@thinkingai/ae-cli 1.0.1

package/skills/te-audience/references/list-clusters.md

@@ -0,0 +1,32 @@
+# te_audience +list_clusters (Cluster Search)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Cluster Management**
+
+## Use Cases
+- List cluster metadata accessible to the current user in the project. Supports keyword filtering and returns cluster names, display names, types, status, user counts, and related metadata, but not cluster members.
+
+## Commands
+```bash
+te-cli te_audience +list_clusters --project_id 1
+te-cli te_audience +list_clusters --project_id 1 --query demo
+te-cli te_audience +list_clusters --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against cluster names, display names, and remarks; if omitted, all clusters are returned. |
+
+## Decision Rules
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`) and add optional parameters after confirming the path works.
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`).
+- If the result is empty, first confirm the project ID/keyword, then try broadening the filter conditions.
+
+## Recommended Chain
+- +list_clusters -> +get_clusters_by_name -> +update_cluster

package/skills/te-audience/references/list-tag-members.md

@@ -0,0 +1,36 @@
+# te_audience +list_tag_members (View Tag Members)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Tag Management**
+
+## Use Cases
+- List members in the specified tag. Returns member information such as user property values and total user count for the selected snapshot date.
+
+## Commands
+```bash
+te-cli te_audience +list_tag_members --project_id 1 --tag_name demo
+te-cli te_audience +list_tag_members --project_id 1 --tag_name demo --snapshot_date 2026-04-01 --property_names '["#user_id","name"]' --use_cache false
+te-cli te_audience +list_tag_members --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--tag_name` | Yes | Tag name |
+| `--snapshot_date` | No | Optional tag snapshot date. Format: YYYY-MM-DD |
+| `--property_names` | No | Optional list of user property names (JSON array) |
+| `--use_cache` | No | Whether to use cache. Default: true |
+
+## Decision Rules
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--tag_name`) and add optional parameters after confirming the path works.
+- `--property_names` must be passed as a JSON array (e.g. `--property_names '["#user_id"]'`).
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--tag_name`).
+- If the result is empty, first confirm the project ID/keyword, then try broadening the filter conditions.
+
+## Recommended Chain
+- +list_tags -> +get_tags_by_name -> +update_tag

package/skills/te-audience/references/list-tags.md

@@ -0,0 +1,32 @@
+# te_audience +list_tags (Tag Search)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Tag Management**
+
+## Use Cases
+- List tag metadata accessible to the current user in the project. Supports keyword filtering and returns tag names, display names, types, status, user counts, and related metadata, but not tag members.
+
+## Commands
+```bash
+te-cli te_audience +list_tags --project_id 1
+te-cli te_audience +list_tags --project_id 1 --query demo
+te-cli te_audience +list_tags --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--query` / `-q` | No | Optional keyword filter. Performs fuzzy matching against tag names, display names, and remarks; if omitted, all tags are returned. |
+
+## Decision Rules
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`) and add optional parameters after confirming the path works.
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`).
+- If the result is empty, first confirm the project ID/keyword, then try broadening the filter conditions.
+
+## Recommended Chain
+- +list_tags -> +get_tags_by_name -> +update_tag

package/skills/te-audience/references/refresh-cluster.md

@@ -0,0 +1,31 @@
+# te_audience +refresh_cluster (Trigger Cluster Recompute)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Cluster Management**
+
+## Use Cases
+- Trigger cluster recomputation and submit an asynchronous refresh task.
+
+## Commands
+```bash
+te-cli te_audience +refresh_cluster --project_id 1 --cluster_name demo
+te-cli te_audience +refresh_cluster --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--cluster_name` | Yes | Cluster name |
+
+## 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.
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+- Write operations keep confirmation prompts by default; for automation scenarios, reevaluate whether to use `--yes`.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--cluster_name`).
+
+## Recommended Chain
+- +list_clusters -> +get_clusters_by_name -> +update_cluster

package/skills/te-audience/references/refresh-tag.md

@@ -0,0 +1,31 @@
+# te_audience +refresh_tag (Trigger Tag Recompute)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Tag Management**
+
+## Use Cases
+- Trigger tag recomputation and submit an asynchronous refresh task.
+
+## Commands
+```bash
+te-cli te_audience +refresh_tag --project_id 1 --tag_name demo
+te-cli te_audience +refresh_tag --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--tag_name` | Yes | Tag name |
+
+## Decision Rules
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--tag_name`) and add optional parameters after confirming the path works.
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+- Write operations keep confirmation prompts by default; for automation scenarios, reevaluate whether to use `--yes`.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--tag_name`).
+
+## Recommended Chain
+- +list_tags -> +get_tags_by_name -> +update_tag

package/skills/te-audience/references/update-cluster.md

@@ -0,0 +1,59 @@
+# te_audience +update_cluster (Update Cluster)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Cluster Management**
+
+## Use Cases
+- Prerequisite helper: first call `+get_cluster_definition_schema` to get the structure, then supplement it with the project's real metadata (events and properties).
+- Update a user cluster definition. Supports updating the display name, remark, type, or definition. Updating only the display name or remark does not trigger recomputation.
+
+## Required Prerequisites (MUST only when updating definition)
+- If this request includes `--definition`, you must first read and follow these reference docs:
+  - [`./get-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 submit a new `definition` until the above docs have been read and the prerequisite commands have been run.
+
+## Prerequisite Call Chain (run only when updating definition)
+1. First determine `--type` (condition / sql).
+2. Read `get-cluster-definition-schema.md`, then call `te-cli te_audience +get_cluster_definition_schema --cluster_type <condition|sql>` to obtain the structure.
+3. Read `list-events.md`, then call `te-cli te_meta +list_events --project_id 1`.
+4. Read `list-properties.md`, then call `te-cli te_meta +list_properties --project_id 1`.
+5. Build the new `definition` based on the schema + metadata, then run `+update_cluster`.
+
+## Commands
+```bash
+te-cli te_audience +update_cluster --project_id 1 --cluster_name demo --display_name "Demo v2"
+te-cli te_audience +update_cluster --project_id 1 --cluster_name demo --type condition --definition '{}' --zone_offset 8
+te-cli te_audience +update_cluster --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--cluster_name` | Yes | Cluster name |
+| `--display_name` | No | New cluster display name. Length: 1-80 |
+| `--remark` | No | New cluster remark |
+| `--type` | No | New cluster type. Supported values: condition and sql. It is recommended to provide this when updating the definition. |
+| `--definition` | No | New cluster definition JSON. If provided, MUST call `+get_cluster_definition_schema` first, then fill valid event/property names from `te_meta` metadata commands in the same `project_id`. |
+| `--zone_offset` | No | Optional time zone offset for cluster computation. Valid range: -12 to 14 (supports decimals like 5.5). |
+
+## Decision Rules
+- If you are not updating `definition` (only updating `display_name`/`remark`), you can skip the schema and metadata prerequisite chain.
+- When updating `definition`, it cannot be written from experience alone; it must satisfy both the schema structure and the project's real metadata.
+- Before calling `list_events` / `list_properties`, you must first read the corresponding reference docs.
+- 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.
+- Wrap JSON parameters in single quotes (e.g. `--definition '{}'`) to avoid shell escaping issues.
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+- Write operations keep confirmation prompts by default; for automation scenarios, reevaluate whether to use `--yes`.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--cluster_name`).
+- If `Invalid JSON` appears, first check whether a schema-required field is missing, then verify whether event/property names come from the same `project_id`'s metadata query results.
+- If the result after writing is not as expected, immediately re-read the corresponding list/get interfaces and compare before and after.
+
+## Recommended Chain
+- +get_cluster_definition_schema -> te_meta +list_events -> te_meta +list_properties -> +update_cluster
+- +list_clusters -> +get_clusters_by_name -> +update_cluster

package/skills/te-audience/references/update-tag.md

@@ -0,0 +1,60 @@
+# te_audience +update_tag (Update Tag)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **Tag Management**
+
+## Use Cases
+- Prerequisite helper: first call `+get_tag_definition_schema` to get the structure, then call this tool.
+- When updating `definition`, you must first supplement it with real project metadata; at minimum, first call `te_meta +list_events` and `te_meta +list_properties`.
+- Update a user tag definition. Supports updating the display name, remark, type, and tag definition. Updating only the display name or remark does not trigger recomputation.
+
+## Required Prerequisites (MUST only when updating definition)
+- If this request includes `--definition`, you must first read and follow these reference docs:
+  - [`./get-tag-definition-schema.md`](./get-tag-definition-schema.md)
+  - [`../../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 submit a new `definition` until the above docs have been read and the prerequisite commands have been run.
+
+## Prerequisite Call Chain (run only when updating definition)
+1. First determine `--type` (condition / metric / first_last / sql).
+2. Read `get-tag-definition-schema.md`, then call `te-cli te_audience +get_tag_definition_schema` to obtain the structure.
+3. Read `list-events.md`, then call `te-cli te_meta +list_events --project_id 1`.
+4. Read `list-properties.md`, then call `te-cli te_meta +list_properties --project_id 1`.
+5. Build the new `definition` based on the schema + metadata, then run `+update_tag`.
+
+## Commands
+```bash
+te-cli te_audience +update_tag --project_id 1 --tag_name demo --display_name "Demo v2"
+te-cli te_audience +update_tag --project_id 1 --tag_name demo --type condition --definition '{}' --zone_offset 8
+te-cli te_audience +update_tag --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--tag_name` | Yes | Tag name |
+| `--display_name` | No | New tag display name. Length: 1-80 |
+| `--remark` | No | New tag remark |
+| `--type` | No | New tag type. Supported values: condition, metric, first_last, sql |
+| `--definition` | No | New tag definition JSON. If provided, MUST call `+get_tag_definition_schema` first, then fill valid event/property names from `te_meta` metadata commands in the same `project_id`. |
+| `--zone_offset` | No | Optional time zone offset for tag computation. Valid range: -12 to 14 (supports decimals like 5.5). |
+
+## Decision Rules
+- If you are not updating `definition` (only updating `display_name`/`remark`), you can skip the schema and metadata prerequisite chain.
+- When updating `definition`, it cannot be written from experience alone; it must satisfy both the schema structure and the project's real metadata.
+- Before calling `list_events` / `list_properties`, you must first read the corresponding reference docs.
+- For the first execution, it is recommended to pass only the required parameters (`--project_id`, `--tag_name`) and add optional parameters after confirming the path works.
+- Wrap JSON parameters in single quotes (e.g. `--definition '{}'`) to avoid shell escaping issues.
+- When troubleshooting across projects, first confirm whether `--project_id` matches the current permissions and target environment.
+- Write operations keep confirmation prompts by default; for automation scenarios, reevaluate whether to use `--yes`.
+
+## Next Step on Failure
+- If required parameters are missing, fall back to the smallest runnable command and fill the gap (focus on `--project_id`, `--tag_name`).
+- If `Invalid JSON` appears, first check whether a schema-required field is missing, then verify whether event/property names come from the same `project_id`'s metadata query results.
+- If the result after writing is not as expected, immediately re-read the corresponding list/get interfaces and compare before and after.
+
+## Recommended Chain
+- +get_tag_definition_schema -> te_meta +list_events -> te_meta +list_properties -> +update_tag
+- +list_tags -> +get_tags_by_name -> +update_tag

package/skills/te-common/SKILL.md

@@ -0,0 +1,135 @@
+---
+name: te-common
+version: 1.0.0
+description: "TE cross-module common constraints: define the post-write flow after create/update operations (resource link completion, output conventions, failure fallback). Triggered when requirements involve shared rules across te-analysis/te-meta/te-audience."
+metadata:
+  requires:
+    bins: ["te-cli"]
+---
+
+# te-common
+
+> **CRITICAL - Before starting, MUST first read [`../te-shared/SKILL.md`](../te-shared/SKILL.md)**: authentication, host configuration, global parameters, and write-operation confirmation rules are all in there.
+> **CRITICAL - Before executing any `+<tool_name>` command, MUST first read the corresponding reference document `./references/<tool-name>.md`** For example: before executing `+get_resource_url`, you must first read [`./references/get-resource-url.md`](./references/get-resource-url.md)
+
+## When to Use
+
+When the requirement belongs to the unified execution constraints across `te-analysis` / `te-meta` / `te-audience`, you must use `te-common` first:
+
+- Post-write actions, such as resource link completion
+- Unified output conventions and fallback policies
+- Future cross-module common constraints
+
+## Execution Sequence (AI Agent Must Follow)
+
+```
+[Start] → [Read command reference document] → [Execute write operation] → [Succeeded?]
+                                          ↓ Yes
+                              [Pause immediately, review the "write-operation post-link completion" section of this document]
+                                          ↓
+                              [Call +get_resource_url]
+                                          ↓
+                              [Output complete result + link]
+                                          ↓
+                                      [End]
+```
+
+**Key point**: after a write operation succeeds → immediately go back to te-common, do not skip it.
+
+---
+
+## Current Mandatory Constraints (MUST)
+
+### A. PROJECT_ID_GATE (preflight gate, no guessing)
+
+- For any command about to be executed, you must first confirm whether that command requires `project_id` (per the corresponding `references/<tool-name>.md` document).
+- **Regardless of whether the user provided a project name or project_id, you must first call `+list_projects` to retrieve the project list for verification.**
+- Verification rules:
+  - If the user provided a number, you must find the matching project_id in the list
+  - If the user provided a name, you must find the matching project name in the list and obtain the corresponding project_id
+  - If no match is found, you must tell the user and show the available project list so they can choose again
+- Before verification passes and the correct `project_id` is confirmed, do not call the target command.
+
+Recommended interaction flow:
+
+**Scenario 1: The user did not provide project information**
+```text
+This step requires project_id.
+I will first list the available projects for you to choose from:
+
+[Call +list_projects to display the project list]
+
+Please choose one from the projects above (for example, reply with the project ID or the project name).
+I will not execute the target command before you confirm.
+```
+
+**Scenario 2: The user provided a project name or ID**
+```text
+The project you mentioned is "xxx".
+I will first verify whether this project exists:
+
+[Call +list_projects to get the project list]
+
+Verification result:
+- ✅ Project "xxx" exists, project_id = 123
+- Or ❌ Project "xxx" was not found, available projects are listed below: [display list]
+
+Please confirm whether to use this project (project_id = 123) for the next operation.
+```
+
+### B. Write-operation post-link completion (mandatory closed loop)
+
+**Trigger condition**: When any of the following commands succeeds, MUST enter the link completion flow:
+
+| resource_type | Create command | Update command |
+|---|---|---|
+| `dashboard` | `+create_dashboard` | `+update_dashboard` |
+| `report` | `+create_report` | - |
+| `metric` | `+create_metric` | `+update_metric` |
+| `alert` | `+create_alert` | `+update_alert` |
+| `tag` | `+create_tag` | `+update_tag` |
+| `cluster` | `+create_cluster`, `+create_result_cluster` | `+update_cluster` |
+| `virtual_event` | `+create_virtual_event` | - |
+| `event_virtual_prop` | `+create_virtual_property` (`--table_type event`) | - |
+| `user_virtual_prop` | `+create_virtual_property` (`--table_type user`) | - |
+| `super_event` | `+batch_create_metadata` (creating events) | `+batch_edit_metadata --type event` |
+| `super_prop_event` | `+batch_create_metadata` (creating event_properties) | `+batch_edit_metadata --type event_property` |
+| `super_prop_user` | `+batch_create_metadata` (creating user_properties) | `+batch_edit_metadata --type user_property` |
+
+**Closed loop execution (must be completed)**:
+1. ✅ Write operation succeeded → immediately check whether the return value contains `resource_id`
+2. ✅ Has `resource_id` → call `+get_resource_url` (using the verified `project_id`)
+3. ✅ Link generated successfully → output the complete response including the clickable link
+4. ⚠️ Link generation failed → output the main result + explicitly state "link completion failed: [reason]"
+
+**Multi-resource result handling (for batch metadata only)**:
+- `+batch_create_metadata` / `+batch_edit_metadata` may return multiple resources at once (events/properties).
+- For each resource from which `resource_id` can be extracted, you must call `+get_resource_url` separately.
+- The final output must provide links for each resource one by one; if some fail, mark the failed items and the reasons, while the successful items are returned normally.
+
+**Prohibited behaviors**:
+- ❌ End the response immediately after a write operation succeeds (you must complete link completion or explain the failure)
+- ❌ Treat a write operation as failed because link completion failed (the write result is independently valid)
+
+**Closed-loop check template** (must explicitly confirm each step):
+```
+[Write operation result]
+→ Check resource_id: [yes/no]
+→ Call get_resource_url: [called / skipped (no ID)]
+→ Link completion status: [successful link / failure reason / skipped]
+→ Closed loop complete ✅
+```
+
+If the ID cannot be extracted or link generation fails, you must explain the failure reason, but you cannot roll back or judge the main write operation as failed.
+
+## Execution Template
+
+1. Execute the main write-operation command.
+2. Extract `project_id`, `resource_type`, `resource_id` from the input or return value.
+3. Call `te-cli te_common +get_resource_url --project_id <id> --resource_type <type> --resource_id <id>`.
+4. Output the main result + `markdown_link` (clickable) / `raw_url`.
+
+## Unified Command Entry
+
+- `+list_projects` ([documentation](./references/list-projects.md))
+- `+get_resource_url` ([documentation](./references/get-resource-url.md))

package/skills/te-common/references/get-resource-url.md

@@ -0,0 +1,32 @@
+# te-common resource link completion (call te_common +get_resource_url)
+
+> **Prerequisite:** Read [`../../te-shared/SKILL.md`](../../te-shared/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.
+- 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`.
+
+## Mandatory Rules (MUST)
+- As long as `project_id + resource_type + resource_id` can be determined, this command must be called.
+- The final response must output `markdown_link` directly (do not place it in a code block) so the user can click through.
+- If resource link generation fails, keep the main write-operation success conclusion and add the failure reason.
+
+## Command
+```bash
+te-cli te_common +get_resource_url --project_id 1 --resource_type dashboard --resource_id 1
+te-cli te_common +get_resource_url --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--project_id` / `-p` | Yes | Project ID |
+| `--resource_type` | Yes | Resource type: dashboard/report/metric/alert/tag/cluster/data_table/super_event/super_prop_user/super_prop_event/virtual_event/user_virtual_prop/event_virtual_prop |
+| `--resource_id` | Yes | Numeric resource ID |
+
+## Recommended Chaining
+- `+create_*` -> `te_common +get_resource_url`
+- `+update_*` -> `te_common +get_resource_url`

package/skills/te-common/references/list-projects.md

@@ -0,0 +1,37 @@
+# te_common +list_projects (view projects accessible to the current user)
+
+> **Prerequisite:** Read [`../te-shared/SKILL.md`](../../te-shared/SKILL.md)
+
+Domain: **project discovery / cross-module pre-query**
+
+## Use Cases
+- List all projects accessible to the current user. No parameters are required.
+- Returns a list of project summaries; key fields include: `projectId`, `projectName`, `companyId`, `projectType`, `remark`, `appId`, `roleName`.
+
+## Mandatory Rules (MUST)
+- This command does not accept any business parameters; do not invent `project_id`, keywords, or pagination parameters.
+- If a later target command requires `project_id`, `+list_projects` may only be used for "candidate project discovery" and cannot replace user confirmation.
+- In the final response, prioritize the returned `projectId`, `projectName`, and `roleName` to help the user confirm the project.
+
+## Command
+```bash
+te-cli te_common +list_projects
+te-cli te_common +list_projects --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| None | - | No business parameters required |
+
+## Decision Rules
+- When the user says "let me see what projects I have", "list the available projects first", or "I don't know project_id", call this command first.
+- When you need to continue with a command that depends on `project_id`, show candidate projects first, then ask the user to explicitly confirm the target `projectId`.
+- If there are many projects returned, prioritize summarizing by `projectName`, `projectId`, and `roleName` to avoid expanding all low-value fields at once.
+
+## Next Step on Failure
+- If the result is empty, first confirm whether the current account, environment, and permissions are correct.
+- If the call fails, first check the authentication status, the target environment host, and the current login identity.
+
+## Recommended Chaining
+- `+list_projects` -> user confirms `project_id` -> any command that requires `project_id`

package/skills/te-community/SKILL.md

@@ -0,0 +1,133 @@
+---
+name: te-community
+version: 1.0.0
+description: "TE 社区分析：帖子搜索、评论情感、话题趋势、风险内容、直播数据"
+metadata:
+  requires:
+    bins: ["te-cli"]
+  cliHelp: "te-cli community --help"
+---
+
+# te-community
+
+> **前置条件:** 阅读 [`../te-shared/SKILL.md`](../te-shared/SKILL.md) 了解认证、全局参数和安全约束。
+
+## 概述
+
+`te-community` 域提供社区社交媒体数据分析能力，包括帖子搜索、评论情感分析、话题趋势、风险内容监控和直播数据。
+
+命令通过 `te-cli community <command>` 调用。**本文件以导航为主**：具体用法、示例与 Flags 见下方 **`references/`** 与各复合分析 reference。
+
+## 通用参数
+
+| 参数 | 说明 |
+|------|------|
+| `--space-id` | 社区空间 ID |
+| `--game-id` | 游戏/空间标识 |
+
+## 渠道 ID 前置：`get_channel_info`
+
+大量子命令依赖 **`--channel-id`** 或 **`--channel-id-list`**（例如帖子详情、评论摘要、直播会话列表、按渠道筛选的搜索等）。在只有 `space-id` / `game-id`、尚未知道渠道编号时，**建议先调用** `te-cli community get_channel_info` 拿到各渠道的 ID 与名称，再执行后续命令。详见 [get_channel_info](references/get_channel_info.md)。
+
+## 数组参数格式
+
+多值参数使用 **逗号分隔**：
+```
+--channel-id-list 1,2,3
+--keywords tag1,tag2
+--sentiment-types 0,1
+```
+
+## 日期格式
+
+所有日期参数使用 `yyyy-MM-dd` 格式，如 `--start-time 2024-01-01`。
+
+## 参考文档（子命令导航）
+
+按需打开对应文件即可查看说明与示例（单命令一页）：
+
+- 按关键词/时间段搜索帖子或视频：[search_posts](references/search_posts.md)
+- 已拿到 `post-id`，查看单条内容详情：[get_post_detail](references/get_post_detail.md)
+- 查询可用分析标签列表：[get_corpus_tags](references/get_corpus_tags.md)
+- 快速查看评论区整体情绪与摘要：[get_comments_summary](references/get_comments_summary.md)
+- 分析评论标签分布与占比：[get_comment_tag_analysis](references/get_comment_tag_analysis.md)
+- 查看情感走势（按时间段）：[get_sentiment_overview](references/get_sentiment_overview.md)
+- 查看社区大盘总览（发帖、互动等）：[get_overview_metrics](references/get_overview_metrics.md)
+- 识别当前热榜话题：[get_hot_topics](references/get_hot_topics.md)
+- 下钻查看某个话题详情：[get_topic_detail](references/get_topic_detail.md)
+- 观察特定标签的趋势变化：[get_tag_trends](references/get_tag_trends.md)
+- 生成/查看单日社区摘要（日报）：[get_daily_summary](references/get_daily_summary.md)
+- 排查风险内容与安全合规问题：[get_risk_content](references/get_risk_content.md)
+- 获取直播间列表并确定房间范围：[get_livestream_rooms](references/get_livestream_rooms.md)
+- 查看直播间历史会话列表：[get_livestream_list](references/get_livestream_list.md)
+- 查看某场直播会话明细：[get_livestream_detail](references/get_livestream_detail.md)
+- 直播场次 AI 分析报告（亮点切片与情感观点）：[get_livestream_analysis](references/get_livestream_analysis.md)
+- 查看直播模块在时间段内的整体表现：[get_livestream_overview](references/get_livestream_overview.md)
+- 查看单直播间年度指标：[get_livestream_room_metrics](references/get_livestream_room_metrics.md)
+- 获取渠道列表与渠道基础信息：[get_channel_info](references/get_channel_info.md)
+
+## 高级分析技能
+
+以下技能基于 MCP 工具链组合调用，用于生成结构化的深度分析报告。
+
+### community-activity-analysis（活动专项运营洞察分析）
+
+深度评估游戏内活动或营销事件的曝光效果、社区口碑、二创生态及长尾影响。
+
+详见：[`references/community-activity-analysis.md`](references/community-activity-analysis.md)
+
+---
+
+### community-daily-report（每日快报）
+
+生成单日大盘、突发舆情与安全合规风控的短平快《用户运营每日快报》，支持环比对比（T-1 与 T-2）。
+
+详见：[`references/community-daily-report.md`](references/community-daily-report.md)
+
+---
+
+### community-character-analysis（角色专项深度分析）
+
+深度剖析特定游戏角色的社区生态、玩家情感动因、核心诉求。
+
+详见：[`references/community-character-analysis.md`](references/community-character-analysis.md)
+
+---
+
+### community-hottopic-insight（话题分析报告）
+
+自动调用 MCP 工具收集语料，智能识别行业属性，输出包含核心摘要、舆情概览及事件脉络、核心热点讨论、情绪切片、社媒渠道洞察及运营建议的结构化《舆情分析》。
+
+详见：[`references/community-hottopic-insight.md`](references/community-hottopic-insight.md)
+
+---
+
+### community-release-analysis（版本运营分析复盘）
+
+提取整个版本周期内的大盘数据、热点榜单、舆情脉络与风控趋势，输出深度的《版本运营分析复盘报告》。
+
+详见：[`references/community-release-analysis.md`](references/community-release-analysis.md)
+
+---
+
+### community-weekly-report（社区运营周度总结）
+
+汇总统揽一周数据，重点基于"每日摘要"串联本周核心发酵事件，输出《社区运营周度总结报告》。
+
+详见：[`references/community-weekly-report.md`](references/community-weekly-report.md)
+
+---
+
+### community-analyzing-official-content（官方内容分析）
+
+分析指定游戏在社区模块中近期发布的官方内容，按照既定分类进行梳理和总结。
+
+详见：[`references/community-analyzing-official-content.md`](references/community-analyzing-official-content.md)
+
+---
+
+### community-analyzing-theme-comment（主题评论区深度分析）
+
+对指定帖子或视频的评论区进行深度分析，生成包含评论走势、观点分布和总结的深度分析报告。
+
+详见：[`references/community-analyzing-theme-comment.md`](references/community-analyzing-theme-comment.md)