filter schema)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Schema Queries**
 

package/skills/{te-analysis/references/get-groupby-schema.md → ae-analysis/references/get_groupby_schema.md}

@@ -1,6 +1,6 @@
 # analysis +get_groupby_schema (Get Group-By Schema)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Schema queries**
 

package/skills/{te-meta/references/get-metric.md → ae-analysis/references/get_metric.md}

@@ -1,6 +1,6 @@
 # analysis_meta +get_metric (View Metric Details)
 
-> **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**
 
@@ -10,7 +10,7 @@ Domain: **Metadata Query**
 
 ## Commands
 ```bash
-ae-cli analysis_meta +get_metric --project_id 1 --metric_id 1
+ae-cli analysis_meta +get_metric --project_id <project_id> --metric_id 1
 ae-cli analysis_meta +get_metric --dry-run
 ```
 

package/skills/{te-meta/references/get-project-config.md → ae-analysis/references/get_project_config.md}

@@ -1,6 +1,6 @@
 # analysis_meta +get_project_config (Read Project Analysis Configuration)
 
-> **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 +get_project_config --project_id 1
+ae-cli analysis_meta +get_project_config --project_id <project_id>
 ae-cli analysis_meta +get_project_config --dry-run
 ```
 

package/skills/{te-analysis/references/get-report-definition.md → ae-analysis/references/get_report_definition.md}

@@ -1,6 +1,6 @@
 # analysis +get_report_definition (read report definition)
 
-> **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**
 
@@ -11,7 +11,7 @@ Domain: **Report Management**
 
 ## Commands
 ```bash
-ae-cli analysis +get_report_definition --project_id 1 --report_id 1
+ae-cli analysis +get_report_definition --project_id <project_id> --report_id 1
 ae-cli analysis +get_report_definition --dry-run
 ```
 

package/skills/{te-common/references/get-resource-url.md → ae-analysis/references/get_resource_url.md}

@@ -1,11 +1,11 @@
-# te-common resource link completion (call analysis_common +get_resource_url)
+# Resource link completion (call analysis_common +get_resource_url)
 
-> **Prerequisite:** Read [`../../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **cross-module post-write constraint**
 
 ## Use Cases
-- After a `create_*` or `update_*` write operation succeeds in `te-analysis` / `te-meta` / `te-audience`, complete the clickable asset link.
+- After a `create_*` or `update_*` write operation succeeds in this unified skill, complete the clickable asset link.
 - Supported resource types (resourceType): `dashboard`, `report`, `metric`, `alert`, `tag`, `cluster`, `data_table`, `super_event`, `super_prop_user`, `super_prop_event`, `virtual_event`, `user_virtual_prop`, `event_virtual_prop`.
 - Key return fields: `markdown_link`, `raw_url`.
 
@@ -16,7 +16,7 @@ Domain: **cross-module post-write constraint**
 
 ## Command
 ```bash
-ae-cli analysis_common +get_resource_url --project_id 1 --resource_type dashboard --resource_id 1
+ae-cli analysis_common +get_resource_url --project_id <project_id> --resource_type dashboard --resource_id 1
 ae-cli analysis_common +get_resource_url --dry-run
 ```
 

package/skills/{te-analysis/references/get-table-columns.md → ae-analysis/references/get_table_columns.md}

@@ -1,6 +1,6 @@
 # analysis +get_table_columns (Read Underlying Table Columns)
 
-> **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**
 
@@ -14,7 +14,7 @@ Domain: **Model analysis**
 
 ## Command
 ```bash
-ae-cli analysis +get_table_columns --project_id 1 --catalog demo --schema demo --table demo
+ae-cli analysis +get_table_columns --project_id <project_id> --catalog demo --schema demo --table demo
 ae-cli analysis +get_table_columns --dry-run
 ```
 

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

@@ -0,0 +1,49 @@
+# analysis_audience +get_tag_definition_schema (Get Tag Definition Schema)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Schema Query**
+
+## Use Cases
+- Support tool positioning: the current command provides the structure definition (schema) and should be used as a prerequisite step.
+- Recommended sequence: first call this schema tool to get the structure, then call specific business tools.
+- Typical downstream tools: `+create_tag`, `+update_tag`
+- Get the tag definition schema. Supports tag type + response mode + condition subtype.
+
+## Commands
+```bash
+ae-cli analysis_audience +get_tag_definition_schema --type condition
+ae-cli analysis_audience +get_tag_definition_schema --type metric
+ae-cli analysis_audience +get_tag_definition_schema --type condition --response_mode examples --condition_subtype behavior_seq
+ae-cli analysis_audience +get_tag_definition_schema --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--type` | Yes | Tag type. Supported values: `condition`, `metric`, `first_last`, `sql`. |
+| `--response_mode` | No | Schema response mode. Supported values: `base`, `examples`, `full`. Default: `base`. |
+| `--condition_subtype` | No | Only effective when `--type condition`. Supported values: `core`, `behavior_seq`, `all`. Default: `core`. |
+
+## Progressive Loading Strategy
+- Use the smallest response that can solve the current task. Large schemas consume context and can make the follow-up definition construction less reliable.
+- Start with `--response_mode base` or omit `--response_mode` for simple `condition`, `metric`, and `sql` tags.
+- Request `--response_mode examples` only when the base schema is not enough to build or validate the target `definition`.
+- `first_last` tags have a more specialized structure; use base first when the requested shape is simple, and escalate to `examples` when the field mapping or event/property role is unclear.
+- Request `--response_mode full` only for complex, ambiguous, or repeatedly failing definition construction. Do not use `full` by default.
+- For normal condition tags, use the default `--condition_subtype core`.
+- Use `--condition_subtype behavior_seq` only when the user specifically needs behavior sequence conditions.
+- Use `--condition_subtype all` only when comparing condition subtypes or when the exact subtype cannot be determined after reading the user request. Avoid `all` for simple creation/update tasks.
+
+## Decision Rules
+- `--type` is required and must match the target tag type.
+- It is recommended to run `--dry-run` first to inspect the request mapping before making the actual call.
+- Prefer `--response_mode base` first; request `examples` only when needed; request `full` only as a last resort.
+
+## Next Step on Failure
+- If reading fails, first verify whether the object ID exists and belongs to the current project.
+- If the schema does not match expectations, confirm whether the correct schema interface was used (filter/groupby/query/tag/cluster).
+
+## Recommended Chain
+- +get_tag_definition_schema -> (first build/update in session or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +create_tag
+- +get_tag_definition_schema -> (first build/update in session or refresh) analysis_meta +list_events -> analysis_meta +list_properties -> +update_tag

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

@@ -0,0 +1,69 @@
+# analysis_audience +get_tags_by_name (Locate Tags by Name)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Tag Management**
+
+## Use Cases
+- Get tag definition details in batch by tag name. Returns complete tag information for matched tags, including IDs, names, display names, types, status, user counts, and tag definitions.
+
+## Commands
+```bash
+ae-cli analysis_audience +get_tags_by_name --project_id <project_id> --names '["demo"]'
+ae-cli analysis_audience +get_tags_by_name --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--names` | Yes | List of tag names (JSON array). Exact-name matching is used; unmatched tags are ignored automatically. |
+
+## Decision Rules
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--names`) and add optional parameters after confirming the path works.
+- `--names` must be passed as a JSON array (e.g. `--names '["tag_a","tag_b"]'`).
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Enum Codebook (Asset Definition Interpretation Only)
+
+When interpreting tag `definition` for users, if operator enum codes appear, use the following complete `calcuSymbol` mapping instead of outputting raw codes only.
+
+| Code | Meaning | Applicable Types |
+|---|---|---|
+| `C00` | equals | all |
+| `C000` | equals empty string | string |
+| `C01` | not equals | all |
+| `C010` | not equals empty string | string |
+| `C02` | less than | number |
+| `C020` | less than or equal | number |
+| `C03` | greater than | number |
+| `C030` | greater than or equal | number |
+| `C04` | has value | all |
+| `C05` | no value | all |
+| `C06` | range | number/date |
+| `C060` | date range | date |
+| `C07` | contains | string |
+| `C08` | does not contain | string |
+| `C09` | true | bool |
+| `C10` | false | bool |
+| `C11` | regex match | string |
+| `C12` | regex does not match | string |
+| `C13` | relative to current time | date/datetime |
+| `C14` | relative to event time | date/datetime |
+| `C15` | element exists | array |
+| `C16` | element does not exist | array |
+| `C17` | element position | array |
+| `C18` | no value | array |
+| `C19` | has value | array |
+| `C20` | belongs to cluster | cluster/tag (`tableType="2"`) |
+| `C21` | does not belong to cluster | cluster/tag (`tableType="2"`) |
+| `C22` | object exists that satisfies condition | array |
+| `C23` | no object satisfies condition | array |
+| `C24` | all objects satisfy condition | array |
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--names`).
+- If reading fails, first verify whether the object ID exists and belongs to the current project.
+
+## Recommended Chain
+- +list_tags -> +get_tags_by_name -> +update_tag

package/skills/{te-meta/references/get-track-program.md → ae-analysis/references/get_track_program.md}

@@ -1,6 +1,6 @@
 # analysis_meta +get_track_program (Read Tracking Plan Baseline)
 
-> **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**
 
 ## Commands
 ```bash
-ae-cli analysis_meta +get_track_program --project_id 1
+ae-cli analysis_meta +get_track_program --project_id <project_id>
 ae-cli analysis_meta +get_track_program --dry-run
 ```
 

package/skills/{te-analysis/references/list-alerts.md → ae-analysis/references/list_alerts.md}

@@ -1,6 +1,6 @@
 # analysis +list_alerts (alert strategy search)
 
-> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
 
 Domain: **Metadata Lookup**
 
@@ -10,8 +10,9 @@ Domain: **Metadata Lookup**
 
 ## Commands
 ```bash
-ae-cli analysis +list_alerts --project_id 1
-ae-cli analysis +list_alerts --project_id 1 --query demo
+ae-cli analysis +list_alerts --project_id <project_id>
+ae-cli analysis +list_alerts --project_id <project_id> --query demo
+ae-cli analysis +list_alerts --project_id <project_id> --limit 20 --offset 0
 ae-cli analysis +list_alerts --dry-run
 ```
 
@@ -20,6 +21,8 @@ ae-cli analysis +list_alerts --dry-run
 |---|---|---|
 | `--project_id` / `-p` | Yes | Project ID |
 | `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against alert names; if omitted, all alerts are returned. |
+| `--limit` / `-l` | No | Optional page size. Default: 20, maximum: 50. |
+| `--offset` / `-o` | No | Optional page offset. Default: 0. |
 
 ## Decision Rules
 - For the first run, it is recommended to pass only the required parameters (`--project_id`) and add optional parameters after confirming the chain works.

package/skills/{te-audience/references/list-cluster-members.md → ae-analysis/references/list_cluster_members.md}

@@ -1,16 +1,19 @@
 # analysis_audience +list_cluster_members (View Cluster Members)
 
-> **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
-- List members in the specified cluster. Returns member information such as user property values and total user count.
+- List members in the specified cluster.
+- Supports payload governance parameters: `query`, `fields`, `limit`, `offset`.
+- Returns a paginated envelope (items + total + limit + offset + hasMore).
 
 ## Commands
 ```bash
-ae-cli analysis_audience +list_cluster_members --project_id 1 --cluster_name demo
-ae-cli analysis_audience +list_cluster_members --project_id 1 --cluster_name demo --property_names '["#user_id","name"]' --use_cache false
+ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo
+ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo --property_names '["#user_id","name"]' --use_cache false
+ae-cli analysis_audience +list_cluster_members --project_id <project_id> --cluster_name demo --query user_001 --fields '["#user_id","name"]' --limit 20 --offset 0
 ae-cli analysis_audience +list_cluster_members --dry-run
 ```
 
@@ -21,6 +24,10 @@ ae-cli analysis_audience +list_cluster_members --dry-run
 | `--cluster_name` | Yes | Cluster name |
 | `--property_names` | No | Optional list of user property names (JSON array) |
 | `--use_cache` | No | Whether to use cache. Default: true |
+| `--query` | No | Optional keyword filter on `#user_id` and selected properties. |
+| `--fields` | No | Optional return field list (JSON array). Invalid fields will fail with `INVALID_FIELDS`. |
+| `--limit` | No | Optional page size. Default: 20, max: 50. |
+| `--offset` | No | Optional page offset. Default: 0. |
 
 ## Decision Rules
 - For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--cluster_name`) and add optional parameters after confirming the path works.