@thinkingai/ae-cli 6.0.24 → 6.0.27

package/skills/ae-agent/references/upload-skill-reference.md

@@ -0,0 +1,51 @@
+# agent +upload-skill-reference (Upload Skill Reference)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Upload a single `.md` file to a Skill's `references` directory (multipart upload).
+- Endpoint: `POST /api/sandbox/agent/skills/[id]/references` (multipart/form-data).
+- Max file size: 1MB per file.
+- **Only `.md` files are allowed** — other extensions are rejected.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- `--file` is required, must be an existing local `.md` file.
+- Non-`.md` files are rejected — use `+upload-skill-asset` for other file types.
+- Max 1MB per file; server enforces `isDangerousFile` checks.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+# Upload a single reference
+ae-cli agent +upload-skill-reference --id <skill-cuid> --file ./guide.md --yes
+
+# Upload to a sub-directory
+ae-cli agent +upload-skill-reference --id <skill-cuid> --file ./advanced.md --sub-path "advanced/" --yes
+
+# Dry-run to inspect the request before executing
+ae-cli agent +upload-skill-reference --dry-run --id <skill-cuid> --file ./guide.md
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+| `--file` | Yes | Local `.md` file path to upload (max 1MB) |
+| `--sub-path` | No | Sub-directory under references (e.g. `"advanced/"`) |
+
+## Decision Rules
+- Verify the file exists locally and has a `.md` extension before uploading.
+- For non-markdown files, use `+upload-skill-asset` instead.
+- Use `--sub-path` to organize references into sub-directories.
+- Use `--dry-run` first to verify the request shape before executing.
+
+## Next Steps on Failure
+- `File not found`: verify the local file path.
+- `--file must be a .md file for references`: use `+upload-skill-asset` for non-markdown files.
+- `文件过大（上限 1MB）`: the file exceeds the 1MB limit — split the markdown.
+
+## Recommended Chaining
+- `+list-skills` → `+list-skill-references` → `+upload-skill-reference` → `+list-skill-references` (verify)

package/skills/ae-agent/references/upload-skill-script.md

@@ -0,0 +1,49 @@
+# agent +upload-skill-script (Upload Skill Script)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Upload a single file to a Skill's `scripts` directory (multipart upload).
+- Endpoint: `POST /api/sandbox/agent/skills/[id]/scripts` (multipart/form-data).
+- Max file size: 1MB per file.
+- Dangerous file types are rejected server-side.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- `--file` is required and must point to an existing local file.
+- Max 1MB per file; server enforces `isDangerousFile` checks.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+# Upload a single script
+ae-cli agent +upload-skill-script --id <skill-cuid> --file ./helper.sh --yes
+
+# Upload to a sub-directory
+ae-cli agent +upload-skill-script --id <skill-cuid> --file ./run.py --sub-path "tools/" --yes
+
+# Dry-run to inspect the request before executing
+ae-cli agent +upload-skill-script --dry-run --id <skill-cuid> --file ./helper.sh
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+| `--file` | Yes | Local file path to upload (max 1MB) |
+| `--sub-path` | No | Sub-directory under scripts (e.g. `"tools/"`) |
+
+## Decision Rules
+- Verify the file exists locally before uploading.
+- Use `--sub-path` to organize scripts into sub-directories.
+- Use `--dry-run` first to verify the request shape before executing.
+
+## Next Steps on Failure
+- `File not found`: verify the local file path.
+- `文件过大（上限 1MB）`: the file exceeds the 1MB limit — compress or split it.
+- `禁止上传危险文件类型`: the file type is blocked by server-side security checks.
+
+## Recommended Chaining
+- `+list-skills` → `+list-skill-scripts` → `+upload-skill-script` → `+list-skill-scripts` (verify)

package/skills/ae-agent/references/upload-skill.md

@@ -0,0 +1,89 @@
+# agent +upload-skill (Upload ZIP Skill)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Upload a ZIP-format Skill package. The server parses SKILL.md from the ZIP, extracts files to the target directory, and writes the DB record.
+- Endpoint: `POST /api/sandbox/agent/skills/upload` (multipart/form-data, 120s timeout).
+- Supports form-field overrides for name, displayName, description, instructions, icon, category.
+- `--scope` controls target scope: `personal` (default) or `company`.
+- `--replace-skill-id` replaces an existing Skill instead of creating a new one.
+- `--auto-rename` auto-renames on name conflict.
+
+## Mandatory Rules (MUST)
+- `--file` is required and must be a `.zip` file that exists on disk.
+- The ZIP must contain a `SKILL.md` file (with name and content at minimum).
+- `--scope` must be `personal` or `company` (default `personal`).
+- `--category` must be one of the market category keys when provided.
+- `--instructions` supports `@-` to read from stdin.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Market Category Keys
+`ae_preset | dev_tool | search_tool | data_query | content_gen | enterprise | life | automation | other`
+
+## Command
+```bash
+# Upload a personal Skill from ZIP
+ae-cli agent +upload-skill --file ./my-skill.zip --yes
+
+# Upload with overrides
+ae-cli agent +upload-skill \
+  --file ./my-skill.zip \
+  --scope personal \
+  --name custom-name \
+  --display-name "Custom Skill" \
+  --description "Override description" \
+  --category dev_tool \
+  --icon-emoji robot \
+  --yes
+
+# Instructions from stdin
+echo "You are a helpful assistant..." | \
+  ae-cli agent +upload-skill --file ./my-skill.zip --instructions @- --yes
+
+# Replace an existing Skill
+ae-cli agent +upload-skill --file ./updated.zip --replace-skill-id <skill-cuid> --yes
+
+# Auto-rename on conflict
+ae-cli agent +upload-skill --file ./my-skill.zip --auto-rename --yes
+
+# Dry-run to inspect the request before executing
+ae-cli agent +upload-skill --dry-run --file ./my-skill.zip
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--file` | Yes | Local `.zip` file path |
+| `--scope` | No | Target scope: `personal` (default) or `company` |
+| `--auto-rename` | No | Auto-rename on name conflict |
+| `--replace-skill-id` | No | Replace an existing Skill (CUID) instead of creating new |
+| `--category` | No | Market category key (see above) |
+| `--name` | No | Override Skill name (from ZIP SKILL.md if omitted) |
+| `--display-name` | No | Override display name |
+| `--description` | No | Override description |
+| `--instructions` | No | Override instructions (use `@-` to read from stdin) |
+| `--icon-emoji` | No | Market icon emoji (e.g. `robot`) |
+| `--icon-color` | No | Market icon color (e.g. `#1E76F0`) |
+
+## Decision Rules
+- The ZIP must contain a `SKILL.md` with at least `name` and content — otherwise the upload fails with `missing_skill_md` or `missing_name_or_content`.
+- Form-field overrides take precedence over ZIP SKILL.md content.
+- Use `--replace-skill-id` to update an existing Skill's full content from a ZIP (different from `+edit-skill` which edits individual fields).
+- Use `--auto-rename` when the Skill name might conflict with an existing one.
+- `company` scope requires root privileges.
+- Use `--dry-run` first to verify the request shape before executing.
+
+## Next Steps on Failure
+- `File not found`: verify the local file path.
+- `--file must be a .zip file`: only ZIP format is supported.
+- `ZIP 中缺少 SKILL.md`: ensure the ZIP contains a `SKILL.md` file.
+- `缺少名称或内容`: the SKILL.md is missing the `name` field or content — fix the ZIP.
+- `缺少描述`: the SKILL.md is missing the description — fix the ZIP or use `--description`.
+- `数据库写入失败`: DB write failed — retry or check server logs.
+- `409` / name conflict: use `--auto-rename` or choose a different `--name`.
+
+## Recommended Chaining
+- `+upload-skill` → `+list-skills` (verify) → `+get-skill-content` (inspect) → `+edit-skill` (fine-tune) → `+submit-skill` (publish)

package/skills/ae-analysis/SKILL.md

@@ -72,6 +72,8 @@ ae-cli analysis dashboard list --project-id <project_id>
 ae-cli analysis dashboard get --project-id <project_id> --dashboard-id <dashboard_id>
 ae-cli analysis dashboard update --project-id <project_id> --operation settings --dashboard-id <dashboard_id> --payload '{...}'
 ae-cli analysis dashboard-report-data export --project-id <project_id> --dashboard-id <dashboard_id>
+ae-cli analysis run inspect --run-id <run_id>
+ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>
 ae-cli analysis bi-panel-page-data run --project-id <project_id> --panel-id <panel_id> --page-key <page_key> --result-type charts
 ae-cli analysis project-space list --project-id <project_id>
 ae-cli analysis query cancel --run-id <run_id>
@@ -97,7 +99,7 @@ Capability-gateway output:
 - Successful commands return the standard gateway envelope: `{ "ok": true, "data": ..., "meta": ... }`.
 - Failed commands return `{ "ok": false, "error": ... }` and exit non-zero.
 - Inline `run` data is bounded by `--limit` and `--timeout-seconds`.
-- Export commands return `run_id`, `artifact_id`, artifact status, inspect path, and download path. Use `--artifact-format jsonl` for the artifact format; `--format` is reserved for CLI output formatting. Cancel with `ae-cli analysis query cancel --run-id <run_id>`.
+- Export commands return `run_id`, `artifact_id`, status fields, and expiration fields. Use `--artifact-format jsonl` for the artifact format; `--format` is reserved for CLI output formatting. Poll with `ae-cli analysis run inspect --run-id <run_id>` until the run and artifact are complete, then download with `ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>`. Do not call raw inspect/download API paths directly. Cancel with `ae-cli analysis query cancel --run-id <run_id>`.
 - Unknown input fields and camelCase external fields are rejected by the gateway; use kebab-case CLI flags only.
 
 See [`references/analysis_gateway_assets.md`](references/analysis_gateway_assets.md) for the command matrix. Before running one command, read its dedicated reference file named as `<resource>_<action>.md`.
@@ -377,7 +379,7 @@ Reports:
 - `+update_report` ([doc](references/update_report.md))
 - `+delete_report` ([doc](references/delete_report.md))
 
-Dashboard, BI panel, project-space, folder, favorite, public-link, dashboard-definition, dashboard-daily-report, and dashboard/BI data commands are capability-gateway commands. Use `ae-cli analysis <resource> <action>` after reading [`references/analysis_gateway_assets.md`](references/analysis_gateway_assets.md); do not use old `+` dashboard/space/BI/public-link command names.
+Dashboard, BI panel, project-space, folder, favorite, public-link, dashboard-definition, dashboard-daily-report, run, artifact, and dashboard/BI data commands are capability-gateway commands. Use `ae-cli analysis <resource> <action>` after reading [`references/analysis_gateway_assets.md`](references/analysis_gateway_assets.md); do not use old `+` dashboard/space/BI/public-link command names.
 
 Model Analysis (17):
 - `+build_event_analysis_qp` ([doc](references/build_event_analysis_qp.md))

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

@@ -20,6 +20,8 @@ Prefer export commands for long-running or large data:
 
 ```bash
 ae-cli analysis dashboard-report-data export --project-id 1 --dashboard-id 1001
+ae-cli analysis run inspect --run-id run_0123456789abcdef0123456789abcdef
+ae-cli analysis artifact download --run-id run_0123456789abcdef0123456789abcdef --artifact-id artifact_0123456789abcdef0123456789abcdef --output /tmp/dashboard.jsonl.gz
 ae-cli analysis bi-panel-page-data export --project-id 1 --panel-id 2001 --page-key main --result-type charts
 ae-cli analysis query cancel --run-id run_0123456789abcdef0123456789abcdef
 ```
@@ -52,7 +54,17 @@ Failures return:
 }
 ```
 
-Export commands return `run_id`, `artifact_id`, `status`, `artifact_status`, `inspect_path`, `download_path`, `expires_at`, and `expires_at_iso`. Download the artifact through the returned path; cancel by `run_id`.
+Export commands return `run_id`, `artifact_id`, `status`, `artifact_status`, `expires_at`, and `expires_at_iso`. They do not expose raw inspect/download API paths.
+
+Artifact workflow:
+
+1. Submit an export command and keep `data.run_id` and `data.artifact_id`.
+2. Poll `ae-cli analysis run inspect --run-id <run_id>` every few seconds until `data.status` is terminal and `data.artifact_status` is complete.
+3. Terminal success is `COMPLETED` or `SUCCEEDED`; terminal failure is `FAILED`, `CANCELED`, or `CANCELLED`. On failure, report the returned error fields instead of downloading.
+4. Download with `ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>`.
+5. Cancel long or abandoned exports with `ae-cli analysis query cancel --run-id <run_id>`.
+
+Prefer the run/artifact commands over hand-written HTTP, Python, or curl. The descriptor paths are informational and may be internal `/api/cli/v1/...` paths behind a domain-routed CLI host.
 
 ## Command matrix
 
@@ -66,17 +78,19 @@ Export commands return `run_id`, `artifact_id`, `status`, `artifact_status`, `in
 | `dashboard share` | `analysis.dashboard.share` | Modify dashboard sharing | `--project-id`, `--dashboard-id`, `--payload` or `--member-authorities` | Share update result |
 | `dashboard delete` | `analysis.dashboard.delete` | Delete dashboards | `--project-id`, `--dashboard-ids '[...]'` | Delete result |
 | `dashboard handover` | `analysis.dashboard.handover` | Transfer dashboards | `--dashboard-ids`, `--to-user-id` | Handover result |
-| `dashboard copy` | `analysis.dashboard.copy` | Copy a dashboard | `--dashboard-id`, `--dashboard-name`, optional target IDs | Copied dashboard |
+| `dashboard copy` | `analysis.dashboard.copy` | Copy a dashboard; omitted target IDs copy to the source location | `--dashboard-id`, `--dashboard-name`, optional target IDs | Copied dashboard |
 | `dashboard freeze` | `analysis.dashboard.freeze` | Freeze/unfreeze dashboards | `--dashboard-ids`, optional `--freeze false` | Freeze status |
 | `dashboard abnormal-get` | `analysis.dashboard.abnormal_get` | Inspect abnormal dependencies | `--dashboard-id` | Abnormal info |
 | `dashboard task-status` | `analysis.dashboard.task_status` | Inspect scheduled task status | `--dashboard-id` | Task status |
 | `dashboard-report-data run` | `analysis.dashboard_report_data.run` | Bounded inline dashboard report data | `--dashboard-id`, optional `--report-ids`, `--start-time`, `--end-time`, `--limit` | Inline data |
 | `dashboard-report-data export` | `analysis.dashboard_report_data.export` | Large/long dashboard report data | same as run, plus optional `--artifact-format jsonl` | Async artifact descriptor |
+| `run inspect` | `analysis.run.inspect` | Poll async export status | `--run-id` | Run and artifact status |
+| `artifact download` | `analysis.artifact.download` | Download run-bound export artifact | `--run-id`, `--artifact-id`, `--output` | Local output file info |
 | `query cancel` | `analysis.query.cancel` | Cancel gateway run/export | `--run-id`, optional `--reason` | Cancellation result |
-| `dashboard-definition export` | `analysis.dashboard_definition.export` | Export dashboard definition JSON | `--dashboard-folder-ids`, `--shared-spaces`, or `--payload` | Definition JSON |
+| `dashboard-definition export` | `analysis.dashboard_definition.export` | Export dashboard definition JSON | `--dashboard-id`, `--dashboard-ids`, `--dashboard-folder-ids`, `--shared-spaces`, or `--payload` | Definition JSON |
 | `dashboard-definition import` | `analysis.dashboard_definition.import` | Validate/import dashboard definition | `--definition`, optional `--validate-only true` | Validation or import result |
-| `dashboard-daily-report update` | `analysis.dashboard_daily_report.update` | Update daily report config | `--dashboard-id`, optional config flags or `--payload` | Config result |
-| `dashboard-daily-report send` | `analysis.dashboard_daily_report.send` | Send daily report immediately | `--dashboard-id`, optional `--payload` | Async send result |
+| `dashboard-daily-report update` | `analysis.dashboard_daily_report.update` | Update daily report config; defaults are sent when `--payload` is absent | `--dashboard-id`, optional config flags or `--payload` | Config result |
+| `dashboard-daily-report send` | `analysis.dashboard_daily_report.send` | Send daily report immediately; defaults are sent when `--payload` is absent | `--dashboard-id`, optional config flags or `--payload` | Async send result |
 | `bi-panel list` | `analysis.bi_panel.list` | Find accessible BI panels | `--project-id`, optional list filters | Paginated BI panel summaries |
 | `bi-panel get` | `analysis.bi_panel.get` | Inspect released BI panel page structure | `--panel-id`, optional `--fields` | Panel structure |
 | `bi-panel create` | `analysis.bi_panel.create` | Create a BI panel | optional `--panel-name`, `--payload` | Created panel |
@@ -88,7 +102,7 @@ Export commands return `run_id`, `artifact_id`, `status`, `artifact_status`, `in
 | `bi-panel-page-data export` | `analysis.bi_panel_page_data.export` | Large/long BI page data | same as run, optional `--artifact-format jsonl` | Async artifact descriptor |
 | `project-space list` | `analysis.project_space.list` | Find accessible project spaces | `--project-id`, optional list filters | Paginated project spaces |
 | `project-space get` | `analysis.project_space.get` | Inspect one project space | `--project-id`, `--space-id` | Project space detail |
-| `project-space create` | `analysis.project_space.create` | Create a project space | `--space-name` or `--payload` | Created space |
+| `project-space create` | `analysis.project_space.create` | Create a project space; `avatar_type` defaults to 1 when omitted | `--space-name` or `--payload` | Created space |
 | `project-space delete` | `analysis.project_space.delete` | Delete project spaces | `--space-id` or `--space-ids` | Delete result |
 | `project-space share` | `analysis.project_space.share` | Modify project-space members | `--space-id`, `--payload` | Share update result |
 | `project-space members` | `analysis.project_space.members` | Read project-space members | `--space-id` | Members |
@@ -109,6 +123,7 @@ Export commands return `run_id`, `artifact_id`, `status`, `artifact_status`, `in
 ```bash
 ae-cli analysis dashboard list --project-id 1 --query retention --limit 20
 ae-cli analysis dashboard update --project-id 1 --operation note-upsert --dashboard-id 1001 --note-title "Summary" --description "Weekly note" --yes
+ae-cli analysis dashboard-definition export --project-id 1 --dashboard-id 1001 --export-file-name retention_dashboard
 ae-cli analysis dashboard-definition import --project-id 1 --definition '{"dashboard_folders":[],"shared_spaces":[]}' --validate-only true
 ae-cli analysis public-link create --project-id 1 --resource-type dashboard --resource-id 1001 --effective-at "2026-07-08 00:00:00" --expires-at "2026-08-08 00:00:00" --yes
 ```

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

@@ -0,0 +1,17 @@
+# analysis artifact download
+
+Use after `run inspect` shows an export artifact is complete.
+
+Do not use before the run reaches a successful terminal status. Use `run inspect` first.
+
+Command:
+
+```bash
+ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>
+```
+
+Input sends `run_id`, `artifact_id`, and local `output` path.
+
+Output is the gateway download result written to the local `--output` path. The command returns JSON with `run_id`, `artifact_id`, `output_path`, `bytes`, and response content headers.
+
+Do not paste large artifact content into chat. Inspect the local file or summarize only the needed rows.

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

@@ -12,4 +12,14 @@ ae-cli analysis bi-panel-page-data export --project-id <project_id> --panel-id <
 
 Input sends `project_id`, `panel_id`, `page_key`, `result_type`, and optional control, paging, cache, request, timeout, and format fields. Use CLI flag `--artifact-format` for the gateway `format` input; `--format` is the CLI output formatter.
 
-Output is the gateway envelope. `data` contains an async export descriptor such as `run_id`, `artifact_id`, status fields, inspect path, and download path.
+Output is the gateway envelope. `data` contains an async export descriptor with `run_id`, `artifact_id`, status fields, and expiration fields. It does not expose inspect/download API paths; use the CLI commands below.
+
+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> --yes`.
+
+Do not write custom Python/curl for polling or download unless the CLI command itself is unavailable.

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

@@ -4,12 +4,14 @@ Use when the user wants to copy a dashboard, optionally copying reports and targ
 
 Do not use to create a blank dashboard. Use `dashboard create`.
 
+If both `--to-space-id` and `--to-folder-id` are omitted, the gateway copies to the source dashboard's current location. Do not manually discover a target folder just to copy in place.
+
 Command:
 
 ```bash
 ae-cli analysis dashboard copy --project-id <project_id> --dashboard-id <source_dashboard_id> --dashboard-name <new_name> [--report-copy true] [--to-space-id <space_id>] [--to-folder-id <folder_id>] --yes
 ```
 
-Input sends `project_id`, `dashboard_id`, `dashboard_name`, and optional `report_copy`, `to_space_id`, `to_folder_id`.
+Input sends `project_id`, `dashboard_id`, `dashboard_name`, `report_copy` defaulting to false, and optional `to_space_id`, `to_folder_id`.
 
 Output is the gateway envelope. `data` contains the copied dashboard result.

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

@@ -7,9 +7,11 @@ Do not use for configuration changes. Use `dashboard-daily-report update`.
 Command:
 
 ```bash
-ae-cli analysis dashboard-daily-report send --project-id <project_id> --dashboard-id <dashboard_id> [--need-csv 1] [--host-url <url>] [--payload '{...}'] --yes
+ae-cli analysis dashboard-daily-report send --project-id <project_id> --dashboard-id <dashboard_id> [--need-csv true] [--host-url <url>] [--payload '{...}'] --yes
 ```
 
-Input sends `project_id`, `dashboard_id`, and optional `need_csv`, `host_url`, `payload`.
+Input sends `project_id`, `dashboard_id`, and optional daily report fields or `payload`.
+
+When `--payload` is absent, the command sends safe defaults expected by the gateway: `need_csv=false`, empty `host_url`, all channel switches false, `send_date=1,2,3,4,5,6,7`, `send_time=09:00`, `lang=zh-CN`, `screen_type=normal`, and `zone_offset=0`. When `--payload` is present, payload values remain authoritative; pass top-level flags only for fields you intentionally want to override.
 
 Output is the gateway envelope. `data` contains the immediate send result.

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

@@ -7,9 +7,11 @@ Do not use to send immediately. Use `dashboard-daily-report send`.
 Command:
 
 ```bash
-ae-cli analysis dashboard-daily-report update --project-id <project_id> --dashboard-id <dashboard_id> [--enable-send 1] [--send-time <time>] [--send-title <title>] [--send-content <content>] [--payload '{...}'] --yes
+ae-cli analysis dashboard-daily-report update --project-id <project_id> --dashboard-id <dashboard_id> [--enable-send true] [--send-time <time>] [--send-title <title>] [--send-content <content>] [--payload '{...}'] --yes
 ```
 
 Input sends `project_id`, `dashboard_id`, and optional daily report fields or `payload`.
 
+When `--payload` is absent, the command sends safe defaults expected by the gateway: `need_csv=false`, empty `host_url`, all channel switches false, `send_date=1,2,3,4,5,6,7`, `send_time=09:00`, `lang=zh-CN`, `screen_type=normal`, `zone_offset=0`, and `enable_send=false`. When `--payload` is present, payload values remain authoritative; pass top-level flags only for fields you intentionally want to override.
+
 Output is the gateway envelope. `data` contains the daily report configuration update result.

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

@@ -1,15 +1,33 @@
 # analysis dashboard-definition export
 
-Use when the user wants to export dashboard definition JSON for selected dashboard folders or shared spaces.
+Use when the user wants to export dashboard definition JSON for one dashboard, multiple dashboards, selected private dashboard folders, or shared project spaces.
 
 Do not use for dashboard report result data. Use `dashboard-report-data run` or `dashboard-report-data export`.
 
 Command:
 
 ```bash
-ae-cli analysis dashboard-definition export --project-id <project_id> [--dashboard-folder-ids '[...]'] [--shared-spaces '[...]'] [--export-file-name <name>] [--payload '{...}']
+ae-cli analysis dashboard-definition export --project-id <project_id> [--dashboard-id <dashboard_id>] [--dashboard-ids '[1,2]'] [--dashboard-folder-ids '[...]'] [--shared-spaces '[...]'] [--export-file-name <name>] [--payload '{...}']
 ```
 
-Input sends `project_id` and optional `dashboard_folder_ids`, `shared_spaces`, `export_file_name`, `payload`.
+Input sends `project_id` and optional `dashboard_id`, `dashboard_ids`, `dashboard_folder_ids`, `shared_spaces`, `export_file_name`, `payload`.
+
+Prefer `--dashboard-id` or `--dashboard-ids` when the user asks for a single dashboard or a known dashboard list. The gateway resolves private-folder or project-space context.
+
+For a private folder export, `--dashboard-folder-ids '[123]'` is accepted. Use the advanced descriptor form only when you need to restrict which dashboards inside the folder are exported.
+
+Advanced private-folder descriptor form:
+
+```bash
+ae-cli analysis dashboard-definition export --project-id <project_id> \
+  --dashboard-folder-ids '[{"dashboard_folder_id":123,"dashboard_ids":[456]}]'
+```
+
+Advanced project-space descriptor form:
+
+```bash
+ae-cli analysis dashboard-definition export --project-id <project_id> \
+  --shared-spaces '[{"space_id":10,"children":[{"is_folder":false,"id":456}]}]'
+```
 
 Output is the gateway envelope. `data` contains exported definition data or an export descriptor.

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

@@ -12,4 +12,14 @@ ae-cli analysis dashboard-report-data export --project-id <project_id> --dashboa
 
 Input sends `project_id`, `dashboard_id`, and optional `report_ids`, `filters`, `start_time`, `end_time`, `use_cache`, `request_id`, `timeout_seconds`, `format`. Use CLI flag `--artifact-format` for the gateway `format` input; `--format` is the CLI output formatter.
 
-Output is the gateway envelope. `data` contains an async export descriptor such as `run_id`, `artifact_id`, status fields, inspect path, and download path.
+Output is the gateway envelope. `data` contains an async export descriptor with `run_id`, `artifact_id`, status fields, and expiration fields. It does not expose inspect/download API paths; use the CLI commands below.
+
+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> --yes`.
+
+Do not write custom Python/curl for polling or download unless the CLI command itself is unavailable.

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

@@ -10,6 +10,6 @@ Command:
 ae-cli analysis project-space create --project-id <project_id> [--space-name <name>] [--space-desc <text>] [--avatar-type <type>] [--color-key <key>] [--avatar <value>] [--payload '{...}'] --yes
 ```
 
-Input sends `project_id` plus optional space metadata and `payload`.
+Input sends `project_id` plus optional space metadata and `payload`. `avatar_type` defaults to `1` (word avatar) when omitted. When using `--payload`, put custom avatar fields in the payload or pass explicit top-level flags.
 
 Output is the gateway envelope. `data` contains the created project-space result.

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

@@ -0,0 +1,22 @@
+# analysis run inspect
+
+Use after an export command returns `run_id`.
+
+Do not use for MCP query cancellation or old `request_id` lifecycle. This is only for capability-gateway export `run_id`.
+
+Command:
+
+```bash
+ae-cli analysis run inspect --run-id <run_id>
+```
+
+Input sends `run_id`.
+
+Output is the gateway envelope. `data` contains run status, artifact status, and error fields when the run failed.
+
+Polling rule:
+
+- Continue polling while status is running or pending.
+- Treat `COMPLETED` or `SUCCEEDED` as success.
+- Treat `FAILED`, `CANCELED`, or `CANCELLED` as terminal failure.
+- After success, download with `ae-cli analysis artifact download --run-id <run_id> --artifact-id <artifact_id> --output <file>`.

package/skills/ae-dataops/references/dataops-flow-create.md

@@ -120,7 +120,7 @@ ae-cli dataops_operations +get_flow_instance_detail --spaceCode "${spaceCode}" \
   --flowCode ${flowCode} --flowInstanceId ${flowInstanceId}
 ae-cli dataops_operations +get_task_instance_detail --spaceCode "${spaceCode}" \
   --flowCode ${flowCode} --flowInstanceId ${flowInstanceId} \
-  --taskName "${taskName}" --includeLog true
+  --taskInstanceId ${taskInstanceId} --includeLog true
 ```
 
 ---
@@ -139,7 +139,7 @@ ae-cli dataops_operations +get_task_instance_detail --spaceCode "${spaceCode}" \
 | `+get_task_params` | View DEV task parameter list | `--spaceCode` `--flowCode` `--taskCode` |
 | `+execute_flow` | Manual PROD execution | `--spaceCode` `--flowCode` `[--baseDate]` |
 | `dataops_operations +get_flow_instance_detail` | View operations instance DAG and task statuses | `--spaceCode` `--flowCode` `--flowInstanceId` |
-| `dataops_operations +get_task_instance_detail` | View operations task detail and optional logs | `--spaceCode` `--flowCode` `--flowInstanceId` (`--taskCode` or `--taskName`) `[--includeLog]` |
+| `dataops_operations +get_task_instance_detail` | View operations task detail and optional logs | `--spaceCode` `--flowCode` `--flowInstanceId` (`--taskInstanceId` or `--taskCode` or `--taskName`) `[--includeLog]` |
 | `+preview_release_flow` | Preview pending DEV-to-PROD release changes without publishing | `--spaceCode` `--flowCode` |
 | `+release_flow` | Submit DEV-to-PROD release | `--spaceCode` `--flowCode` |
 

package/skills/ae-dataops/references/dataops-flow-monitor.md

@@ -55,7 +55,7 @@ ae-cli dataops_operations +get_flow_instance_detail --spaceCode "${spaceCode}" \
 # Step 2: View task detail and logs
 ae-cli dataops_operations +get_task_instance_detail --spaceCode "${spaceCode}" \
   --flowCode ${flowCode} --flowInstanceId ${flowInstanceId} \
-  --taskName "${taskName}" --includeLog true
+  --taskInstanceId ${taskInstanceId} --includeLog true
 
 # Step 3: Re-execute after fixing
 ae-cli dataops_flow +execute_flow --spaceCode "${spaceCode}" \
@@ -105,7 +105,7 @@ ae-cli dataops_flow +get_flow_overview --spaceCode "${spaceCode}" \
 | `+execute_flow` | Manual PROD execution | `--spaceCode` `--flowCode` `[--baseDate]` |
 | `dataops_operations +search_flow_instances` | Search operations workflow instances | `--spaceCode` `[--keyword]` `[--startDate]` `[--endDate]` `[--status]` `[--pageNum]` `[--pageSize]` |
 | `dataops_operations +get_flow_instance_detail` | Operations instance DAG and task statuses | `--spaceCode` `--flowCode` `--flowInstanceId` |
-| `dataops_operations +get_task_instance_detail` | Operations task detail and optional logs | `--spaceCode` `--flowCode` `--flowInstanceId` (`--taskCode` or `--taskName`) `[--includeLog]` |
+| `dataops_operations +get_task_instance_detail` | Operations task detail and optional logs | `--spaceCode` `--flowCode` `--flowInstanceId` (`--taskInstanceId` or `--taskCode` or `--taskName`) `[--includeLog]` |
 | `dataops_operations +stop_flow_instance` | Stop a running execution | `--spaceCode` `--flowCode` exactly one of `--executeId` or `--flowInstanceId` |
 | `+get_task_params` | DEV task parameter list | `--spaceCode` `--flowCode` `--taskCode` |
 | `+update_flow` | Update DEV workflow name and/or remark | `--spaceCode` `--flowCode` `[--flowName]` `[--remark]` |
@@ -118,7 +118,7 @@ ae-cli dataops_flow +get_flow_overview --spaceCode "${spaceCode}" \
 - **Flow update**: `+update_flow` requires `--spaceCode`, `--flowCode`, and at least one of `--flowName` or `--remark`. It returns `action/result/status`; `result` is an array with items containing `flowCode`, `operationStatus`, `nameChanged`, and optional `flowName`.
 - **High-frequency release flows**: `+list_high_frequency_release_flows` requires `--spaceCode`; `--days`, `--topN`, `--minCount`, and `--status` are optional. Defaults are `days=30`, `topN=10`, and `status=SUCCESS`. It returns `period`, `filters`, `flows`, `returnedCount`, and `nextAction`; flow items include `rank`, `flowCode`, `flowName`, `releaseCount`, `lastReleaseTime`, and `avgIntervalHours`.
 - **Operations instance search**: `dataops_operations +search_flow_instances` requires `--spaceCode`; `--keyword`, `--startDate`, `--endDate`, `--status`, `--pageNum`, and `--pageSize` are optional. `--keyword` fuzzy-matches `flowName` or `flowCode`. `pageNum` defaults to `1`; `pageSize` defaults to `20` and maxes at `100`. It returns `totalCount`, `returnedCount`, `pageNum`, `pageSize`, `hasMore`, `instances`, `statusCounts`, `triggerTypeCounts`, and `ownerCounts`.
-- **Task instance detail**: `dataops_operations +get_task_instance_detail` requires `--spaceCode`, `--flowCode`, `--flowInstanceId`, and either `--taskCode` or exact `--taskName`. `--taskCode` takes precedence when both are passed. `--includeLog` is optional and defaults to `false`. It returns `success`, `flowInstanceId`, `taskCode`, `taskName`, `taskInstanceId`, `status`, `task`, `taskInstance`, `definition`, and `log` only when requested.
+- **Task instance detail**: `dataops_operations +get_task_instance_detail` requires `--spaceCode`, `--flowCode`, `--flowInstanceId`, and one selector: `--taskInstanceId`, `--taskCode`, or exact `--taskName`. Prefer `--taskInstanceId` because retries can create multiple instances with the same task code/name. `--includeLog` is optional and defaults to `false`. It returns `success`, `flowInstanceId`, `taskCode`, `taskName`, `taskInstanceId`, `status`, `task`, `taskInstance`, `definition`, and `log` only when requested.
 - **env**: `DEV` (development) | `PROD` (production, instance list defaults to PROD)
 - **flow list paging**: `+list_flows` requires `--spaceCode`; `--keyword`, `--pageNum`, and `--pageSize` are optional. It returns `flows`, `totalCount`, `returnedCount`, `pageNum`, `pageSize`, and `hasMore`; flow items include `latestProductionInstance` only when available. `pageSize` defaults to `20` and maxes at `100`.
 - **Task parameters**: `+get_task_params` requires `--spaceCode`, `--flowCode`, and `--taskCode`; it has no optional flags. It queries DEV and returns `data` as an array. Items include fields such as `paramKey`, `paramType`, `paramDataType`, `paramFrom`, and built-in flags like `isBd`.

package/skills/ae-dataops/references/dataops-integration.md

@@ -18,6 +18,7 @@ Use the `dataops_integration` subcommand to manage datasources and sync solution
 - sourceConfig/sinkConfig/channelConfig/fieldsMapping are all JSON strings
 - Sync solution updates are not partial patches: call `+get_sync_detail --withParams true` first, then submit complete sourceConfig and sinkConfig JSON. Pass channelConfig and fieldsMapping when keeping or updating them
 - Test datasource connection before creating sync solution
+- `sinkConfig.dataSaveMode` codes are fixed: `1 = APPEND_DATA` (insert/append new data; UI label `插入新数据`), `2 = OVERWRITE` (`DROP_DATA`; UI label `覆盖写入`). Never describe `dataSaveMode=1` as overwrite; use `2` for overwrite.
 
 ---
 

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

@@ -1,7 +1,7 @@
 # ae-engage +flow_node_config_schema
 
 
-Query the configuration schema for a flow node type.
+Query the configuration schema for one flow node type before constructing a `save_flow` node config.
 
 Mapped command: `ae-cli engage +flow_node_config_schema`
 
@@ -9,13 +9,34 @@ Mapped command: `ae-cli engage +flow_node_config_schema`
 
 | Flag | Type | Required | Description |
 |------|------|------|------|
-| `--node_type` | string | Yes | node type |
+| `--node_type` | string | Yes | Flow node type |
+
+## When To Use
+
+Call this before writing any non-trivial `save_flow` `nodes[].config` or `nodeConfigs[].config`. The response is the source of truth for:
+
+- `required` and `conditional_required` fields
+- defaulted fields that can be omitted from draft input
+- enum values and allowed modes
+- `minimal_valid`, `full_valid`, and `common_invalid` examples
+- submit-time requirements for stricter `save_submit_flow` validation
+
+Do not use this command to build an old full `FlowSaveReqDTO`, `nodeList`, or `edgeList`. `save_flow` uses compact `nodes` / `edges`.
+
+## Recent Save Flow Notes
+
+- `event_trigger` supports `targetUserType=1` custom and `targetUserType=3` all users; existing cluster `targetUserType=2` is not supported for this node.
+- `event_trigger` and `event_judge` A-segment trigger rules are non-branch rules and use `periodStart`, `periodEnd`, and `periodTimeSymbol`.
+- `event_split_flow` branch rules use `delayTime` and `delayTimeSymbol`; `branchType=1` also needs `targetClusterType`, and non-all-user branches need `clusterKey`.
+- Push nodes default `processType=1`, `enableChannelTouchLimits=0`, and `isOccasionUp=false`.
+- The validator normalizes compatible inputs before schema validation: apostrophe-prefixed field aliases, case-insensitive property aliases, `enableChannelTouchLimits` booleans, string `"0"`/`"1"` QP relations inside `targetClusterQp`, and `clusterPredictCount: null`.
+- For push nodes, `contentList[].content` should be a JSON array; the validator also accepts a JSON-stringified array for compatibility. For push `OBJ_ARRAY` params, `value` must still be a JSON array and `objArray` must be copied from `query_channel_detail data.config.paramsList[].objArray`.
 
 ## Enum Notes
 
 ### `--node_type`
 
-Common node types include:
+Schema-backed node types include:
 
 - `single_trigger`
 - `repeat_trigger`
@@ -25,15 +46,10 @@ Common node types include:
 - `message_push`
 - `wechat_push`
 - `webhook_push`
-- `config_push`
-- `tag`
 - `time_control`
 - `feature_split_flow`
 - `event_split_flow`
-- `trigger_prop_split_flow`
-- `percent_split_flow`
 - `ab_split_flow`
-- `race_split_flow`
 - `exit_flow`
 
 ## Examples
@@ -41,3 +57,11 @@ Common node types include:
 ```bash
 ae-cli engage +flow_node_config_schema --node_type message_push
 ```
+
+Typical flow:
+
+```bash
+ae-cli engage +flow_node_config_schema --node_type event_trigger
+ae-cli engage +validate_flow_node_config \
+  --node_type event_trigger --operation_mode save_flow --config '<config-json-string>'
+```