@thinkingai/ae-cli 6.1.5 → 6.1.7

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

@@ -1,44 +1,11 @@
-# ae-engage +task_experiment_report
+# engage-task.task-data.experiment-report
 
+Query a task experiment report through the L3 Capability Gateway.
 
-Query the task experiment report.
+Mapped command: `ae-cli capability run engage-task.task-data.experiment-report --input '<json>'`
 
-Mapped command: `ae-cli engage +task_experiment_report`
-
-## Flags
-
-| Flag | Type | Required | Description |
-|------|------|------|------|
-| `--project_id` / `-p` | number | Yes | Project ID |
-| `--task_id` | string | Yes | task ID |
-| `--report_type` | string | Yes | report type: `overview` or `detail` |
-| `--start_time` | string | Yes | Start date |
-| `--end_time` | string | Yes | End date |
-| `--request_id` | string | No | query requestId |
-| `--push_language_code` | string | No | push language code |
-
-## Enum Notes
-
-### `--report_type`
-
-- `overview`: experiment overview
-- `detail`: experiment detail
-
-### `--push_language_code`
-
-Common values include:
-
-- `default`
-- `en`
-- `zh-Hans`
-- `zh-Hant`
-- `ja`
-- `ko`
-
-## Examples
+Required input: `project_id`, `task_id`, `report_type`, `start_time`, `end_time`. `report_type` is `overview` or `detail`.
 
 ```bash
-ae-cli engage +task_experiment_report \
-  --project_id 1 --task_id task_123 \
-  --report_type overview --start_time 2026-04-01 --end_time 2026-04-07
+ae-cli capability run engage-task.task-data.experiment-report --input '{"project_id":1,"task_id":"task_123","report_type":"overview","start_time":"2026-04-01","end_time":"2026-04-07"}'
 ```

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

@@ -1,15 +1,15 @@
-# ae-engage +task_list
+# ae-cli engage-task task list
 
 
 Query the paginated task list.
 
-Mapped command: `ae-cli engage +task_list`
+Mapped command: `ae-cli engage-task task list`
 
 ## Flags
 
 | Flag | Type | Required | Description |
 |------|------|------|------|
-| `--project_id` / `-p` | number | Yes | Project ID |
+| `--project-id` / `-p` | number | Yes | Project ID |
 | `--req` | json | Yes | query-condition JSON object |
 
 ## `--req` Object Fields
@@ -86,5 +86,5 @@ Common fields are listed below; provide them as needed:
 ## Examples
 
 ```bash
-ae-cli engage +task_list --project_id 1 --req '{"pageNum":1,"pageSize":20}'
+ae-cli engage-task task list --project-id 1 --req '{"pageNum":1,"pageSize":20}'
 ```

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

@@ -1,49 +1,11 @@
-# ae-engage +task_metric_detail
+# engage-task.task-data.metric-detail
 
+Query a task metric detail report through the L3 Capability Gateway.
 
-Query the metric-oriented detail report for a task.
+Mapped command: `ae-cli capability run engage-task.task-data.metric-detail --input '<json>'`
 
-Mapped command: `ae-cli engage +task_metric_detail`
-
-## Flags
-
-| Flag | Type | Required | Description |
-|------|------|------|------|
-| `--project_id` / `-p` | number | Yes | Project ID |
-| `--task_id` | string | Yes | task ID |
-| `--start_time` | string | Yes | Start date |
-| `--end_time` | string | Yes | End date |
-| `--request_id` | string | No | query requestId |
-| `--push_language_code` | string | No | push language code |
-| `--metric_id_list` | json | No | metric ID JSON array |
-| `--group_type` | number | No | group type |
-| `--show_time_zone` | string | No | Display timezone offset |
-
-## Enum Notes
-
-### `--group_type`
-
-- `1`: group by batch
-- `2`: group by date
-- `3`: group by trigger
-- `4`: group by experiment result
-
-### `--push_language_code`
-
-Common values include:
-
-- `default`
-- `en`
-- `zh-Hans`
-- `zh-Hant`
-- `ja`
-- `ko`
-
-## Examples
+Required input: `project_id`, `task_id`, `start_time`, `end_time`. Optional input includes `request_id`, `push_language_code`, `metric_id_list`, `group_type`, and `show_time_zone`.
 
 ```bash
-ae-cli engage +task_metric_detail \
-  --project_id 1 --task_id task_123 \
-  --start_time 2026-04-01 --end_time 2026-04-07 \
-  --metric_id_list '["metric_1"]'
+ae-cli capability run engage-task.task-data.metric-detail --input '{"project_id":1,"task_id":"task_123","start_time":"2026-04-01","end_time":"2026-04-07"}'
 ```

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

@@ -1,20 +1,20 @@
-# ae-engage +task_stats
+# ae-cli engage-task task stats
 
 
 Query task status statistics.
 
-Mapped command: `ae-cli engage +task_stats`
+Mapped command: `ae-cli engage-task task stats`
 
 ## Flags
 
 | Flag | Type | Required | Description |
 |------|------|------|------|
-| `--project_id` / `-p` | number | Yes | Project ID |
+| `--project-id` / `-p` | number | Yes | Project ID |
 | `--req` | json | Yes | statistics-condition JSON object |
 
 ## `--req` Object Fields
 
-The `--req` structure of `+task_stats` is broadly the same as `+task_list`, and common fields include:
+The `--req` structure of `engage-task task stats` is broadly the same as `engage-task task list`, and common fields include:
 
 | Field | Type | Required | Description |
 |------|------|------|------|
@@ -84,5 +84,5 @@ The `--req` structure of `+task_stats` is broadly the same as `+task_list`, and
 ## Examples
 
 ```bash
-ae-cli engage +task_stats --project_id 1 --req '{"pageNum":1,"pageSize":20}'
+ae-cli engage-task task stats --project-id 1 --req '{"pageNum":1,"pageSize":20}'
 ```

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

@@ -1,24 +1,24 @@
-# ae-engage +update_channel_status
+# ae-engage engage-setting channel update-status
 
 
 Update the status of an Engage channel.
 
-Mapped command: `ae-cli engage +update_channel_status`
+Mapped command: `ae-cli engage-setting channel update-status`
 
 ## Flags
 
 | Flag | Type | Required | Description |
 |------|------|------|------|
-| `--project_id` / `-p` | number | Yes | Project ID |
-| `--channel_id` | string | Yes | channel ID |
+| `--project-id` / `-p` | number | Yes | Project ID |
+| `--channel-id` | string | Yes | channel ID |
 | `--status` | number | Yes | channel status |
 
 ## Enum Notes
 
 ### `--status`
 
-- `0`: disabled
 - `1`: enabled
+- `2`: disabled
 
 ## Safety Constraints
 
@@ -27,5 +27,5 @@ This command is a **write operation** and Before executing, confirm that the use
 ## Examples
 
 ```bash
-ae-cli engage +update_channel_status --project_id 1 --channel_id <channel_id> --status 1
+ae-cli engage-setting channel update-status --project-id 1 --channel-id <channel_id> --status 1
 ```

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

@@ -1,30 +1,31 @@
-# ae-engage +validate_flow_node_config
+# ae-cli engage-flow node-config validate
 
 
 Validate and normalize a single node configuration before placing it into a `save_flow` request.
 
-Mapped command: `ae-cli engage +validate_flow_node_config`
+Mapped command: `ae-cli engage-flow node-config validate`
 
 ## Flags
 
 | Flag | Type | Required | Description |
 |------|------|------|------|
-| `--node_type` | string | Yes | Flow node type |
+| `--project-id` / `-p` | number | Yes | Project ID |
+| `--node-type` | string | Yes | Flow node type |
 | `--config` | string | Yes | Node config JSON object encoded as a string |
-| `--operation_mode` | string | Yes | Validation mode |
+| `--operation-mode` | string | Yes | Validation mode |
 
 ## When To Use
 
-Use this after `+flow_node_config_schema` and before passing a config into `+save_flow`.
+Use this after `engage-flow node-config schema` and before passing a config into `engage-flow flow save`.
 
 The command validates one node config only; it does not validate the full canvas topology. It returns:
 
 - `valid`: whether the candidate config passed validation
 - `normalizedConfigObject`: backend-normalized config with defaulted fields
-- `errors`: hard validation failures to fix before calling `+save_flow`
+- `errors`: hard validation failures to fix before calling `engage-flow flow save`
 - `warnings`: issues that depend on live channel/template/config data
 
-Use `--operation_mode save_flow` for the current exposed MCP protocol. Use `save_submit_flow` only when you intentionally want stricter submit-time checks.
+Use `--operation-mode save_flow` for the current exposed MCP protocol. Use `save_submit_flow` only when you intentionally want stricter submit-time checks.
 
 Important current rules:
 
@@ -38,7 +39,7 @@ Important current rules:
 
 ## Enum Notes
 
-### `--node_type`
+### `--node-type`
 
 Schema-backed node types include:
 
@@ -56,7 +57,7 @@ Schema-backed node types include:
 - `ab_split_flow`
 - `exit_flow`
 
-### `--operation_mode`
+### `--operation-mode`
 
 - `save_flow`
 - `save_submit_flow`
@@ -64,6 +65,6 @@ Schema-backed node types include:
 ## Examples
 
 ```bash
-ae-cli engage +validate_flow_node_config \
-  --node_type message_push --operation_mode save_flow --config '{}'
+ae-cli engage-flow node-config validate \
+  --project-id 1 --node-type message_push --operation-mode save_flow --config '{}'
 ```

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

@@ -1,18 +1,18 @@
-# ae-engage +whitelist_list
+# ae-engage engage-setting whitelist list
 
 
 Query the whitelist list in a project.
 
-Mapped command: `ae-cli engage +whitelist_list`
+Mapped command: `ae-cli engage-setting whitelist list`
 
 ## Flags
 
 | Flag | Type | Required | Description |
 |------|------|------|------|
-| `--project_id` / `-p` | number | Yes | Project ID |
+| `--project-id` / `-p` | number | Yes | Project ID |
 
 ## Examples
 
 ```bash
-ae-cli engage +whitelist_list --project_id 1
+ae-cli engage-setting whitelist list --project-id 1
 ```

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

@@ -68,5 +68,5 @@ ae-cli engage-setting whitelist verify \
 ## Decision Rules
 
 - Use these commands when the user asks to add / edit / delete / verify project whitelist entries.
-- Discover existing whitelist IDs with `ae-cli engage +whitelist_list --project_id <project_id>` first; never invent IDs.
+- Discover existing whitelist IDs with `ae-cli engage-setting whitelist list --project-id <project_id>` first; never invent IDs.
 - `delete` is `high-risk-write` and requires `--yes` (or interactive confirmation).

package/skills/ae-engage/references/workbench-workbench.md

@@ -2,7 +2,7 @@
 
 > Capability ids: `engage-workbench.workbench.{list,add,update,delete}` · Domain: `engage`.
 
-工作台 - 工作台指标卡槽（workbench slot）管理。每个用户在每个项目下最多 4 个指标卡；卡槽按当前登录用户隔离，`update`/`delete` 只能操作本人卡槽。首次 `list` 会自动初始化 4 个默认卡槽。
+Workbench — workbench metric slot management. Each user may configure up to 4 metric cards per project; slots are scoped to the current login user, so `update`/`delete` only affect the caller's own slots. The first `list` auto-initialises 4 default slots.
 
 ## Commands
 

package/skills/ae-experiment/SKILL.md

@@ -6,39 +6,49 @@ description: "Use when managing Atlas AB experiments, traffic layers, Features,
 
 # ae-experiment
 
-AE CLI (`ae-cli`) exposes Atlas AB Experiment MCP capabilities through the `experiment` domain.
+AE CLI (`ae-cli`) exposes Atlas AB Experiment capabilities through the `experiment` domain.
 
 ## Global Rules
 
 - Prefer `ae-cli experiment <command>` for Atlas AB Experiment work.
-- Use `--project_id` / `-p` for project-scoped commands.
+- Use `--project-id` / `-p` for project-scoped commands.
 - Use `--req` JSON for complex save, status, and delete DTOs.
 - Do not invent experiment IDs, traffic layer IDs, bucket IDs, Feature keys, metric IDs, or payload field names.
 - Read commands can run directly after IDs are verified.
 - Write commands require explicit user intent and normally keep the confirmation prompt. Use `--dry-run` before write calls when composing JSON.
 
+Naming and response boundary:
+
+- CLI command segments and flags use kebab-case.
+- Outer Capability input and all response keys use snake_case.
+- Nested business DTOs passed through `--req` keep their native camelCase fields.
+- Lists return `data.items` and `data.total`; detail commands return `data.item`.
+- Readiness returns `data.readiness`; reports return `data.report`; writes return `data.result`.
+- Query cancellation returns `data.success`.
+
 ## Typical Workflow
 
 1. Discover reusable assets:
-   - `+query_bucket_list`
-   - `+query_traffic_layer_list`
-   - `+query_feature_list`
-   - `+query_metric_list`
+   - `experiment bucket list`
+   - `experiment traffic-layer list`
+   - `experiment feature list`
+   - `experiment metric list`
 2. Create missing assets if needed:
-   - `+save_traffic_layer`
-   - `+save_feature`
-   - `+save_metric`
-3. Create or patch the experiment draft with `+save_experiment`.
-4. Check readiness with `+check_experiment_ready`.
-5. Move status with `+manage_experiment`.
-6. Query reports with summary, sample-size, and metric-trend commands.
+   - `experiment traffic-layer save`
+   - `experiment feature save`
+   - `experiment metric save`
+3. Create or patch the experiment draft with `experiment experiment save`.
+4. Check readiness with `experiment experiment ready-check`.
+5. For a non-mutex traffic layer, run `experiment experiment conflict-check` before submit (needs `feature_key_list` from context or `experiment get`).
+6. Move status with `experiment experiment manage`.
+7. Query reports with summary, sample-size, and metric-trend commands.
 
 ## Parameter Conventions
 
 ```bash
-ae-cli experiment +query_experiment_detail --project_id 1 --exp_id exp_123
-ae-cli --dry-run experiment +save_experiment --project_id 1 --req '{"expName":"Demo"}'
-ae-cli experiment +query_experiment_metric_trend --project_id 1 --exp_id exp_123 --metric_id metric_1 --start_time 2026-07-01 --end_time 2026-07-07
+ae-cli experiment experiment get --project-id 1 --exp-id exp_123
+ae-cli experiment experiment save --project-id 1 --req '{"expName":"Demo"}' --dry-run
+ae-cli capability run experiment.report.metric-trend --input '{"project_id":1,"exp_id":"exp_123","metric_id":"metric_1","start_time":"2026-07-01","end_time":"2026-07-07"}'
 ```
 
 Optional global parameters work as in other domains: `--host`, `--mcp-url`, `--format`, `--jq`, `--dry-run`, and `--yes`.
@@ -49,16 +59,16 @@ Open the matching file in `references/` before using a command, especially for w
 
 ### Experiment
 
-`+save_experiment`, `+save_submit_experiment`, `+query_experiment_list`, `+query_experiment_detail`, `+check_experiment_ready`, `+manage_experiment`, `+batch_delete_experiment`
+`experiment experiment save`, `capability run experiment.experiment.save-submit`, `experiment experiment list`, `experiment experiment list-archived`, `experiment experiment get`, `experiment experiment ready-check`, `experiment experiment conflict-check`, `experiment experiment manage`, `experiment experiment update-group`, `experiment experiment batch-delete`, `experiment operation-log query`
 
 ### Traffic Layer and Buckets
 
-`+save_traffic_layer`, `+query_traffic_layer_detail`, `+query_traffic_layer_list`, `+batch_delete_traffic_layer`, `+query_bucket_list`
+`experiment traffic-layer save`, `experiment traffic-layer get`, `experiment traffic-layer list`, `experiment traffic-layer batch-delete`, `experiment bucket list`
 
 ### Reports
 
-`+query_experiment_report_summary`, `+query_experiment_sample_size_report`, `+query_experiment_metric_trend`, `+cancel_experiment_query_by_request_id`
+`capability run experiment.report.summary`, `capability run experiment.report.sample-size`, `capability run experiment.report.metric-trend`, `capability run experiment.query.cancel`
 
 ### Metric and Feature
 
-`+save_metric`, `+query_metric_detail`, `+query_metric_list`, `+delete_metric`, `+save_feature`, `+manage_feature_status`, `+query_feature_detail`, `+query_feature_list`, `+batch_delete_feature`
+`experiment metric save`, `experiment metric get`, `experiment metric list`, `experiment metric delete`, `experiment feature save`, `experiment feature update-status`, `experiment feature get`, `experiment feature list`, `experiment feature version-list`, `experiment feature operation-log query`, `experiment feature batch-delete`

package/skills/ae-experiment/references/batch_delete_experiment.md

@@ -1,11 +1,11 @@
-# +batch_delete_experiment
+# experiment experiment batch-delete
 
 Batch delete experiments.
 
 ```bash
-ae-cli experiment +batch_delete_experiment --project_id <id> --exp_ids '["exp_1","exp_2"]' [--yes]
+ae-cli experiment experiment batch-delete --project-id <id> --exp-ids '["exp_1","exp_2"]' [--yes]
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
-- `--exp_ids`: Experiment ID list as JSON array.
+- `--project-id`, `-p`: Project ID.
+- `--exp-ids`: Experiment ID list as JSON array.

package/skills/ae-experiment/references/batch_delete_feature.md

@@ -1,11 +1,11 @@
-# +batch_delete_feature
+# experiment feature batch-delete
 
 Batch delete Features.
 
 ```bash
-ae-cli experiment +batch_delete_feature --project_id <id> --req '<json>' [--yes]
+ae-cli experiment feature batch-delete --project-id <id> --req '<json>' [--yes]
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
+- `--project-id`, `-p`: Project ID.
 - `--req`: Feature delete request JSON object.

package/skills/ae-experiment/references/batch_delete_traffic_layer.md

@@ -1,11 +1,11 @@
-# +batch_delete_traffic_layer
+# experiment traffic-layer batch-delete
 
 Batch delete traffic layers.
 
 ```bash
-ae-cli experiment +batch_delete_traffic_layer --project_id <id> --layer_ids '["layer_1","layer_2"]' [--yes]
+ae-cli experiment traffic-layer batch-delete --project-id <id> --layer-ids '["layer_1","layer_2"]' [--yes]
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
-- `--layer_ids`: Traffic layer ID list as JSON array.
+- `--project-id`, `-p`: Project ID.
+- `--layer-ids`: Traffic layer ID list as JSON array.

package/skills/ae-experiment/references/cancel_experiment_query_by_request_id.md

@@ -1,10 +1,11 @@
-# +cancel_experiment_query_by_request_id
+# capability run experiment.query.cancel
 
 Cancel a running experiment report query.
 
 ```bash
-ae-cli experiment +cancel_experiment_query_by_request_id --request_id <id>
+ae-cli capability run experiment.query.cancel --input '{"request_id":"<id>"}'
 ```
 
-Flags:
-- `--request_id`: Request ID to cancel.
+Required input: `request_id`.
+
+Response shape: `data.success`.

package/skills/ae-experiment/references/check_experiment_ready.md

@@ -1,13 +1,15 @@
-# +check_experiment_ready
+# experiment experiment ready-check
 
 Check whether an experiment can enter online status transitions.
 
 ```bash
-ae-cli experiment +check_experiment_ready --project_id <id> --exp_id <expId>
+ae-cli experiment experiment ready-check --project-id <id> --exp-id <expId>
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
-- `--exp_id`: Experiment ID.
+- `--project-id`, `-p`: Project ID.
+- `--exp-id`: Experiment ID.
 
-Use this before `+manage_experiment` moves an experiment to `pending`, `testing`, or `running`.
+Use this before `experiment experiment manage` moves an experiment to `pending`, `testing`, or `running`.
+
+Response shape: the readiness result is in `data.readiness`, with recursively snake_case keys.

package/skills/ae-experiment/references/check_experiment_traffic_layer_conflict.md

@@ -0,0 +1,37 @@
+# experiment experiment conflict-check
+
+Pre-submit check for cross-layer Feature conflicts on a **non-mutex** traffic layer.
+
+Reuse the existing Hermes `trafficLayerConflictCheck` API. Do **not** call this command for mutex traffic layers.
+
+## Workflow
+
+1. Ensure you already have the Feature keys for the current experiment:
+   - Editing an existing draft: call `experiment experiment get` and read `feature_key_list`.
+   - Creating a new experiment: reuse the Feature keys already chosen in the current workflow.
+2. Call conflict-check with the selected non-mutex `traffic-layer-id`.
+3. Interpret the response before `save-submit`:
+   - `data.features` non-empty: some Features are not enabled.
+   - `data.experiments` non-empty: same Features are active on other traffic layers.
+   - both empty: no conflict signal from this check.
+
+```bash
+ae-cli experiment experiment conflict-check \
+  --project-id <id> \
+  --feature-key-list '["checkout_color"]' \
+  --traffic-layer-id <layer-id>
+
+ae-cli experiment experiment conflict-check \
+  --project-id <id> \
+  --feature-key-list '["checkout_color"]' \
+  --traffic-layer-id <layer-id> \
+  --exp-id <exp-id>
+```
+
+Flags:
+- `--project-id`, `-p`: Project ID.
+- `--feature-key-list`: Required JSON string array of Feature keys selected by the current experiment.
+- `--traffic-layer-id`: Required selected non-mutex traffic layer ID.
+- `--exp-id`: Optional current experiment ID when editing an existing draft (excludes self from conflicts).
+
+Response shape: `data.experiments` and `data.features`, with recursively snake_case item keys.

package/skills/ae-experiment/references/delete_metric.md

@@ -1,11 +1,11 @@
-# +delete_metric
+# experiment metric delete
 
 Delete a metric.
 
 ```bash
-ae-cli experiment +delete_metric --project_id <id> --metric_id <metricId> [--yes]
+ae-cli experiment metric delete --project-id <id> --metric-id <metricId> [--yes]
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
-- `--metric_id`: Metric ID.
+- `--project-id`, `-p`: Project ID.
+- `--metric-id`: Metric ID.

package/skills/ae-experiment/references/manage_experiment.md

@@ -1,15 +1,17 @@
-# +manage_experiment
+# experiment experiment manage
 
 Manage experiment status.
 
 ```bash
-ae-cli experiment +manage_experiment --project_id <id> --exp_id <expId> --target_status <status> [--remark <text>]
+ae-cli experiment experiment manage --project-id <id> --exp-id <expId> --target-status <status> [--remark <text>]
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
-- `--exp_id`: Experiment ID.
-- `--target_status`: One of `draft`, `testing`, `pending`, `running`, `paused`, `ended`, `archive`.
+- `--project-id`, `-p`: Project ID.
+- `--exp-id`: Experiment ID.
+- `--target-status`: One of `draft`, `testing`, `pending`, `running`, `paused`, `ended`, `archive`.
 - `--remark`: Optional operation remark.
 
-When target status is `pending`, `testing`, or `running`, the MCP server performs a ready check first.
+When target status is `pending`, `testing`, or `running`, Hermes performs a ready check before changing status.
+
+Response shape: the operation or blocking readiness result is in `data.result`, with object keys recursively converted to snake_case.

package/skills/ae-experiment/references/manage_feature_status.md

@@ -1,11 +1,11 @@
-# +manage_feature_status
+# experiment feature update-status
 
 Update Feature status.
 
 ```bash
-ae-cli experiment +manage_feature_status --project_id <id> --req '<json>'
+ae-cli experiment feature update-status --project-id <id> --req '<json>'
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
+- `--project-id`, `-p`: Project ID.
 - `--req`: Feature status request JSON object.

package/skills/ae-experiment/references/query_bucket_list.md

@@ -1,10 +1,12 @@
-# +query_bucket_list
+# experiment bucket list
 
 Query split buckets in a project.
 
 ```bash
-ae-cli experiment +query_bucket_list --project_id <id>
+ae-cli experiment bucket list --project-id <id>
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
+- `--project-id`, `-p`: Project ID.
+
+Response shape: `data.items` contains split buckets, `data.total` contains the count, and item keys are recursively snake_case.

package/skills/ae-experiment/references/query_experiment_detail.md

@@ -1,11 +1,13 @@
-# +query_experiment_detail
+# experiment experiment get
 
 Query full experiment detail.
 
 ```bash
-ae-cli experiment +query_experiment_detail --project_id <id> --exp_id <expId>
+ae-cli experiment experiment get --project-id <id> --exp-id <expId>
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
-- `--exp_id`: Experiment ID.
+- `--project-id`, `-p`: Project ID.
+- `--exp-id`: Experiment ID.
+
+Response shape: the experiment is in `data.item`, with recursively snake_case keys such as `exp_id` and `feature_key_list`.

package/skills/ae-experiment/references/query_experiment_list.md

@@ -1,10 +1,18 @@
-# +query_experiment_list
+# experiment experiment list
 
-Query experiments in a project.
+Query experiments in a project with optional filters from the existing list API.
 
 ```bash
-ae-cli experiment +query_experiment_list --project_id <id>
+ae-cli experiment experiment list --project-id <id>
+ae-cli experiment experiment list --project-id <id> --status archive
+ae-cli experiment experiment list --project-id <id> --traffic-layer-id <layer-id> --group-id <group-id> --query-name checkout
 ```
 
 Flags:
-- `--project_id`, `-p`: Project ID.
+- `--project-id`, `-p`: Project ID.
+- `--status`: Optional status filter (`draft`, `testing`, `pending`, `running`, `paused`, `ended`, `archive`). For the dedicated archived list command, prefer `experiment experiment list-archived`.
+- `--traffic-layer-id`: Optional traffic layer ID filter.
+- `--group-id`: Optional business group ID filter.
+- `--query-name`: Optional fuzzy match against experiment name (`exp_name LIKE`). Does not match `exp_id`.
+
+Response shape: `data.items` contains the experiments, `data.total` contains the count, and item keys are recursively snake_case.