@thinkingai/ae-cli 6.0.30 → 6.0.32

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

@@ -0,0 +1,69 @@
+# engage-scene config-item
+
+> Capability ids: `engage-scene.config-item.{list,create,update}` · Domain: `engage`.
+
+`config-item` 是配置中心（场景管理）里的配置项。create 走 multipart，可携带可选头像文件。
+
+## Commands
+
+```bash
+# List config items of a project
+ae-cli engage-scene config-item list --project-id <project_id>
+
+# Create a config item (business type, group, optional avatar)
+ae-cli engage-scene config-item create \
+  --project-id <project_id> --config-id <config_id> --config-name <name> \
+  --business-type <config_file|params> \
+  [--config-remark <remark>] [--group-id <group_id>] \
+  [--avatar-word '["A","B"]'] [--file-name avatar.png] [--file-content "$(base64 -i avatar.png)"]
+
+# Update a config item's basic info and bound channel
+ae-cli engage-scene config-item update \
+  --project-id <project_id> --config-id <config_id> \
+  [--config-name <name>] [--config-remark <remark>] [--business-type <type>] \
+  [--group-id <group_id>] [--channel-id <channel_id>]
+```
+
+## Parameters
+
+### list
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+
+### create
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID (unique within the project). |
+| `--config-name` | Yes | Config item display name (<=80 chars). |
+| `--business-type` | Yes | Business type: `config_file` or `params`. |
+| `--config-remark` | No | Remark (<=200 chars). |
+| `--group-id` | No | Group ID (0 = default group). |
+| `--avatar-word` | No | JSON array of avatar words for the icon. |
+| `--file-name` | No | Avatar file name incl. extension. |
+| `--file-content` | No | Base64-encoded avatar file content. |
+
+### update
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID to update. |
+| `--config-name` | No | New display name. |
+| `--config-remark` | No | New remark. |
+| `--business-type` | No | New business type. |
+| `--group-id` | No | New group ID. |
+| `--channel-id` | No | Config channel ID to bind. |
+
+## Output
+
+- `list`: `data.items` + `data.total`.
+- `create` / `update`: `data.success` — whether the operation succeeded.
+
+## Decision Rules
+
+- `create` / `update` are `write`; `list` is read.
+- Use `config-item list` (or `engage +config_item_list`) to discover existing config items first; never invent IDs.

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

@@ -0,0 +1,13 @@
+# engage-task group list
+
+List task groups in a project.
+
+> Capability id: `engage-task.group.list` · Domain: `engage`.
+
+```bash
+ae-cli engage-task group list --project-id <project-id>
+```
+
+## Parameters
+
+- `--project-id` / `-p`: Numeric project ID.

package/skills/ae-engage/references/operation-log-query.md

@@ -0,0 +1,11 @@
+# engage-flow operation-log query
+
+Use this command to query aggregated operation records and application logs for a flow canvas.
+
+> Capability id: `engage-flow.operation-log.query` · Domain: `engage`.
+
+```bash
+ae-cli engage-flow operation-log query --project-id <project-id> --flow-id <flow-id>
+```
+
+The result contains `operation_record_list` and `app_log_list`, grouped by flow version.

package/skills/ae-engage/references/preset-event.md

@@ -0,0 +1,42 @@
+# engage-setting preset-event
+
+> Capability ids: `engage-setting.preset-event.{list,update}` · Domain: `engage`.
+
+## Commands
+
+```bash
+# Query the project preset-event config
+ae-cli engage-setting preset-event list --project-id <project_id>
+
+# Update the project preset-event config
+ae-cli engage-setting preset-event update --project-id <project_id> [--add-event-desc <qp>] [--active-event-desc <qp>] [--recharge-event-desc <qp>]
+```
+
+## Parameters
+
+### list
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+
+### update
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--add-event-desc` | No | Add-event qp definition. |
+| `--active-event-desc` | No | Active-event qp definition. |
+| `--recharge-event-desc` | No | Recharge-success-event qp definition. |
+
+At least one `*-event-desc` must be provided for `update`.
+
+## Output
+
+- `list`: `data.add_event_desc`, `data.active_event_desc`, `data.recharge_event_desc` (each may be `null`).
+- `update`: `data.success` — whether the config was updated.
+
+## Decision Rules
+
+- Use these commands when the user asks to query or configure preset events (预置事件) for the analysis workbench.
+- `update` replaces the provided desc fields; omitting a field clears it. Before clearing a field that is in use, the backend rejects the update if metrics still depend on it.

package/skills/ae-engage/references/push-language.md

@@ -0,0 +1,39 @@
+# engage-setting push-language
+
+> Capability ids: `engage-setting.push-language.{get,set}` · Domain: `engage`.
+
+## Commands
+
+```bash
+# Query the project push-language property field
+ae-cli engage-setting push-language get --project-id <project_id>
+
+# Set the project push-language property field
+ae-cli engage-setting push-language set --project-id <project_id> --push-language-column <prop_code>
+```
+
+## Parameters
+
+### get
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+
+### set
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--push-language-column` | Yes | User property code used as the push language field. |
+
+## Output
+
+- `get`: `data.push_language_column` — configured push-language property code, or `null` if unset.
+- `set`: `data.success` — whether the field was updated.
+
+## Decision Rules
+
+- Use these commands when the user asks to query or configure the project push-language (本地化) property field.
+- `--push-language-column` must be a real user property code; discover available properties via the analysis metadata commands first.
+- `set` is `write`; ordinary update, no confirmation gate.

package/skills/ae-engage/references/push-record-query.md

@@ -0,0 +1,26 @@
+# engage-task push-record query
+
+Query delivery and push records for an engagement task. Hermes automatically selects scheduled, user-time-zone, or triggered record data based on the task configuration.
+
+> Capability id: `engage-task.push-record.query` · Domain: `engage`.
+
+```bash
+ae-cli engage-task push-record query \
+  --project-id <project-id> \
+  --task-id <task-id> \
+  --page-num 1 \
+  --page-size 20
+```
+
+## Parameters
+
+- `--project-id`, `-p`: Numeric project ID.
+- `--task-id`: Engagement task ID.
+- `--page-num`: Optional page number for scheduled tasks. Defaults to `1`.
+- `--page-size`: Optional page size for scheduled tasks. Defaults to `20`.
+- `--start-date`: Optional start date in `yyyy-MM-dd` format. Must not be after `--end-date`.
+- `--end-date`: Optional end date in `yyyy-MM-dd` format. Must not be before `--start-date`.
+
+## Output
+
+Returns `record_type`, `items`, `total`, and pagination metadata when the selected backend record type is paginated. Records include available trigger, planned-send, actual-send, success, channel-exception, status, and failure-reason fields.

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

@@ -33,7 +33,7 @@ You still organize user requirements into an intermediate intent first, then map
 ## 2. Workflow
 
 1. Identify the flow intent from the user input and produce a unified intent JSON.
-2. Run `ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition` to obtain the condition cluster definition schema for assembling condition-related fields later.
+2. Build a semantic condition request from `ae-analysis/references/user_cluster_models.md`, create the audience directly with `analysis user-cluster create`, and prefer its `cluster_name`/`clusterKey`. Read the saved server-authored definition with `analysis user-cluster get` only when an Engage node schema explicitly requires QP-derived fields; never assemble raw QP.
 3. Run `ae-cli engage +channel_list --project_id <projectId>` to get the available channels and match real `channelId` values for touchpoint nodes. For `webhook_push`, also run `ae-cli engage +channel_detail` and use `data.config.paramsList` to build `contentList`.
 4. Query `ae-cli engage +flow_node_config_schema --node_type <type>` before constructing each non-trivial node config, then run `ae-cli engage +validate_flow_node_config --node_type <type> --operation_mode save_flow --config '<config-json-string>'` before placing the config into `nodes` or `nodeConfigs`.
 5. Map the intent JSON to `nodes` and `edges` (compact form, see §7 / §8).
@@ -167,13 +167,14 @@ Organize the user requirement into an intermediate intent JSON (not the final `r
 
 ## 5. Step Two: Required CLI Queries
 
-### 5.1 Cluster Definition Schema
+### 5.1 Semantic Audience
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster create --project-id <projectId> --cluster-name <condition_cluster_name> --display-name <display_name> --definition-request '<semantic-definition-json>'
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
-Provides the basis for `targetClusterQp` and `triggerRule.events`.
+Prefer the created cluster reference. Only when the node schema requires `targetClusterQp` or `triggerRule.events`, copy the corresponding server-authored fields returned by `user-cluster get`.
 
 ### 5.2 Project Channels
 

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

@@ -10,16 +10,17 @@ Recommended workflow:
 
 1. `ae-cli engage +channel_list --project_id <projectId>`
 2. `ae-cli engage +build_task_save_guide --project_id <projectId> --req '{...}'`
-3. If the guide indicates QP-derived fields are needed, call:
+3. If the guide indicates an audience or QP-derived fields are needed, create the audience directly and read it back:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster create --project-id <projectId> --cluster-name <condition_cluster_name> --display-name <display_name> --definition-request '<semantic-definition-json>'
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
 4. Build the final grouped `req`
 5. `ae-cli engage +save_task --project_id <projectId> --req '{...}'`
 
-The audience schema query is not a fixed preflight step. Call it only when the guide indicates that you must construct:
+Audience creation is not a fixed preflight step. Use direct create/get only when the guide indicates that you must construct:
 
 - `targetConfig.qp`
 - `triggerConfig.triggerRule`
@@ -98,22 +99,23 @@ Use the guide to determine:
 - current handoff template
 - whether the current payload is already close to submit-ready
 
-### 2.3 Query Audience Condition Schema Only When Needed
+### 2.3 Create and Read the Audience Only When Needed
 
-If the guide indicates that QP-derived fields are needed, run:
+If the guide indicates that an audience or QP-derived fields are needed, run:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster create --project-id <projectId> --cluster-name <condition_cluster_name> --display-name <display_name> --definition-request '<semantic-definition-json>'
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
-Use the returned schema to build:
+Prefer the returned `cluster_name`/`clusterKey`. Only when required, use the server-authored definition to build:
 
 - `targetConfig.qp`
 - `triggerConfig.triggerRule`
 - `clientConfig.clientQp`
 - `completionIndicatorDef.event`
 
-Do not call this command by default for every task. It is conditional, not mandatory.
+Do not create an audience by default for every task. It is conditional, not mandatory.
 
 ### 2.4 Build Final `req` and Save
 
@@ -191,10 +193,11 @@ Use the guide to decide which audience shape applies:
 - `targetClusterType=2`: existing cluster, requires `clusterKey`
 - `targetClusterType=3`: all users, forbids both `qp` and `clusterKey`
 
-If `qp` is required, construct it from:
+If `qp` is required, create/read a server-authored audience and copy the saved definition rather than building raw QP:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster create --project-id <projectId> --cluster-name <condition_cluster_name> --display-name <display_name> --definition-request '<semantic-definition-json>'
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
 ### 4.4 `triggerConfig`
@@ -210,10 +213,10 @@ Rules:
 
 - `triggerType=6` is not supported
 - use the guide for cron format and wrong-example checks
-- if `triggerRule` is needed, build it from:
+- if `triggerRule` is needed, copy it from the saved server-authored audience definition:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
 ### 4.5 `controlConfig`
@@ -222,10 +225,10 @@ Minimum required field:
 
 - `completionIndicatorDef`
 
-When the guide points to event-based completion or experiment-driven main-goal rules, use:
+When the guide points to event-based completion or experiment-driven main-goal rules, use the saved server-authored audience definition:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
 to build `completionIndicatorDef.event`.
@@ -243,10 +246,10 @@ Important constraints that still apply:
 
 Use this block only when client-side conditions are needed.
 
-If `clientConfig.clientQp` is required, build it from:
+If `clientConfig.clientQp` is required, copy it from the saved server-authored audience definition:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
 Only call that schema query when the guide explicitly shows that the field is needed.
@@ -260,7 +263,7 @@ Before submission, verify:
 1. `channelId` comes from a real channel query.
 2. `build_task_save_guide` has already been called for the current scenario or partial draft.
 3. `fieldRules.channelContentSchema` was used as the source of truth for content structure.
-4. Any required QP-derived fields were built from `ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition`.
+4. Any required QP-derived fields came from `analysis user-cluster get`, never from hand-built raw QP.
 5. `targetClusterType` matches the presence or absence of `clusterKey` / `qp`.
 6. `triggerType` matches the provided scheduling or event fields.
 7. `completionIndicatorDef` is present and structurally valid for the current scenario.
@@ -280,10 +283,11 @@ ae-cli engage +build_task_save_guide --project_id 1 --req '{"context":{"triggerT
 ae-cli engage +save_task --project_id 1 --req '{...final grouped req...}'
 ```
 
-If the guide indicates QP-derived fields are needed, insert:
+If the guide indicates an audience or QP-derived fields are needed, insert direct create/get:
 
 ```bash
-ae-cli analysis_audience +get_cluster_definition_schema --cluster_type condition
+ae-cli analysis user-cluster create --project-id <projectId> --cluster-name <condition_cluster_name> --display-name <display_name> --definition-request '<semantic-definition-json>'
+ae-cli analysis user-cluster get --project-id <projectId> --cluster-names '["<condition_cluster_name>"]'
 ```
 
 before building the final `req`.
@@ -301,4 +305,4 @@ This command is a write operation.
 - Do not invent `channelId`, `clusterKey`, audience definitions, or content keys
 - Do not use `taskId` for a non-draft task
 - Do not pass `occasionKeys`; Hermes derives them from content
-- Do not call the audience schema query as a reflex; call it only when guide output says QP-derived fields are needed
+- Do not call the semantic cluster definition builder as a reflex; call it only when guide output says QP-derived fields are needed

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

@@ -0,0 +1,58 @@
+# engage-scene config-channel
+
+> Capability ids: `engage-scene.config-channel.{create,update,query-log}` · Domain: `engage`.
+
+场景管理 / 配置中心 - 配置通道管理与操作日志。
+
+## Commands
+
+```bash
+# Create a config channel and enable it
+ae-cli engage-scene config-channel create \
+  --project-id <project_id> --channel-name <name> --channel-type <0|1> --config '<json string>'
+
+# Update a config channel's name and optionally its config
+ae-cli engage-scene config-channel update \
+  --project-id <project_id> --channel-id <channel_id> --channel-name <name> [--config '<json string>']
+
+# Query a config channel's operation log
+ae-cli engage-scene config-channel query-log --project-id <project_id> --channel-id <channel_id>
+```
+
+## Parameters
+
+### create
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--channel-name` | Yes | Channel name. |
+| `--channel-type` | Yes | Channel type: **0 webhook**, **1 client** (not the same as engage push `channelType`, where 1=webhook). |
+| `--config` | Yes | Channel-specific JSON config string. Webhook (`0`) requires `config.url`; client (`1`) must not include `url`. |
+
+### update
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--channel-id` | Yes | Channel ID to update. |
+| `--channel-name` | Yes | New channel name. |
+| `--config` | No | Channel-specific JSON config string. Omit to keep the current config (typical when renaming an enabled channel). Required when changing webhook URL, auth, or parameter definitions on a disabled channel. |
+
+### query-log
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--channel-id` | Yes | Channel ID whose operation log to query. |
+
+## Output
+
+- `create`: `data.channel_id` — the created channel ID.
+- `update`: `data.success`.
+- `query-log`: `data.items` + `data.total`.
+
+## Decision Rules
+
+- `create`/`update` are `write`; `query-log` is read.
+- Discover real `channel_id`s with `ae-cli engage +config_channel_list --project_id <project_id>` first.

package/skills/ae-engage/references/scene-config-group.md

@@ -0,0 +1,62 @@
+# engage-scene config-group
+
+> Capability ids: `engage-scene.config-group.{list,batch-add,update,batch-delete}` · Domain: `engage`.
+
+场景管理 / 配置中心 - 配置项分组管理。
+
+## Commands
+
+```bash
+# List config groups of a project
+ae-cli engage-scene config-group list --project-id <project_id>
+
+# Batch-create config groups
+ae-cli engage-scene config-group batch-add --project-id <project_id> --group-names '["g1","g2"]'
+
+# Rename a config group
+ae-cli engage-scene config-group update --project-id <project_id> --group-id <group_id> --group-name <name>
+
+# Batch-delete config groups (high-risk)
+ae-cli engage-scene config-group batch-delete --project-id <project_id> --group-ids '[1,2]' --yes
+```
+
+## Parameters
+
+### list
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+
+### batch-add
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--group-names` | Yes | JSON array of group names (<=80 chars each). |
+
+### update
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--group-id` | Yes | Group ID to update. |
+| `--group-name` | Yes | New group name (<=80 chars). |
+
+### batch-delete
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--group-ids` | Yes | JSON array of group IDs. |
+
+## Output
+
+- `list`: `data.items` + `data.total`.
+- `batch-add` / `batch-delete`: `data.success_num` + `data.fail_list` (looped single calls; non-atomic).
+- `update`: `data.success`.
+
+## Decision Rules
+
+- Discover real `group_id`s with `list` before update/delete; never invent IDs.
+- `batch-delete` is `high-risk-write` and requires `--yes`.

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

@@ -0,0 +1,68 @@
+# engage-scene config-item
+
+> Capability ids: `engage-scene.config-item.{list,create,update}` · Domain: `engage`.
+
+场景管理 / 配置中心 - 配置项管理。
+
+## Commands
+
+```bash
+# List config items of a project
+ae-cli engage-scene config-item list --project-id <project_id>
+
+# Create a config item (business type, group, optional avatar)
+ae-cli engage-scene config-item create \
+  --project-id <project_id> --config-id <config_id> --config-name <name> \
+  --business-type <config_file|params> \
+  [--config-remark <remark>] [--group-id <group_id>] \
+  [--avatar-word '["A"]'] [--file-name icon.png] [--file-content "$(base64 -i icon.png)"]
+
+# Update a config item's basic info and bound channel
+ae-cli engage-scene config-item update \
+  --project-id <project_id> --config-id <config_id> \
+  [--config-name <name>] [--config-remark <remark>] [--business-type <type>] \
+  [--group-id <group_id>] [--channel-id <channel_id>]
+```
+
+## Parameters
+
+### list
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+
+### create
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID (unique within the project). |
+| `--config-name` | Yes | Config item display name (<=80 chars). |
+| `--business-type` | Yes | Business type: `config_file` or `params`. |
+| `--config-remark` | No | Remark (<=200 chars). |
+| `--group-id` | No | Group ID (0 = default group). |
+| `--avatar-word` | No | JSON array of avatar words for the icon. |
+| `--file-name` | No | Avatar file name including extension. |
+| `--file-content` | No | Base64-encoded avatar file content. |
+
+### update
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID to update. |
+| `--config-name` | No | New display name. |
+| `--config-remark` | No | New remark. |
+| `--business-type` | No | New business type. |
+| `--group-id` | No | New group ID. |
+| `--channel-id` | No | Config channel ID to bind. |
+
+## Output
+
+- `list`: `data.items` + `data.total`.
+- `create` / `update`: `data.success` — whether the operation succeeded.
+
+## Decision Rules
+
+- `create` / `update` are `write`; `list` is read. Use `config-item list` (or `engage +config_item_list`) to discover real `config_id`s and group IDs; never invent IDs.

package/skills/ae-engage/references/scene-config-metric.md

@@ -0,0 +1,79 @@
+# engage-scene config-metric
+
+> Capability ids: `engage-scene.config-metric.{list,get,batch-add,update-rule,batch-delete}` · Domain: `engage`.
+
+场景管理 / 配置中心 - 配置项关联指标管理。
+
+## Commands
+
+```bash
+# List related metrics of a config item (optionally include preset metrics)
+ae-cli engage-scene config-metric list --project-id <project_id> --config-id <config_id> [--all-metric]
+
+# Get a related metric's detail
+ae-cli engage-scene config-metric get --project-id <project_id> --metric-id <metric_id>
+
+# Batch-relate TA (event-analysis) metrics to a config item
+ae-cli engage-scene config-metric batch-add --project-id <project_id> --config-id <config_id> --ta-metric-ids '[1,2]'
+
+# Update a config metric's event relation rule
+ae-cli engage-scene config-metric update-rule \
+  --project-id <project_id> --metric-id <metric_id> \
+  --event-list '[{"event_name":"e1","filter":"true"}]'
+
+# Batch-remove related metrics (high-risk)
+ae-cli engage-scene config-metric batch-delete --project-id <project_id> --config-id <config_id> --metric-ids '[1,2]' --yes
+```
+
+## Parameters
+
+### list
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID. |
+| `--all-metric` | No | Include preset metrics as well. |
+
+### get
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--metric-id` | Yes | Config metric primary ID. |
+
+### batch-add
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID. |
+| `--ta-metric-ids` | Yes | JSON array of TA metric IDs. |
+
+### update-rule
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--metric-id` | Yes | Config metric primary ID. |
+| `--event-list` | Yes | JSON array of event rules (`event_name` or `eventName`, plus `filter`). |
+
+### batch-delete
+
+| Parameter | Required | Description |
+|---|---|---|
+| `--project-id` / `-p` | Yes | Numeric project ID. |
+| `--config-id` | Yes | Config item ID. |
+| `--metric-ids` | Yes | JSON array of config metric primary IDs. |
+
+## Output
+
+- `list`: `data.items` + `data.total`.
+- `get`: `data` — metric detail.
+- `batch-add` / `update-rule`: `data.success`.
+- `batch-delete`: `data.success`.
+
+## Decision Rules
+
+- Discover real metric IDs via `list`/`get`; never invent IDs.
+- `batch-delete` is `high-risk-write` and requires `--yes`.