@thinkingai/ae-cli 6.0.28 → 6.0.30

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

@@ -1,4 +1,4 @@
-# analysis asset recent-list
+# analysis-meta asset recent-list
 
 Use when the user needs to list recently visited assets for the current user.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis asset recent-list --project-id <project_id> --payload '{}'
-ae-cli analysis asset recent-list --dry-run
+ae-cli analysis-meta asset recent-list --project-id <project_id> --payload '{}'
+ae-cli analysis-meta asset recent-list --dry-run
 ```
 
 Capability id: `metadata.asset.recent_list`.

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

@@ -1,4 +1,4 @@
-# analysis asset search
+# analysis-meta asset search
 
 Use when the user needs to search project assets by keyword.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis asset search --project-id <project_id> --payload '{}'
-ae-cli analysis asset search --dry-run
+ae-cli analysis-meta asset search --project-id <project_id> --payload '{}'
+ae-cli analysis-meta asset search --dry-run
 ```
 
 Capability id: `metadata.asset.search`.

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

@@ -8,7 +8,7 @@ Domain: **Model Analysis**
 - Build a validated event-analysis QP from structured intent.
 - Use in the mandatory builder flow before `+query_adhoc --model_type event`.
 - This command builds QP only and does not execute the analysis query.
-- This is one of exactly four QP builders: `event`, `retention`, `funnel`, `prop_analysis`.
+- This is the `event` builder in the ten-model guided QP builder set.
 - Use this builder for event-analysis ad hoc requests; do not manually build event QP through `+get_analysis_query_schema`.
 
 ## JSON Rules

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

@@ -8,7 +8,7 @@ Domain: **Model Analysis**
 - Build a validated funnel-analysis QP from structured intent.
 - Use in the mandatory builder flow before `+query_adhoc --model_type funnel`.
 - This command builds QP only and does not execute the analysis query.
-- This is one of exactly four QP builders: `event`, `retention`, `funnel`, `prop_analysis`.
+- This is the `funnel` builder in the ten-model guided QP builder set.
 - Use this builder for funnel ad hoc requests; do not manually build funnel QP through `+get_analysis_query_schema`.
 
 ## JSON Rules

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

@@ -8,7 +8,7 @@ Domain: **Model Analysis**
 - Build a validated `prop_analysis` QP from structured intent.
 - Use in the mandatory builder flow before `+query_adhoc --model_type prop_analysis`.
 - This command builds QP only and does not execute the analysis query.
-- This is one of exactly four QP builders: `event`, `retention`, `funnel`, `prop_analysis`.
+- This is the `prop_analysis` builder in the ten-model guided QP builder set.
 - Use this builder for property-analysis ad hoc requests; do not manually build prop_analysis QP through `+get_analysis_query_schema`.
 
 ## JSON Rules

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

@@ -8,7 +8,7 @@ Domain: **Model Analysis**
 - Build a validated retention-analysis QP from structured intent.
 - Use in the mandatory builder flow before `+query_adhoc --model_type retention`.
 - This command builds QP only and does not execute the analysis query.
-- This is one of exactly four QP builders: `event`, `retention`, `funnel`, `prop_analysis`.
+- This is the `retention` builder in the ten-model guided QP builder set.
 - Use this builder for retention ad hoc requests; do not manually build retention QP through `+get_analysis_query_schema`.
 
 ## JSON Rules

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

@@ -26,7 +26,7 @@ ae-cli analysis +cancel_query --request_id mcp_0123456789abcdef0123456789abcdef
 | `--reason` | No | Optional cancellation reason. Default: `MCP_CANCEL_QUERY_TOOL`. |
 
 ## Decision Rules
-- This is a write operation. Use `--yes` only when the user clearly asked to cancel or stop a running query.
+- This is a write operation (`risk: write`). Use `--yes` only when the user clearly asked to cancel or stop a running query.
 - The request must belong to the current MCP user. Otherwise the service returns `REQUEST_NOT_FOUND_OR_NOT_OWNED`.
 - Do not invent a request ID. Use the ID from the query response or the ID explicitly supplied to the original query.
 - This command cancels by request ID only. It does not cancel by SQL text, report ID, dashboard ID, BI panel ID, run ID, or tool call ID.

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

@@ -1,4 +1,4 @@
-# analysis datatable columns-get
+# analysis-meta datatable columns-get
 
 Use when the user needs to get columns for a project table reference.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis datatable columns-get --project-id <project_id> --table-ref <table_ref>
-ae-cli analysis datatable columns-get --dry-run
+ae-cli analysis-meta datatable columns-get --project-id <project_id> --table-ref <table_ref>
+ae-cli analysis-meta datatable columns-get --dry-run
 ```
 
 Capability id: `metadata.data_table.columns_get`.

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

@@ -1,4 +1,4 @@
-# analysis datatable influence-list
+# analysis-meta datatable influence-list
 
 Use when the user needs to list metadata and assets affected by data table deletion or column changes.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis datatable influence-list --project-id <project_id> --datatable-id <datatable_id>
-ae-cli analysis datatable influence-list --dry-run
+ae-cli analysis-meta datatable influence-list --project-id <project_id> --datatable-id <datatable_id>
+ae-cli analysis-meta datatable influence-list --dry-run
 ```
 
 Capability id: `metadata.data_table.influence_list`.

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

@@ -1,4 +1,4 @@
-# analysis datatable version-get
+# analysis-meta datatable version-get
 
 Use when the user needs to get data table version detail.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis datatable version-get --project-id <project_id> --version-id <version_id>
-ae-cli analysis datatable version-get --dry-run
+ae-cli analysis-meta datatable version-get --project-id <project_id> --version-id <version_id>
+ae-cli analysis-meta datatable version-get --dry-run
 ```
 
 Capability id: `metadata.data_table_version.get`.

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

@@ -1,4 +1,4 @@
-# analysis datatable version-list
+# analysis-meta datatable version-list
 
 Use when the user needs to list data table historical versions.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis datatable version-list --project-id <project_id> --datatable-id <datatable_id>
-ae-cli analysis datatable version-list --dry-run
+ae-cli analysis-meta datatable version-list --project-id <project_id> --datatable-id <datatable_id>
+ae-cli analysis-meta datatable version-list --dry-run
 ```
 
 Capability id: `metadata.data_table_version.list`.

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

@@ -8,7 +8,7 @@ Domain: **Model analysis**
 - Drill down to detailed event sequences for a specific user on specific dates.
 - This tool is typically used after drilldown_users.
 - Common parameters (focus on these): projectId, userId, eventNames, targetDates.
-- Advanced parameters (for special scenarios): zoneOffset, properties, timeGranularity, firstDayOfWeek, sortOrder, eventNameFilter, timeFilter, timeFilterBeforeNums, timeFilterAfterNums, entityId, entityValue, useCache, pageNum, pageSize.
+- Advanced parameters (for special scenarios): zoneOffset, properties, timeGranularity, firstDayOfWeek, sortOrder, eventNameFilter, timeFilter, timeFilterBeforeNums, timeFilterAfterNums, entityId, entityValue, useCache, limit, offset.
 - The userId must come from drilldown_users and must not be guessed.
 - targetDates is a list of discrete dates, not a date range.
 - Constraint: drilldown positioning parameters must come from the previous query result and must not be guessed.
@@ -31,7 +31,7 @@ Domain: **Model analysis**
 ## Command
 ```bash
 ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]'
-ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]' --zone_offset 8 --use_cache true --page_num 1 --page_size 20 --request_id mcp_bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
+ae-cli analysis +drilldown_user_events --project_id <project_id> --user_id u_123 --event_names '["login"]' --target_dates '["2026-04-08 00:00:00"]' --zone_offset 8 --use_cache true --limit 20 --offset 0 --request_id mcp_bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb
 ae-cli analysis +drilldown_user_events --dry-run
 ```
 
@@ -54,8 +54,8 @@ ae-cli analysis +drilldown_user_events --dry-run
 | `--entity_id` | No | Optional entity ID for multi-entity scenarios |
 | `--entity_value` | No | Optional entity value for multi-entity scenarios |
 | `--use_cache` | No | Whether to use cache. Default: true |
-| `--page_num` | No | Start page number, default 1 |
-| `--page_size` | No | Page size. Default: 1000, maximum: 10000 |
+| `--limit` | No | Maximum rows. Default: 1000, maximum: 10000 |
+| `--offset` | No | Row offset. Default: 0 |
 | `--request_id` | Yes | Required unique request ID used for tracking and cancellation. Generate it before starting the query. It must use `mcp_<32 lowercase hex UUID>`, for example `mcp_0123456789abcdef0123456789abcdef`. Provide this before starting the query so it can be cancelled later with `+cancel_query --request_id <same value>`, even if the caller stops waiting before the tool returns. If `fetch failed`, HTTP timeout, or caller timeout happens, the backend query may still be running. `requestId` is not auto-generated for MCP query tools because the caller must know it before the response for proactive cleanup. If omitted or blank, the backend returns `REQUEST_ID_REQUIRED`; invalid format returns `INVALID_REQUEST_ID`. The response `metadata.requestId` echoes the supplied requestId and can also be passed to `cancel_query(requestId)` when the query is no longer needed. |
 | `--timeout_minutes` | No | Query timeout in minutes |
 

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

@@ -1,4 +1,4 @@
-# analysis event changelog-list
+# analysis-meta event changelog-list
 
 Use when the user needs to list event metadata change logs.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event changelog-list --project-id <project_id> --event-name <event_name>
-ae-cli analysis event changelog-list --dry-run
+ae-cli analysis-meta event changelog-list --project-id <project_id> --event-name <event_name>
+ae-cli analysis-meta event changelog-list --dry-run
 ```
 
 Capability id: `metadata.event.changelog_list`.

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

@@ -1,4 +1,4 @@
-# analysis event create
+# analysis-meta event create
 
 Use when the user needs to create super events and optionally associate event properties.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event create --project-id <project_id> --payload '{}'
-ae-cli analysis event create --dry-run
+ae-cli analysis-meta event create --project-id <project_id> --payload '{}'
+ae-cli analysis-meta event create --dry-run
 ```
 
 Capability id: `metadata.event.create`.

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

@@ -1,4 +1,4 @@
-# analysis event delete
+# analysis-meta event delete
 
 Use when the user needs to batch delete events or virtual events.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event delete --project-id <project_id> --event-names '{}'
-ae-cli analysis event delete --dry-run
+ae-cli analysis-meta event delete --project-id <project_id> --event-names '{}'
+ae-cli analysis-meta event delete --dry-run
 ```
 
 Capability id: `metadata.event.delete`.

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

@@ -1,4 +1,4 @@
-# analysis event get
+# analysis-meta event get
 
 Use when the user needs to get one super event metadata detail.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event get --project-id <project_id> --event-name <event_name>
-ae-cli analysis event get --dry-run
+ae-cli analysis-meta event get --project-id <project_id> --event-name <event_name>
+ae-cli analysis-meta event get --dry-run
 ```
 
 Capability id: `metadata.event.get`.

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

@@ -1,4 +1,4 @@
-# analysis event hide-update
+# analysis-meta event hide-update
 
 Use when the user needs to batch hide or show events.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event hide-update --project-id <project_id> --event-names '{}' --is-hide true
-ae-cli analysis event hide-update --dry-run
+ae-cli analysis-meta event hide-update --project-id <project_id> --event-names '{}' --is-hide true
+ae-cli analysis-meta event hide-update --dry-run
 ```
 
 Capability id: `metadata.event.hide_update`.

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

@@ -1,4 +1,4 @@
-# analysis event influence-list
+# analysis-meta event influence-list
 
 Use when the user needs to list assets affected by event delete, hide, or update.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event influence-list --project-id <project_id> --event-name <event_name>
-ae-cli analysis event influence-list --dry-run
+ae-cli analysis-meta event influence-list --project-id <project_id> --event-name <event_name>
+ae-cli analysis-meta event influence-list --dry-run
 ```
 
 Capability id: `metadata.event.influence_list`.

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

@@ -1,4 +1,4 @@
-# analysis event list
+# analysis-meta event list
 
 Use when the user needs to list project super events.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event list --project-id <project_id>
-ae-cli analysis event list --dry-run
+ae-cli analysis-meta event list --project-id <project_id>
+ae-cli analysis-meta event list --dry-run
 ```
 
 Capability id: `metadata.event.list`.

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

@@ -1,4 +1,4 @@
-# analysis event relation-update
+# analysis-meta event relation-update
 
 Use when the user needs to update event-property connection or source relations.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event relation-update --project-id <project_id> --payload '{}'
-ae-cli analysis event relation-update --dry-run
+ae-cli analysis-meta event relation-update --project-id <project_id> --payload '{}'
+ae-cli analysis-meta event relation-update --dry-run
 ```
 
 Capability id: `metadata.event.relation_update`.

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

@@ -1,4 +1,4 @@
-# analysis event update
+# analysis-meta event update
 
 Use when the user needs to update event display names and remarks.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis event update --project-id <project_id> --event-name <event_name> --event-desc <event_desc> --remark <remark>
-ae-cli analysis event update --dry-run
+ae-cli analysis-meta event update --project-id <project_id> --event-name <event_name> --event-desc <event_desc> --remark <remark>
+ae-cli analysis-meta event update --dry-run
 ```
 
 Capability id: `metadata.event.update`.

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

@@ -1,4 +1,4 @@
-# analysis exchange config-update
+# analysis-meta exchange config-update
 
 Use when the user needs to update exchange-rate configuration switch or value.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis exchange config-update --project-id <project_id> --config-val <config_val>
-ae-cli analysis exchange config-update --dry-run
+ae-cli analysis-meta exchange config-update --project-id <project_id> --config-val <config_val>
+ae-cli analysis-meta exchange config-update --dry-run
 ```
 
 Capability id: `metadata.exchange_config.update`.

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

@@ -1,4 +1,4 @@
-# analysis exchange rate-refresh
+# analysis-meta exchange rate-refresh
 
 Use when the user needs to refresh exchange-rate data manually.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis exchange rate-refresh --project-id <project_id>
-ae-cli analysis exchange rate-refresh --dry-run
+ae-cli analysis-meta exchange rate-refresh --project-id <project_id>
+ae-cli analysis-meta exchange rate-refresh --dry-run
 ```
 
 Capability id: `metadata.exchange_rate.refresh`.

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

@@ -1,4 +1,4 @@
-# analysis exchange rule-list
+# analysis-meta exchange rule-list
 
 Use when the user needs to list exchange-rate conversion rules.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis exchange rule-list --project-id <project_id>
-ae-cli analysis exchange rule-list --dry-run
+ae-cli analysis-meta exchange rule-list --project-id <project_id>
+ae-cli analysis-meta exchange rule-list --dry-run
 ```
 
 Capability id: `metadata.exchange_rule.list`.

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

@@ -1,4 +1,4 @@
-# analysis exchange rule-update
+# analysis-meta exchange rule-update
 
 Use when the user needs to save currency field, amount field, and target currency rules.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis exchange rule-update --project-id <project_id> --payload '{}'
-ae-cli analysis exchange rule-update --dry-run
+ae-cli analysis-meta exchange rule-update --project-id <project_id> --payload '{}'
+ae-cli analysis-meta exchange rule-update --dry-run
 ```
 
 Capability id: `metadata.exchange_rule.update`.

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

@@ -1,4 +1,4 @@
-# analysis exchange rule-validate
+# analysis-meta exchange rule-validate
 
 Use when the user needs to validate affected range before saving exchange-rate rules.
 
@@ -7,8 +7,8 @@ Do not use this command for unrelated analysis queries, ad-hoc query constructio
 Command:
 
 ```bash
-ae-cli analysis exchange rule-validate --project-id <project_id> --payload '{}'
-ae-cli analysis exchange rule-validate --dry-run
+ae-cli analysis-meta exchange rule-validate --project-id <project_id> --payload '{}'
+ae-cli analysis-meta exchange rule-validate --dry-run
 ```
 
 Capability id: `metadata.exchange_rule.validate`.

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

@@ -1,15 +1,27 @@
-# analysis folder create
+# analysis folder create (L3)
 
-Use when the user explicitly wants to create a folder in personal space or a project space.
+Use when the user wants to create a folder in personal space or project space.
 
-Do not use to create a project space. Use `project-space create`.
+Do not use to create a project space. Use `analysis.project_space.create` via capability run.
 
-Command:
+This capability has no curated `ae-cli analysis` command. Read [`ae-capability`](../../ae-capability/SKILL.md), then:
 
 ```bash
-ae-cli analysis folder create --project-id <project_id> --folder-name <name> [--space-id <space_id>] [--parent-folder-id <folder_id>] [--payload '{...}'] --yes
+ae-cli capability inspect analysis.folder.create
+ae-cli capability dry-run analysis.folder.create --input '{"project_id":1,"folder_name":"Weekly","space_id":10}'
+ae-cli capability run analysis.folder.create --input '{"project_id":1,"folder_name":"Weekly","space_id":10}'
 ```
 
-Input sends `project_id`, `folder_name`, and optional `space_id`, `parent_folder_id`, `payload`.
+`risk=write` — no chat confirmation required after dry-run succeeds.
+
+Input uses snake_case JSON. Common fields:
+
+| field | type | required | description |
+| --- | --- | --- | --- |
+| `project_id` | integer | yes | Project ID. |
+| `folder_name` | string | no | Folder name. |
+| `space_id` | integer | no | Project space ID. Omit for personal-space folders. |
+| `parent_folder_id` | integer | no | Parent project-space folder ID. |
+| `payload` | object | no | Optional snake_case object for complex create payloads. |
 
 Output is the gateway envelope. `data` contains the created folder result.

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

@@ -1,15 +1,30 @@
-# analysis folder delete
+# analysis folder delete (L3)
 
-Use when the user explicitly wants to delete one or more folders.
+Use when the user wants to delete one or more folders.
 
-Do not use for deleting dashboards or BI panels inside a folder. Use the asset delete command.
+This capability has no curated `ae-cli analysis` command. Read [`ae-capability`](../../ae-capability/SKILL.md) High-Risk Confirmation Workflow, then:
 
-Command:
+**Phase 1 — preview:**
 
 ```bash
-ae-cli analysis folder delete --project-id <project_id> [--folder-id <folder_id>] [--folder-ids '[1,2]'] [--space-id <space_id>] --yes
+ae-cli capability inspect analysis.folder.delete
+ae-cli capability dry-run analysis.folder.delete --input '{"project_id":1,"folder_ids":[1001,1002]}'
 ```
 
-Input sends `project_id`, either `folder_id` or `folder_ids`, and optional `space_id`.
+Summarize capability ID, target folder IDs, and `risk=high-risk-write` in chat. Ask the user to confirm.
+
+**Phase 2 — execute (only after explicit user confirmation):**
+
+```bash
+ae-cli capability run analysis.folder.delete --input '{"project_id":1,"folder_ids":[1001,1002]}' --yes
+```
+
+Input uses snake_case JSON. Common fields:
+
+| field | type | required | description |
+| --- | --- | --- | --- |
+| `project_id` | integer | yes | Project ID. |
+| `folder_id` | integer | no | Single folder ID. |
+| `folder_ids` | integer[] | no | Batch folder IDs. |
 
 Output is the gateway envelope. `data` contains the delete result.

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

@@ -1,15 +1,25 @@
-# analysis folder share
+# analysis folder share (L3)
 
-Use when the user wants to add, remove, or batch modify folder sharing members.
+Use when the user wants to modify folder sharing members.
 
-Do not use to inspect members only. Use `folder members`.
+Do not use to inspect members only. Use `analysis.folder.members` via `capability search/inspect/run`; see [`analysis_gateway_assets.md`](analysis_gateway_assets.md) L3 members section.
 
-Command:
+This capability has no curated `ae-cli analysis` command. Read [`ae-capability`](../../ae-capability/SKILL.md), then:
 
 ```bash
-ae-cli analysis folder share --project-id <project_id> --folder-id <folder_id> [--payload '{...}'] --yes
+ae-cli capability inspect analysis.folder.share
+ae-cli capability dry-run analysis.folder.share --input '{"project_id":1,"folder_id":1001,"payload":{...}}'
+ae-cli capability run analysis.folder.share --input '{"project_id":1,"folder_id":1001,"payload":{...}}'
 ```
 
-Input sends `project_id`, `folder_id`, and backend-compatible snake_case `payload`.
+`risk=write` — no chat confirmation required after dry-run succeeds.
+
+Input uses snake_case JSON. Common fields:
+
+| field | type | required | description |
+| --- | --- | --- | --- |
+| `project_id` | integer | yes | Project ID. |
+| `folder_id` | integer | yes | Folder ID. |
+| `payload` | object | no | Optional snake_case share/member update payload. Inspect the capability schema before composing it. |
 
 Output is the gateway envelope. `data` contains the share update result.

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

@@ -6,49 +6,48 @@ Domain: **Model schema queries**
 
 > **CRITICAL - Builder-supported ad hoc models**
 >
-> Do **not** use this tool for natural-language ad hoc requests whose target model is `event`, `retention`, `funnel`, or `prop_analysis`.
-> For those four models, use the matching QP builder first:
-> `+build_event_analysis_qp`, `+build_retention_analysis_qp`, `+build_funnel_analysis_qp`, or `+build_prop_analysis_qp`, then `+query_adhoc`.
+> Do **not** use this tool for natural-language non-SQL ad hoc requests.
+> All ten non-SQL models have matching QP builders; use the builder first, then `+query_adhoc`.
 >
 > If a builder returns `need_clarification`, `invalid_argument`, `unsupported_feature`, or `validation_error`, stop and ask the user or report the structured error. Do not fall back to this schema tool.
 
 > **CRITICAL - Step-by-Step Execution (BLOCKING)**
 >
-> This blocking sequence applies only to non-builder/manual model paths such as `distribution`, `attribution`, `heat_map`, `interval`, `path`, `rank_list`, or `sql`.
+> This blocking sequence applies only to the SQL manual path.
 > **You MUST execute these steps in order. Do NOT skip any step.**
 >
 > | Step | Command | When to proceed |
 > |------|---------|-----------------|
-> | **Step 1 (MANUAL PATH ONLY)** | `--model_type <type>` **without `--segments`** | Execute first only for non-builder/manual models. Review result. |
+> | **Step 1 (MANUAL PATH ONLY)** | `--model_type sql` **without `--segments`** | Execute first only for SQL. Review result. |
 > | **Step 2 (OPTIONAL)** | Add `--segments 'filter_group'` | Only if Step 1 result lacks filter/groupBy structures AND you need them |
 > | **Step 3 (OPTIONAL)** | Add `--segments 'examples'` | Only if Step 1+2 insufficient for multi-metric, time comparison, formulas |
 >
-> **WRONG:** `ae-cli analysis +get_analysis_query_schema --model_type distribution --segments 'examples'` ← **Never start here!**
-> **RIGHT:** `ae-cli analysis +get_analysis_query_schema --model_type distribution` → review → add segments if needed
+> **WRONG:** `ae-cli analysis +get_analysis_query_schema --model_type sql --segments 'examples'` ← **Never start here!**
+> **RIGHT:** `ae-cli analysis +get_analysis_query_schema --model_type sql` → review → add segments if needed
 
 ## Pre-call Checklist (Execute in Order)
 
-0. ✓ **Builder-supported model?** → If `event`/`retention`/`funnel`/`prop_analysis`, stop using this tool and use the matching builder.
+0. ✓ **Builder-supported model?** → If non-SQL, stop using this tool and use the matching builder.
 1. ✓ **Step 1 completed?** → Review core schema
 2. ✓ **Gap identified?** → Justify need (e.g., "need filter_group structure")
 3. ✓ **Justified?** → Call again with specific segment
 
-**Rule**: For non-builder/manual models, uncertain → execute Step 1 first. For `event`, `retention`, `funnel`, or `prop_analysis`, uncertain → read the matching builder reference first.
+**Rule**: For SQL, uncertain → execute Step 1 first. For non-SQL models, uncertain → read the matching builder reference first.
 
 ## Command (Execute in Order)
 
 ```bash
-# Step 1: start here only for non-builder/manual models (no segments)
-ae-cli analysis +get_analysis_query_schema --model_type distribution
+# Step 1: start here only for SQL (no segments)
+ae-cli analysis +get_analysis_query_schema --model_type sql
 
 # Step 2: Only after Step 1, if filter/groupBy needed
-ae-cli analysis +get_analysis_query_schema --model_type distribution --segments 'filter_group' --include_core false
+ae-cli analysis +get_analysis_query_schema --model_type sql --segments 'filter_group' --include_core false
 
 # Step 3: Only after Step 1/2, for complex scenarios
-ae-cli analysis +get_analysis_query_schema --model_type distribution --segments 'examples' --include_core false
+ae-cli analysis +get_analysis_query_schema --model_type sql --segments 'examples' --include_core false
 
 # Follow-up request (already have core from earlier step in same session)
-ae-cli analysis +get_analysis_query_schema --model_type distribution --segments 'examples' --include_core false
+ae-cli analysis +get_analysis_query_schema --model_type sql --segments 'examples' --include_core false
 ```
 
 ## Parameters
@@ -63,10 +62,10 @@ ae-cli analysis +get_analysis_query_schema --model_type distribution --segments
 
 | 场景 | 参数 | 执行顺序 |
 |---|---|---|
-| Builder 支持模型 | 不适用 | `event`/`retention`/`funnel`/`prop_analysis` 禁止用此工具作为 QP 准备步骤，改用 builder |
-| 简单 | 不传 `--segments` | **Step 1** - 非 builder/manual 模型 |
-| 中等 | `--segments 'filter_group'` | **Step 2** - 非 builder/manual 模型，有过滤或分组，需先完成 Step 1 |
-| 复杂 | `--segments 'examples'` | **Step 3** - 非 builder/manual 模型，需先完成 Step 1 |
+| Builder 支持模型 | 不适用 | 所有非 SQL 模型禁止用此工具作为 QP 准备步骤，改用 builder |
+| 简单 | 不传 `--segments` | **Step 1** - SQL manual path |
+| 中等 | `--segments 'filter_group'` | **Step 2** - SQL manual path，有过滤或分组，需先完成 Step 1 |
+| 复杂 | `--segments 'examples'` | **Step 3** - SQL manual path，需先完成 Step 1 |
 
 ## Next Steps on Failure
 - Verify model type and segment compatibility (e.g., aggregatetype not for funnel/path/interval/sql)

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

@@ -6,7 +6,7 @@ Domain: **Report Management**
 
 ## Constraints
 
-**Not a builder fallback:** Do not call `+get_report_definition` to repair or replace a failed `+build_event_analysis_qp`, `+build_retention_analysis_qp`, `+build_funnel_analysis_qp`, or `+build_prop_analysis_qp` call. For builder-supported ad-hoc analysis, builder failure means stop and ask for clarification or report the structured error.
+**Not a builder fallback:** Do not call `+get_report_definition` to repair or replace a failed non-SQL QP builder call. Builder failure means stop and ask for clarification or report the structured error.
 
 ## Use Cases
 - Get the definition details of a single report. Returns model type, event configuration, display configuration, and other definition data without executing a data query.