@thinkingai/ae-cli 1.0.27 → 1.0.30

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

@@ -0,0 +1,51 @@
+---
+name: ae-analysis-global
+version: 1.0.0
+description: "Overlay rules for AE/TE analysis global multi-cluster mode. Use only when ae-cli config cluster-mode status reports sw_cfg_enable_global_query=true. This skill supplements ae-analysis; it does not replace it."
+---
+
+# ae-analysis-global
+
+
+This is an overlay for `ae-analysis`. First use the normal `ae-analysis` rules and matching command references. Apply the rules below only when local multi-cluster mode is enabled (`ae-cli config cluster-mode status`):
+
+```bash
+ae-cli config cluster-mode status
+```
+
+The result must contain:
+
+```json
+{"sw_cfg_enable_global_query": true}
+```
+
+If the mode is not enabled, do not use this overlay.
+
+For commands added only by this overlay, read this skill's matching reference file before composing commands. Example: `+list_query_clusters` -> `references/list_query_clusters.md`.
+
+Every command accepts `--host <url>` to override the active AE host, and it may be placed after the subcommand (e.g. `ae-cli analysis +list_query_clusters --project_id <id> --host <url>`). Host selection is independent of `--cluster_query_scope`: `--host` chooses which AE instance to call, while `--cluster_query_scope` / `--slave_cluster_id` choose which cluster within global mode.
+
+## Routing Rules
+
+- In this overlay, **query cluster / service cluster / deployment cluster** means multi-cluster routing for analysis queries. **audience/user segment cluster** means audience membership assets under `analysis_audience`.
+- If the user asks for cluster inventory or cluster info, call `ae-cli analysis +list_query_clusters --project_id <project_id>`. Localized examples include "集群信息" and "有哪些集群".
+- Do not answer query-cluster inventory questions with `ae-cli analysis_audience +list_clusters` unless the user explicitly asks for audience clusters, cohorts, segments, user membership, or cluster definitions.
+- If the user mentions country, region, server, shard, site, market, or deployment area semantics, call `ae-cli analysis +list_query_clusters --project_id <project_id>` before choosing query scope.
+- Match slave cluster intent only against `slaveClusters[].clusterId`, `slaveClusters[].clusterName`, and `slaveClusters[].clusterDesc` returned by `+list_query_clusters`.
+- If a matching accessible slave cluster exists, pass `--cluster_query_scope SLAVE --slave_cluster_id <clusterId>` to `+query_report_data`, `+query_dashboard_report_data`, or `+query_adhoc`.
+- Use `--cluster_query_scope GLOBAL` only when the user clearly asks for global, all clusters, all servers, or cross-cluster aggregated data, and `permissions.canQueryGlobal=true`.
+- If the user does not express global or slave-cluster intent, omit `--cluster_query_scope`.
+- If requested global/slave scope is not allowed, explain `permissions.allowedClusterQueryParams` instead of guessing forbidden parameters.
+- For `+query_adhoc --model_type sql`, never pass `--cluster_query_scope`; SQL model analysis only supports the current self cluster.
+
+## Response Wording
+
+- For `+list_query_clusters`, call the result "query clusters" and summarize `currentCluster`, `slaveClusters`, and `permissions.allowedClusterQueryParams`.
+- For `analysis_audience +list_clusters`, call the result "audience clusters" or "user segments"; do not call those results query clusters.
+
+## Commands Added By Multi-Cluster Mode
+
+- `ae-cli analysis +list_query_clusters --project_id <project_id>`
+- `ae-cli analysis +query_report_data ... --cluster_query_scope <GLOBAL|SLAVE> [--slave_cluster_id <id>]`
+- `ae-cli analysis +query_dashboard_report_data ... --cluster_query_scope <GLOBAL|SLAVE> [--slave_cluster_id <id>]`
+- `ae-cli analysis +query_adhoc ... --cluster_query_scope <GLOBAL|SLAVE> [--slave_cluster_id <id>]`

package/skills/ae-analysis-global/references/list_query_clusters.md

@@ -0,0 +1,67 @@
+# analysis +list_query_clusters (Query Cluster Options)
+
+> **Prerequisite:** Use this reference only after `ae-analysis-global` confirms local multi-cluster mode is enabled. This command is added by the global overlay, not by the base `ae-analysis` skill.
+
+Domain: **Multi-Cluster Query Routing**
+
+## Use Cases
+
+- List the query cluster options accessible to the current account in the project.
+- Answer user questions such as "cluster info", "available query clusters", or "current cluster". Localized examples include "集群信息" and "有哪些集群".
+- Decide whether a later report/dashboard/ad-hoc query should use the current self cluster, global aggregated data, or one specific slave cluster.
+- Resolve country, region, game server, service shard, site, market, or deployment area wording to an accessible slave cluster before passing `cluster_query_scope=SLAVE`.
+
+This command is not for audience/user segment clusters. For cohort, audience, or segment assets, use `analysis_audience +list_clusters`.
+
+## Commands
+
+```bash
+ae-cli analysis +list_query_clusters --project_id <project_id>
+ae-cli analysis +list_query_clusters --dry-run
+```
+
+## Parameters
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID used to resolve the current account's cluster query permissions. |
+
+## Output Shape
+
+The result data follows the server DTO used by `list_query_clusters`:
+
+| Field | Description |
+|---|---|
+| `globalQueryEnabled` | Whether global query is enabled by server config. |
+| `currentCluster` | The current self query cluster. Fields: `clusterId`, `clusterName`, `clusterDesc`. |
+| `slaveClusters` | Accessible slave query clusters for this account and project. Each item has `clusterId`, `clusterName`, `clusterDesc`. |
+| `permissions` | Permission summary for choosing query scope. |
+| `permissions.canQueryCurrent` | Whether the user can query the current self cluster. Usually true. |
+| `permissions.canQueryGlobal` | Whether `cluster_query_scope=GLOBAL` is allowed. |
+| `permissions.canQueryAllSlaveClusters` | Whether any enabled slave cluster may be queried. |
+| `permissions.allowedSlaveClusterIds` | Slave cluster IDs this account may use. |
+| `permissions.allowedClusterQueryParams` | Human-readable allowed query parameter combinations, e.g. `omit clusterQueryScope`, `clusterQueryScope=GLOBAL`, or `clusterQueryScope=SLAVE, slaveClusterId in [...]`. |
+
+## Decision Rules
+
+- For query-cluster inventory or cluster-info questions, call this command and answer with "query clusters", not "audience clusters".
+- Default query behavior is to omit `cluster_query_scope`, which queries the current self cluster or follows the tool-specific default.
+- Pass `--cluster_query_scope GLOBAL` only when the user clearly asks for global, all clusters, all servers, cross-cluster aggregation, or equivalent aggregate wording, and `permissions.canQueryGlobal=true`.
+- Pass `--cluster_query_scope SLAVE --slave_cluster_id <clusterId>` only after this command confirms a requested country, region, server, site, market, or deployment maps to an accessible `slaveClusters[]` item.
+- Match slave intent only against `slaveClusters[].clusterId`, `slaveClusters[].clusterName`, and `slaveClusters[].clusterDesc`.
+- If the requested scope is not allowed, do not guess forbidden parameters. Explain `permissions.allowedClusterQueryParams`.
+- For `+query_adhoc --model_type sql`, never pass `cluster_query_scope`; SQL model analysis only supports the current self cluster.
+
+## Recommended Chains
+
+- Cluster inventory / cluster info -> `analysis +list_query_clusters`
+- Query DAU for Japan server -> `analysis +list_query_clusters` -> match JP/Japan slave cluster -> query report/dashboard/ad-hoc with `--cluster_query_scope SLAVE --slave_cluster_id <clusterId>`
+- Query all-cluster aggregated DAU -> `analysis +list_query_clusters` -> if `permissions.canQueryGlobal=true`, query with `--cluster_query_scope GLOBAL`
+- View audience cohorts or user segments -> `analysis_audience +list_clusters` instead
+
+## Response Wording
+
+- Use "current query cluster" for `currentCluster`.
+- Use "accessible slave query clusters" for `slaveClusters`.
+- Use "allowed query-scope parameters" for `permissions.allowedClusterQueryParams`.
+- Do not call `analysis_audience +list_clusters` results query clusters; those are audience clusters or user segments.

package/skills/ae-community/SKILL.md

@@ -1,13 +1,11 @@
 ---
 name: ae-community
 version: 2.0.0
-description: "AE community analysis: post search, comment sentiment, topic trends, risky content, livestream data. Includes AE CLI authentication, global parameters, and safety rules (self-contained)."
+description: "AE community analysis: post search, comment sentiment, topic trends, risky content, livestream data."
 ---
 
 # ae-community
 
-> **CRITICAL - This skill is self-contained.** Use the Global AE CLI Rules below; do not require a separate shared skill for community-side tasks.
-
 The AE Community domain provides social data analysis: post/video search, comment analytics, sentiment and topics, risk monitoring, and livestream metrics. Commands run as **`ae-cli community +<subcommand>`** — every community subcommand uses the **`+` prefix**.
 
 | Route (MCP) | CLI service | Responsibility |
@@ -28,6 +26,7 @@ Global parameters:
 |---|---|
 | `--format <json\|table>` | Output format. Default is JSON. |
 | `--jq <expr>` | jq filter expression for JSON output. |
+| `--host <url>` | Override the active AE host. Available on every command and may be placed after the subcommand, e.g. `ae-cli community +<command> --host <url>`. |
 
 Output and errors:
 - Successful commands return machine-readable JSON by default.

package/skills/ae-dataops/SKILL.md

@@ -6,8 +6,6 @@ description: "AE Data Development and Operations: Data warehouse management, flo
 
 # ae-dataops
 
-> **CRITICAL - This skill is self-contained.** Use the Global AE CLI Rules below; do not require a separate shared skill for DataOps-side tasks.
-
 The AE Data Development and Operations domain provides capabilities for data warehouse management, flow orchestration, IDE SQL queries, data integration, operations and backfill management, including the following subcommands:
 
 | Subcommand | Responsibility | Corresponding Scenario Skill |
@@ -33,6 +31,7 @@ Global parameters:
 |---|---|
 | `--format <json\|table>` | Output format. Default is JSON. |
 | `--jq <expr>` | jq filter expression for JSON output. |
+| `--host <url>` | Override the active AE host. Available on every command and may be placed after the subcommand, e.g. `ae-cli dataops_ide +<command> --host <url>`. |
 
 Output and errors:
 - Successful commands return machine-readable JSON by default.

package/skills/ae-engage/SKILL.md

@@ -18,6 +18,7 @@ Global parameters:
 |---|---|
 | `--format <json\|table>` | Output format. Default is JSON. |
 | `--jq <expr>` | jq filter expression for JSON output. |
+| `--host <url>` | Override the active AE host. Available on every command and may be placed after the subcommand, e.g. `ae-cli engage +<command> --host <url>`. |
 
 Output and errors:
 - Successful commands return machine-readable JSON by default.

package/skills/ae-engage/references/add-approver.md

@@ -1,6 +1,5 @@
 # ae-engage +add_approver
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Batch add approvers.
 

package/skills/ae-engage/references/add-channel.md

@@ -1,6 +1,5 @@
 # ae-engage +add_channel
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Create a new Engage channel.
 

package/skills/ae-engage/references/approver-list.md

@@ -1,6 +1,5 @@
 # ae-engage +approver_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the project approver list.
 

package/skills/ae-engage/references/cancel-query-by-request-id.md

@@ -1,6 +1,5 @@
 # ae-engage +cancel_query_by_request_id
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Cancel a running data query by requestId.
 

package/skills/ae-engage/references/channel-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +channel_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the details of a single Engage channel.
 

package/skills/ae-engage/references/channel-list.md

@@ -1,6 +1,5 @@
 # ae-engage +channel_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the list of Engage channels in a project.
 

package/skills/ae-engage/references/config-channel-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +config_channel_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query config channel details.
 

package/skills/ae-engage/references/config-channel-list.md

@@ -1,6 +1,5 @@
 # ae-engage +config_channel_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the config channel list.
 

package/skills/ae-engage/references/config-item-analysis-report.md

@@ -1,6 +1,5 @@
 # ae-engage +config_item_analysis_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the config item analysis report.
 

package/skills/ae-engage/references/config-item-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +config_item_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query config item details.
 

package/skills/ae-engage/references/config-item-list.md

@@ -1,6 +1,5 @@
 # ae-engage +config_item_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the list of config items in a project.
 

package/skills/ae-engage/references/config-item-strategy-comparison.md

@@ -1,6 +1,5 @@
 # ae-engage +config_item_strategy_comparison
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Compare multiple strategies under the same config item.
 

package/skills/ae-engage/references/config-item-trigger-report.md

@@ -1,6 +1,5 @@
 # ae-engage +config_item_trigger_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the publish and trigger trend report for a config item.
 

package/skills/ae-engage/references/copy-config-template.md

@@ -1,6 +1,5 @@
 # ae-engage +copy_config_template
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Copy a template from the source config item to the target config item.
 

package/skills/ae-engage/references/delete-channel.md

@@ -1,6 +1,5 @@
 # ae-engage +delete_channel
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Delete an Engage channel.
 

package/skills/ae-engage/references/delete-config-channel.md

@@ -1,6 +1,5 @@
 # ae-engage +delete_config_channel
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Delete a config channel.
 

package/skills/ae-engage/references/delete-config-item.md

@@ -1,6 +1,5 @@
 # ae-engage +delete_config_item
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Delete a config item.
 

package/skills/ae-engage/references/delete-flow.md

@@ -1,6 +1,5 @@
 # ae-engage +delete_flow
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Batch delete flows.
 

package/skills/ae-engage/references/flow-ab-split-node-report.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_ab_split_node_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the AB split node report.
 

package/skills/ae-engage/references/flow-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query flow details.
 

package/skills/ae-engage/references/flow-list.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the flow list.
 

package/skills/ae-engage/references/flow-node-config-schema.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_node_config_schema
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the configuration schema for a flow node type.
 

package/skills/ae-engage/references/flow-node-detail-report.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_node_detail_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the detailed report for a single flow node.
 

package/skills/ae-engage/references/flow-node-overview-report.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_node_overview_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the overview report for all nodes in a flow.
 

package/skills/ae-engage/references/flow-process-report.md

@@ -1,6 +1,5 @@
 # ae-engage +flow_process_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the process-level report for a flow.
 

package/skills/ae-engage/references/manage-flow.md

@@ -1,6 +1,5 @@
 # ae-engage +manage_flow
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Batch manage flow status or review actions.
 

package/skills/ae-engage/references/manage-strategy.md

@@ -1,6 +1,5 @@
 # ae-engage +manage_strategy
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Batch manage strategy status or review actions.
 

package/skills/ae-engage/references/manage-task.md

@@ -1,6 +1,5 @@
 # ae-engage +manage_task
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Perform task lifecycle actions such as send, pause, end, or review.
 

package/skills/ae-engage/references/modify-flow-base-info.md

@@ -1,6 +1,5 @@
 # ae-engage +modify_flow_base_info
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Modify the basic information of a flow canvas.
 

package/skills/ae-engage/references/strategy-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +strategy_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the details of a single strategy.
 

package/skills/ae-engage/references/strategy-list.md

@@ -1,6 +1,5 @@
 # ae-engage +strategy_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the strategy list.
 

package/skills/ae-engage/references/task-data-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +task_data_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the task detailed data report.
 

package/skills/ae-engage/references/task-data-overview.md

@@ -1,6 +1,5 @@
 # ae-engage +task_data_overview
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the funnel-style task data overview.
 

package/skills/ae-engage/references/task-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +task_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the details of a single task.
 

package/skills/ae-engage/references/task-experiment-report.md

@@ -1,6 +1,5 @@
 # ae-engage +task_experiment_report
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the task experiment report.
 

package/skills/ae-engage/references/task-list.md

@@ -1,6 +1,5 @@
 # ae-engage +task_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the paginated task list.
 

package/skills/ae-engage/references/task-metric-detail.md

@@ -1,6 +1,5 @@
 # ae-engage +task_metric_detail
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the metric-oriented detail report for a task.
 

package/skills/ae-engage/references/task-stats.md

@@ -1,6 +1,5 @@
 # ae-engage +task_stats
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query task status statistics.
 

package/skills/ae-engage/references/update-channel-status.md

@@ -1,6 +1,5 @@
 # ae-engage +update_channel_status
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Update the status of an Engage channel.
 

package/skills/ae-engage/references/update-config-channel-status.md

@@ -1,6 +1,5 @@
 # ae-engage +update_config_channel_status
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Update the status of a config channel.
 

package/skills/ae-engage/references/validate-flow-node-config.md

@@ -1,6 +1,5 @@
 # ae-engage +validate_flow_node_config
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Validate a single node configuration before saving a flow.
 

package/skills/ae-engage/references/whitelist-list.md

@@ -1,6 +1,5 @@
 # ae-engage +whitelist_list
 
-> **Prerequisite:** Read [`../../ae-shared/SKILL.md`](../../ae-shared/SKILL.md)
 
 Query the whitelist list in a project.
 

package/skills/ae-kb/SKILL.md

@@ -20,6 +20,7 @@ ae-cli kb +<command> [options]
 - Do not invent knowledge base names, scopes, source display names, or JSON payloads. Ask the user or query known context when values are missing.
 - JSON flags must be valid JSON strings, usually wrapped in single quotes in shell commands.
 - Successful commands return JSON by default. Use `--format table` only when a table is easier for a human to scan.
+- `--host <url>` overrides the active AE host. It is available on every command and may be placed after the subcommand, e.g. `ae-cli kb +<command> --host <url>`.
 - For external-agent retrieval, prefer the deterministic flow `+index` -> `+grep` -> `+read`: inspect navigation, locate candidate pages, then open the exact page or line window.
 
 ## Commands

package/skills/ae-team/SKILL.md

@@ -20,7 +20,7 @@ Global parameters:
 |---|---|
 | `--format <json\|table>` | Output format. Default is JSON. |
 | `--jq <expr>` | jq filter expression for JSON output. |
-| `--host <url>` | Override active AE host URL. |
+| `--host <url>` | Override the active AE host. Available on every command and may be placed after the subcommand, e.g. `ae-cli team +<command> --host <url>`. |
 | `--yes` | Skip confirmation for write operations. |
 | `--dry-run` | Show request details without executing. |