@thinkingai/ae-cli 6.1.20 → 6.1.23

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

@@ -7,19 +7,18 @@ Do not use it for general asset information or query execution; it exports SQL d
 Command:
 
 ```bash
-ae-cli analysis-governance asset batch-sql-export --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset batch-sql-export --dry-run --project-id <project_id>
+ae-cli analysis-governance asset batch-sql-export --project-id <project_id> --node-ids '["<node_id>"]'
 ```
 
-Capability id: analysis_meta.asset_batch.sql_export.
+Capability id: governance.asset.batch_export_sql.
 
-Input sends project_id, payload, node_ids, reports_version, zone_offset, schedule_ui_config, dashboard_status, refresh_type, cache_config, clear_history_tag. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends `project_id` and `node_ids`. Optional `request_id`, `format` (only `xlsx`), and `timeout_seconds` (1..7200, default 3600) may be supplied through `--payload`. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
-Output `data` is an async XLSX descriptor with `run_id`, `artifact_id`, status, and expiry fields. Reuse those IDs for lifecycle inspection and download.
+Output `data` is an async XLSX descriptor with `run_id`, `artifact_id`, status, and expiry fields. This command has no `--output` flag. Wait and download with `ae-cli analysis run wait --run-id <run_id> --output <file>` using the returned run ID; see [`run_wait.md`](run_wait.md).
 
 ## Parameters
 | Parameter | Required | Description |
 |---|---|---|
 | --project-id | Yes | Numeric project ID. |
 | --node-ids | No | Asset node ID JSON array; required unless provided inside payload. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. `node_ids` is a non-empty string array. Optional export fields are `request_id`, `format`, and `timeout_seconds`. |

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

@@ -7,13 +7,12 @@ Do not use it for downstream impact or a full lineage tree; this command pages d
 Command:
 
 ```bash
-ae-cli analysis-governance asset-dependency list --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset-dependency list --dry-run --project-id <project_id>
+ae-cli analysis-governance asset-dependency list --project-id <project_id> --node-id <node_id>
 ```
 
-Capability id: analysis_meta.asset_dependency.list.
+Capability id: governance.asset_dependency.list.
 
-Input sends project_id, payload, node_id, query, searchs, rule, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends project_id, node_id, query, searchs, rule, limit, offset. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
 Output `data` contains dependency `items`, `total`, `operation_types`, `limit`, and `offset`; continue paging only while the observed total exceeds the current page.
 
@@ -27,4 +26,4 @@ Output `data` contains dependency `items`, `total`, `operation_types`, `limit`,
 | --rule | No | Advanced governance Filter JSON. |
 | --limit | No | Inline page size. |
 | --offset | No | Zero-based page offset. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. `node_ids`, `searchs`, and `status` are arrays; `rule` is an object when supplied. |

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

@@ -7,13 +7,12 @@ Do not use it for a small interactive preview; use `asset list` when bounded inl
 Command:
 
 ```bash
-ae-cli analysis-governance asset export --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset export --dry-run --project-id <project_id>
+ae-cli analysis-governance asset export --project-id <project_id>
 ```
 
-Capability id: analysis_meta.asset_usage.export.
+Capability id: governance.asset.export.
 
-Input sends project_id, payload, query, searchs, rule, operation_type, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends project_id, query, searchs, rule, operation_type, limit, offset. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
 Output `data` is an async export descriptor with `run_id`, `artifact_id`, status, and expiry fields. Inspect and download that exact artifact rather than resubmitting the export.
 
@@ -27,4 +26,4 @@ Output `data` is an async export descriptor with `run_id`, `artifact_id`, status
 | --operation-type | No | Batch operation type filter. |
 | --limit | No | Inline page size. |
 | --offset | No | Zero-based page offset. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. `node_ids`, `searchs`, and `status` are arrays; `rule` is an object when supplied. |

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

@@ -7,24 +7,20 @@ Do not use it for upstream dependencies or a full lineage tree; this command pag
 Command:
 
 ```bash
-ae-cli analysis-governance asset-impact list --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset-impact list --dry-run --project-id <project_id>
+ae-cli analysis-governance asset-impact list --project-id <project_id> --node-id <node_id>
 ```
 
-Capability id: analysis_meta.asset_impact.list.
+Capability id: governance.asset_impact.list.
 
-Input sends project_id, payload, node_id, query, searchs, rule, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends `project_id`, `node_id`, and optional `limit` and `offset`. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
-Output `data` contains impacted-asset `items`, `total`, `operation_types`, `limit`, and `offset`; an empty page means no downstream impact matched the filters.
+Output `data` contains impacted-asset `items`, `total`, `operation_types`, `limit`, and `offset`; an empty page means no downstream consumers in the selected scope.
 
 ## Parameters
 | Parameter | Required | Description |
 |---|---|---|
 | --project-id | Yes | Numeric project ID. |
 | --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
-| --query | No | Keyword filter. |
-| --searchs | No | Quick filter JSON array. |
-| --rule | No | Advanced governance Filter JSON. |
 | --limit | No | Inline page size. |
 | --offset | No | Zero-based page offset. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. Supported business fields are `node_id`, `limit`, and `offset`. |

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

@@ -2,18 +2,17 @@
 
 Use when the user needs to get an asset lineage tree through the capability gateway.
 
-Do not use it for a flat upstream or downstream page; use `dependency-list` or `impact-list` when pagination and filtering are required.
+Do not use it for a flat upstream or downstream page; use `asset-dependency list` or `asset-impact list` when pagination and filtering are required.
 
 Command:
 
 ```bash
-ae-cli analysis-governance asset-lineage get --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset-lineage get --dry-run --project-id <project_id>
+ae-cli analysis-governance asset-lineage get --project-id <project_id> --node-id <node_id>
 ```
 
-Capability id: analysis_meta.asset_lineage.get.
+Capability id: governance.asset_lineage.get.
 
-Input sends project_id, payload, node_id. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends project_id, node_id. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
 Output `data` is the lineage tree rooted at the requested `node_id`; an absent node is an asset-resolution failure, not an empty lineage result.
 
@@ -22,4 +21,4 @@ Output `data` is the lineage tree rooted at the requested `node_id`; an absent n
 |---|---|---|
 | --project-id | Yes | Numeric project ID. |
 | --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. `node_ids`, `searchs`, and `status` are arrays; `rule` is an object when supplied. |

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

@@ -7,13 +7,12 @@ Do not use it for report/dashboard result data or lineage; it lists governance r
 Command:
 
 ```bash
-ae-cli analysis-governance asset list --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset list --dry-run --project-id <project_id>
+ae-cli analysis-governance asset list --project-id <project_id>
 ```
 
-Capability id: analysis_meta.asset_usage.list.
+Capability id: governance.asset.list.
 
-Input sends project_id, payload, query, searchs, rule, operation_type, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends project_id, query, searchs, rule, operation_type, limit, offset. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
 Output `data` contains `items`, `total`, `operation_types`, `limit`, and `offset`. An empty `items` array is a successful page with no matching governed assets.
 
@@ -27,4 +26,4 @@ Output `data` contains `items`, `total`, `operation_types`, `limit`, and `offset
 | --operation-type | No | Batch operation type filter. |
 | --limit | No | Inline page size. |
 | --offset | No | Zero-based page offset. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. `node_ids`, `searchs`, and `status` are arrays; `rule` is an object when supplied. |

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

@@ -7,13 +7,12 @@ Do not use it to execute or inspect an analysis query; it only pages historical
 Command:
 
 ```bash
-ae-cli analysis-governance asset-query-history list --project-id <project_id> --payload '{}'
-ae-cli analysis-governance asset-query-history list --dry-run --project-id <project_id>
+ae-cli analysis-governance asset-query-history list --project-id <project_id> --node-id <node_id>
 ```
 
-Capability id: analysis_meta.asset_query_history.list.
+Capability id: governance.asset_query_history.list.
 
-Input sends project_id, payload, node_id, query, searchs, rule, limit, offset. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends `project_id`, `node_id`, and optional `limit` and `offset`. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
 Output `data` contains query-history `items`, `total`, `operation_types`, `limit`, and `offset`; treat an empty history as a successful no-usage result.
 
@@ -22,9 +21,6 @@ Output `data` contains query-history `items`, `total`, `operation_types`, `limit
 |---|---|---|
 | --project-id | Yes | Numeric project ID. |
 | --node-id | No | Poseidon asset node ID; required unless provided inside payload. |
-| --query | No | Keyword filter. |
-| --searchs | No | Quick filter JSON array. |
-| --rule | No | Advanced governance Filter JSON. |
 | --limit | No | Inline page size. |
 | --offset | No | Zero-based page offset. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. Supported business fields are `node_id`, `limit`, and `offset`. |

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

@@ -8,7 +8,6 @@ Command:
 
 ```bash
 ae-cli analysis-meta asset recent-list --project-id <project_id> --payload '[{"res_id":<resource_id>,"res_cat":"<resource_category>"}]'
-ae-cli analysis-meta asset recent-list --dry-run
 ```
 
 Capability id: `metadata.asset.recent_list`.

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

@@ -1,26 +1,29 @@
-# analysis-meta asset search
+# analysis asset search
 
-Use when the user needs to search project assets by keyword.
+Use when the user needs to search visible saved analysis assets by keyword.
 
-Do not use it to query report/dashboard result data; it discovers asset records only.
+For first-pass asset discovery, do not pass `--asset-types`. The default intentionally searches both analysis dashboards and reports together, so the agent does not miss a relevant dashboard after guessing report-only, or miss a relevant report after guessing dashboard-only. Pass `--asset-types` only when the user explicitly asks for one type or when refining after a broad search.
+
+Do not use it to query report/dashboard result data; it discovers saved report and analysis dashboard records only. It does not return metrics, events, properties, clusters, tags, alerts, or BI dashboards.
 
 Command:
 
 ```bash
-ae-cli analysis-meta asset search --project-id <project_id> --payload '{"keyword":"revenue"}' --limit 50 --offset 0
-ae-cli analysis-meta asset search --dry-run
+ae-cli analysis asset search --project-id <project_id> --queries '["revenue"]' --limit 50 --offset 0
 ```
 
-Capability id: `metadata.asset.search`.
+Capability id: `analysis.asset.search`.
 
-Input sends `project_id`, `payload`, `limit`, and `offset`.
+Input sends `project_id`, `queries`, optional `asset_types`, optional `own_types`, `limit`, and `offset`. Omit `asset_types` by default for unified discovery.
 
-Output always uses the directory envelope: `data.items[]`, `total`, `limit`, `offset`, `has_more`, and `next_offset`. A blank keyword returns an empty envelope rather than a full asset list.
+Output always uses the directory envelope: `data.items[]`, `total`, `limit`, `offset`, `has_more`, and `next_offset`, plus `searched_asset_types` and `counts_by_type`.
 
 ## Parameters
 | Parameter | Required | Description |
 |---|---|---|
 | `--project-id` | Yes | Numeric project ID. |
-| `--payload` | Yes | Search object. Required semantic field: non-blank `keyword`. Optional filters are `own_types` and `res_cats`; do not pass server-owned identity or pagination-test fields. |
+| `--queries` | Yes | JSON array of 1 to 20 keyword filters. Search is OR across keywords. |
+| `--asset-types` | No | JSON array containing `dashboard`, `report`, or both. Omit by default for first-pass discovery so the same query searches both dashboards and reports. |
+| `--own-types` | No | JSON array containing `CREATED`, `SHARED`, or both. |
 | `--limit` / `-l` | No | Page size. Default: 50, maximum: 200. |
 | `--offset` / `-o` | No | Zero-based page offset. Default: 0. |

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

@@ -7,14 +7,13 @@ Do not use it to discover assets or query asset data; resolve a real asset first
 Command:
 
 ```bash
-ae-cli analysis-meta asset url-get --project-id <project_id> --payload '{}'
+ae-cli analysis-meta asset url-get --project-id <project_id> --node-id <node_id>
 ae-cli analysis-meta asset url-get --project-id <project_id> --resource-type dashboard --resource-id 1
-ae-cli analysis-meta asset url-get --dry-run --project-id <project_id>
 ```
 
 Capability id: analysis_meta.asset_url.get.
 
-Input sends project_id, payload, node_id, resource_id, resource_type, link_info. Payload keys must follow the common-service snake_case input schema; do not send camelCase aliases.
+Input sends project_id, node_id, resource_id, resource_type, link_info. The CLI merges the snake_case object from `--payload` into these top-level Gateway fields; explicit flags override matching payload fields. `--project-id` owns the project identity and cannot be supplied or overridden by payload. Required business fields must exist in the final merged input.
 
 Output `data` identifies the normalized asset and returns `raw_url` plus `markdown_link` when the resource type supports a link. ae-cli rewrites relative URL/link fields into absolute URLs using the current host. `status=ok` without a URL means no URL mapping was available.
 
@@ -26,4 +25,4 @@ Output `data` identifies the normalized asset and returns `raw_url` plus `markdo
 | --resource-id | No | Asset business resource ID. |
 | --resource-type | No | Asset resource type. |
 | --link-info | No | link_info JSON from asset governance results. |
-| --payload | No | Optional snake_case object carrying the same fields. Use this for complex governance filters or backend-shaped payloads. |
+| --payload | No | Optional JSON object merged into top-level input. Use schema-declared snake_case fields; explicit flags take precedence. `node_ids`, `searchs`, and `status` are arrays; `rule` is an object when supplied. |

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

@@ -7,9 +7,9 @@ Do not use to create a blank BI panel. Use `bi-panel create`.
 Command:
 
 ```bash
-ae-cli analysis bi-panel copy --project-id <project_id> [--panel-name <name>] [--panel-uuid <source_uuid>] [--space-id <space_id>] [--folder-id <folder_id>] [--payload '{...}']
+ae-cli analysis bi-panel copy --project-id <project_id> --panel-name <name> --panel-uuid <source_uuid> [--space-id <space_id>] [--folder-id <folder_id>] [--payload '{...}']
 ```
 
-Input sends `project_id`, optional source/target fields, and `payload`.
+Input requires `project_id`, source `panel_uuid`, and target `panel_name` through their explicit flags. Optional `space_id`, `folder_id`, and `payload` retain their documented destination fields.
 
 Output is the gateway envelope. `data` contains the copied BI panel result.

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

@@ -2,28 +2,20 @@
 
 Use for BI panel page data that may be large or long-running.
 
-Routing: read [`analysis_data_retrieval.md`](analysis_data_retrieval.md) before choosing this `export` command instead of `bi-panel-page-data run`.
+For full data, read [export handling](analysis_data_export.md) and use this `export` command instead of `bi-panel-page-data run`.
 
 Do not use this command for bounded inline previews; use `bi-panel-page-data run` when the requested result fits the sync data retrieval rule.
 
 Command:
 
 ```bash
-ae-cli analysis bi-panel-page-data export --project-id <project_id> --panel-id <panel_id> --page-key <page_key> --result-type charts [--chart-ids '["chart1"]'] [--artifact-format jsonl]
+ae-cli analysis bi-panel-page-data export --project-id <project_id> --panel-id <panel_id> --page-key <page_key> --result-type charts [--chart-ids '["chart1"]'] [--artifact-format jsonl] --output <file>
 ```
 
 Input sends `project_id`, `panel_id`, `page_key`, `result_type=charts`, and optional chart, control, column, cache, request, timeout, and format fields. Use CLI flag `--artifact-format` for the gateway `format` input; `--format` is the CLI output formatter. The export does not accept row/block paging fields: Common streams chart rows directly and applies only `model_full_download_limit`. Runtime defaults to and is capped at 21600 seconds (6 hours); cancel earlier with `analysis query cancel --run-id <run_id>`. BI summary is rendered presentation data; query it with `bi-panel-page-data run`.
 
-Output is the gateway envelope. `data` contains an async export descriptor with `run_id`, `artifact_id`, status fields, and expiration fields. It does not create `query_context_id` or expose inspect/download API paths; use the CLI commands below.
+Output is the gateway envelope. `data` contains an async export descriptor with `run_id`, `artifact_id`, status fields, and expiration fields. It does not create `query_context_id`. The CLI handles waiting and download with `--output`.
 
 BI chart sources are SQL and do not support analysis drilldown or result-cluster creation. Exported rows are not interactive coordinates.
 
-Follow-up workflow:
-
-1. Save `data.run_id` and `data.artifact_id` from the export response.
-2. Poll status with `ae-cli analysis run inspect --run-id <run_id>`.
-3. Continue polling while status is running or pending. Treat `COMPLETED` or `SUCCEEDED` as success, and `FAILED`, `CANCELED`, or `CANCELLED` as terminal failure.
-4. On success, download with `ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>`.
-5. If the export is no longer needed, cancel with `ae-cli analysis query cancel --run-id <run_id>`.
-
-Do not write custom Python/curl for polling or download unless the CLI command itself is unavailable.
+Use `--output` to wait and download the completed artifact. If interrupted, resume with `ae-cli analysis run wait --run-id <run_id> --output <file>` using the same export response. See [`run_wait.md`](run_wait.md).

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

@@ -17,3 +17,5 @@ Input sends `project_id`, `panel_id`, `page_key`, `result_type`, and optional co
 Output is the gateway envelope. `data` contains bounded inline page data.
 
 BI page/chart sources are SQL and do not support analysis drilldown or result-cluster creation. Do not call model drilldown commands from this result.
+
+For `--result-type charts`, `--preview-rows` applies per chart; configured chart top-N remains part of its semantics. Summary is presentation data, available only from `run`, and rejects `--preview-rows`. BI SQL results do not support analysis drilldown.

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

@@ -1,28 +1,15 @@
 # analysis-meta catalog export
 
-## Use
-
-Export the complete permission-filtered analysis metadata catalog for conversation-local reuse.
-
-Do not use it for ordinary discovery, bounded search, or when compiler candidates already exist; use `catalog list` for the one aggregate online search.
+Use this command to export one complete, permission-filtered analysis metadata JSONL when the task requires the complete directory, including an explicit complete no-match check. Do not use it again when the current conversation already has a successful export for this project and environment. Follow [`metadata_resolution.md`](metadata_resolution.md) for discovery and confirmation.
 
 ```bash
 ae-cli analysis-meta catalog export \
   --project-id <project_id> \
-  --output <conversation_catalog_dir>/catalog.jsonl
+  --output ./analysis-meta-catalog-project-<project_id>.jsonl
 ```
 
 Capability id: `metadata.catalog.export`.
 
-## Input
-
-The gateway input contains only `project_id`. The response must contain every accessible event, metric, event property, user property, cluster, and tag row with `complete=true` and `total` equal to the row count.
-
-## Output
-
-The CLI validates completeness, publishes the JSONL atomically with mode `0600`, and writes the adjacent `catalog.meta.json` last. Search the file locally and keep full rows out of model context. Reuse a valid snapshot only for the same host, project, principal, and conversation.
+Input: `--project-id` selects the project. `--output` is the required `.jsonl` path and implies waiting for export completion. The CLI streams the download and publishes the finished file with mode `0600`. An existing output is rejected unless replacement is requested with `--force`; a failed download preserves the existing file.
 
-| Parameter | Required | Description |
-|---|---|---|
-| `--project-id` | Yes | Numeric project ID. |
-| `--output` | Yes | Conversation-local `.jsonl` path. |
+Output: success returns the run/artifact descriptor plus `output_path`, `format: "jsonl"`, `row_count`, `bytes` and `complete: true`. Search the returned absolute path locally. The rows cover accessible events, metrics, event/user properties, clusters and tags.

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

@@ -1,8 +1,8 @@
 # analysis-meta catalog list
 
-Use only for a structured AI-QP metadata compile failure that requires one aggregate online search across selected resource types.
+Use for a metadata lookup across selected resource types when their definitions or identities are still missing.
 
-Do not use it for ordinary asset discovery or when the compiler already returned candidates. Follow [`../metadata_resolution.md`](../metadata_resolution.md).
+Reuse known candidates or search an existing project catalog locally. Do not use it to search saved reports; use `analysis report list`. Follow [`metadata_resolution.md`](metadata_resolution.md).
 
 Online search:
 
@@ -22,7 +22,7 @@ Sends `project_id`, `queries`, `resource_types`, and optional `limit_per_type`.
 
 ## Output
 
-Both modes return unified rows with:
+The response returns unified rows with:
 
 - `resource_type`: `event`, `metric`, `event_property`, `user_property`, `cluster`, or `tag`
 - `resource_key`: canonical server-defined identifier
@@ -41,4 +41,4 @@ Online rows also contain `matched_query`, `matched_field`, and `match_type`. Res
 | `--queries` | Online mode | JSON array of 1–20 deduplicated keywords, OR matched. |
 | `--resource-types` | Online mode | JSON array containing only `event`, `metric`, `event_property`, `user_property`, `cluster`, or `tag`. |
 | `--limit-per-type` | No | Online result limit per selected resource type; default 20, maximum 200. |
-Use at most one online search for the complete compiler error array. If every path gets candidates, ask for confirmation. If any path remains empty, use [`catalog_export.md`](catalog_export.md) once.
+Use the task's terms and relevant English words in the same batch, deduplicated; split only when more than 20 are needed. Match applies literally to `resource_key`, `display_name` and `remark`, without automatic translation. Suitable candidates advance to definition inspection or confirmation. A missing match does not imply metadata is absent; choose the next lookup for the specific missing information. [Catalog export](catalog_export.md) is for complete-directory requests.

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

@@ -1,8 +1,6 @@
 # tracking check delete
 
-Use when delete one tracking validation run.
-
-Do not use for commands listed under the sheet's non-CLI section or for unrelated metadata/report operations. If the command needs a complex JSON object, read the backend schema or existing asset first and send snake_case fields only.
+Use only when the user asks to delete one tracking validation run.
 
 Command:
 
@@ -16,12 +14,12 @@ Capability id: `tracking.check.delete`
 
 Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Delete also sends `yes` from `--confirm`. Do not send camelCase aliases.
 
-Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`. Export commands return lifecycle data such as `run_id` and `artifact_id` for inspect/download.
+Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`.
 
 Parameters:
 
 | Parameter | Description | Required |
 | --- | --- | --- |
-| `--project-id` | See command help | Yes |
-| `--uuid` | See command help | Yes |
-| `--confirm` | See command help | Yes |
+| `--project-id` | Numeric project ID. | Yes |
+| `--uuid` | Tracking check task UUID. | Yes |
+| `--confirm` | Must be true for this destructive tracking operation. Also use global --yes to skip local confirmation. | Yes |

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

@@ -1,27 +1,27 @@
 # tracking check export
 
-Use when export one tracking validation result.
-
-Do not use for commands listed under the sheet's non-CLI section or for unrelated metadata/report operations. If the command needs a complex JSON object, read the backend schema or existing asset first and send snake_case fields only.
+Use only when the user asks to export one tracking validation result.
 
 Command:
 
 ```bash
-ae-cli tracking check export [options]
+ae-cli tracking check export --project-id <project_id> --uuid <uuid> --output <file>
 ```
 
 Capability id: `tracking.check.export`
 
-Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Delete also sends `yes` from `--confirm`. Do not send camelCase aliases.
+Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Do not send camelCase aliases.
+
+Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`.
 
-Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`. Export commands return lifecycle data such as `run_id` and `artifact_id` for inspect/download.
+Use `--output` to wait and download the completed artifact. To resume an interrupted export, use [`analysis run wait`](run_wait.md) with its returned `run_id`.
 
 Parameters:
 
 | Parameter | Description | Required |
 | --- | --- | --- |
-| `--project-id` | See command help | Yes |
-| `--uuid` | See command help | Yes |
-| `--request-id` | See command help | No |
-| `--async-timeout-seconds` | See command help | No |
-
+| `--project-id` | Numeric project ID. | Yes |
+| `--uuid` | Tracking check task UUID. | Yes |
+| `--request-id` | Optional caller-supplied cli_<32 lowercase hex> lifecycle ID. ae-cli generates and prints one before dispatch when omitted. | No |
+| `--timeout-seconds` | Async runtime in seconds. Default and max: 21600 (6 hours); cancel earlier with analysis query cancel --run-id <run_id>. | No |
+| `--output` | Wait and download to this local file. | No |

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

@@ -1,27 +1,25 @@
 # tracking check get
 
-Use when get one tracking validation result.
-
-Do not use for commands listed under the sheet's non-CLI section or for unrelated metadata/report operations. If the command needs a complex JSON object, read the backend schema or existing asset first and send snake_case fields only.
+Use only when the user asks to get one tracking validation result.
 
 Command:
 
 ```bash
-ae-cli tracking check get [options]
+ae-cli tracking check get --project-id <project_id> --uuid <uuid>
 ```
 
 Capability id: `tracking.check.get`
 
-Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Delete also sends `yes` from `--confirm`. Do not send camelCase aliases.
+Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Do not send camelCase aliases.
 
-Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`. Export commands return lifecycle data such as `run_id` and `artifact_id` for inspect/download.
+Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`.
 
 Parameters:
 
 | Parameter | Description | Required |
 | --- | --- | --- |
-| `--project-id` | See command help | Yes |
-| `--uuid` | See command help | Yes |
-| `--request-id` | See command help | No |
-| `--timeout-seconds` | See command help | No |
+| `--project-id` | Numeric project ID. | Yes |
+| `--uuid` | Tracking check task UUID. | Yes |
+| `--request-id` | Optional caller-supplied cli_<32 lowercase hex> lifecycle ID. ae-cli generates and prints one before dispatch when omitted. | No |
+| `--timeout-seconds` | Optional capability execution timeout in seconds. | No |
 

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

@@ -1,24 +1,22 @@
 # tracking check list
 
-Use when list tracking validation runs.
-
-Do not use for commands listed under the sheet's non-CLI section or for unrelated metadata/report operations. If the command needs a complex JSON object, read the backend schema or existing asset first and send snake_case fields only.
+Use only when the user asks to list tracking validation runs.
 
 Command:
 
 ```bash
-ae-cli tracking check list [options]
+ae-cli tracking check list --project-id <project_id>
 ```
 
 Capability id: `tracking.check.list`
 
 Input sends `project_id`. Do not send camelCase aliases.
 
-Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`. Export commands return lifecycle data such as `run_id` and `artifact_id` for inspect/download.
+Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`.
 
 Parameters:
 
 | Parameter | Description | Required |
 | --- | --- | --- |
-| `--project-id` | See command help | Yes |
+| `--project-id` | Numeric project ID. | Yes |
 

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

@@ -1,27 +1,25 @@
 # tracking check retry
 
-Use when retry one tracking validation run.
-
-Do not use for commands listed under the sheet's non-CLI section or for unrelated metadata/report operations. If the command needs a complex JSON object, read the backend schema or existing asset first and send snake_case fields only.
+Use only when the user asks to retry one tracking validation run.
 
 Command:
 
 ```bash
-ae-cli tracking check retry [options]
+ae-cli tracking check retry --project-id <project_id> --uuid <uuid>
 ```
 
 Capability id: `tracking.check.retry`
 
-Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Delete also sends `yes` from `--confirm`. Do not send camelCase aliases.
+Input sends `project_id`, `uuid`, and lifecycle fields when exposed. Do not send camelCase aliases.
 
-Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`. Export commands return lifecycle data such as `run_id` and `artifact_id` for inspect/download.
+Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`.
 
 Parameters:
 
 | Parameter | Description | Required |
 | --- | --- | --- |
-| `--project-id` | See command help | Yes |
-| `--uuid` | See command help | Yes |
-| `--request-id` | See command help | No |
-| `--timeout-seconds` | See command help | No |
+| `--project-id` | Numeric project ID. | Yes |
+| `--uuid` | Tracking check task UUID. | Yes |
+| `--request-id` | Optional caller-supplied cli_<32 lowercase hex> lifecycle ID. ae-cli generates and prints one before dispatch when omitted. | No |
+| `--timeout-seconds` | Optional capability execution timeout in seconds. | No |
 

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

@@ -1,8 +1,6 @@
 # tracking check run
 
-Use when run tracking plan validation.
-
-Do not use for commands listed under the sheet's non-CLI section or for unrelated metadata/report operations. If the command needs a complex JSON object, read the backend schema or existing asset first and send snake_case fields only.
+Use only when the user asks to run tracking plan validation.
 
 Command:
 
@@ -14,7 +12,7 @@ Capability id: `tracking.check.run`
 
 Input sends `project_id`, required `check_scope`, and optional `result_scope`. `check_scope` supports `check_data_types`, `start_time`, `end_time`, `check_events`, `event_filter`, `user_filter`, `has_empty_check`, and `prop_null_value_threshold`. `result_scope` supports `event_results` and `user_results`. Do not send camelCase aliases.
 
-Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`. Export commands return lifecycle data such as `run_id` and `artifact_id` for inspect/download.
+Output is the capability gateway envelope: success is `ok=true,data,meta`; failure is `ok=false,error`.
 
 Parameters: