@thinkingai/ae-cli 6.0.22 → 6.0.27

package/skills/ae-agent/references/del-model.md

@@ -0,0 +1,37 @@
+# agent +del-model (Delete Model)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Models / write**
+
+## Use Cases
+- Delete a custom model (personal or company scope).
+- `--scope personal` (default) deletes a personal model; `--scope company` deletes a company model (requires root/agent_admin). System models cannot be deleted.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real model record ID (CUID) via `+list-models` — do not guess.
+- `--scope` controls target scope: `personal` (default) or `company`. Company scope requires root/agent_admin.
+- Prefer `--dry-run` before executing a destructive delete.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+ae-cli agent +del-model --id <model-cuid> --yes
+ae-cli agent +del-model --dry-run --id <model-cuid>
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Model record ID (CUID) |
+| `--scope` | No | Target scope: `personal` (default) or `company` (requires root/agent_admin) |
+
+## Decision Rules
+- Confirm the model ID with `+list-models` before deleting.
+- Company-scope models can be deleted with `--scope company` by root/agent_admin; system models cannot be deleted via CLI.
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-models` to verify the model ID and scope.
+
+## Recommended Chaining
+- `+list-models` → confirm `id` → `+del-model`

package/skills/ae-agent/references/del-skill-asset.md

@@ -0,0 +1,41 @@
+# agent +del-skill-asset (Delete Skill Asset)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Delete a file from a Skill's `assets` directory.
+- Endpoint: `DELETE /api/sandbox/agent/skills/[id]/assets/[...path]`.
+- Physical delete — cannot be undone.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- `--path` is required and specifies the relative file path within the assets directory.
+- This is a **physical delete** — prefer `--dry-run` before executing.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+ae-cli agent +del-skill-asset --id <skill-cuid> --path icon.png --yes
+ae-cli agent +del-skill-asset --id <skill-cuid> --path "sub/data.csv" --yes
+ae-cli agent +del-skill-asset --dry-run --id <skill-cuid> --path icon.png
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+| `--path` | Yes | Relative file path within assets to delete |
+
+## Decision Rules
+- Use `+list-skill-assets` to confirm the file path before deleting.
+- This is a physical delete, not a soft delete — proceed only when the user clearly intends to remove it.
+- Use `--dry-run` first to verify the request shape before executing.
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-skill-assets` to verify the file path.
+- `文件不存在`: the file path does not exist in the assets directory.
+
+## Recommended Chaining
+- `+list-skill-assets` → confirm `path` → `+del-skill-asset` → `+list-skill-assets` (verify)

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

@@ -0,0 +1,41 @@
+# agent +del-skill-reference (Delete Skill Reference)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Delete a file from a Skill's `references` directory.
+- Endpoint: `DELETE /api/sandbox/agent/skills/[id]/references/[...path]`.
+- Physical delete — cannot be undone.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- `--path` is required and specifies the relative file path within the references directory.
+- This is a **physical delete** — prefer `--dry-run` before executing.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+ae-cli agent +del-skill-reference --id <skill-cuid> --path guide.md --yes
+ae-cli agent +del-skill-reference --id <skill-cuid> --path "advanced/tips.md" --yes
+ae-cli agent +del-skill-reference --dry-run --id <skill-cuid> --path guide.md
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+| `--path` | Yes | Relative file path within references to delete |
+
+## Decision Rules
+- Use `+list-skill-references` to confirm the file path before deleting.
+- This is a physical delete, not a soft delete — proceed only when the user clearly intends to remove it.
+- Use `--dry-run` first to verify the request shape before executing.
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-skill-references` to verify the file path.
+- `文件不存在`: the file path does not exist in the references directory.
+
+## Recommended Chaining
+- `+list-skill-references` → confirm `path` → `+del-skill-reference` → `+list-skill-references` (verify)

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

@@ -0,0 +1,41 @@
+# agent +del-skill-script (Delete Skill Script)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Delete a file from a Skill's `scripts` directory.
+- Endpoint: `DELETE /api/sandbox/agent/skills/[id]/scripts/[...path]`.
+- Physical delete — cannot be undone.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- `--path` is required and specifies the relative file path within the scripts directory.
+- This is a **physical delete** — prefer `--dry-run` before executing.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+ae-cli agent +del-skill-script --id <skill-cuid> --path helper.sh --yes
+ae-cli agent +del-skill-script --id <skill-cuid> --path "tools/run.py" --yes
+ae-cli agent +del-skill-script --dry-run --id <skill-cuid> --path helper.sh
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+| `--path` | Yes | Relative file path within scripts to delete |
+
+## Decision Rules
+- Use `+list-skill-scripts` to confirm the file path before deleting.
+- This is a physical delete, not a soft delete — proceed only when the user clearly intends to remove it.
+- Use `--dry-run` first to verify the request shape before executing.
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-skill-scripts` to verify the file path.
+- `文件不存在`: the file path does not exist in the scripts directory.
+
+## Recommended Chaining
+- `+list-skill-scripts` → confirm `path` → `+del-skill-script` → `+list-skill-scripts` (verify)

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

@@ -0,0 +1,36 @@
+# agent +del-skill (Delete Personal Skill)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Delete a personal-scope Skill (physical delete).
+- Only `personal` scope Skills can be deleted via CLI; company/system Skills are read-only.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- This is a **physical delete** — prefer `--dry-run` before executing.
+- Write operation: keep the confirmation prompt unless `--yes` is explicitly requested.
+
+## Command
+```bash
+ae-cli agent +del-skill --id <skill-cuid> --yes
+ae-cli agent +del-skill --dry-run --id <skill-cuid>
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+
+## Decision Rules
+- Confirm the Skill ID with `+list-skills` before deleting.
+- This is a physical delete, not a soft delete — proceed only when the user clearly intends to remove it.
+- If the Skill is company/system scope, deletion is not available via CLI (use `+toggle-skill` to disable it per-user instead).
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-skills` to verify the Skill ID and scope.
+
+## Recommended Chaining
+- `+list-skills` → confirm `id` → `+del-skill`

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

@@ -0,0 +1,64 @@
+# agent +edit-skill (Edit Skill Content)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / write**
+
+## Use Cases
+- Edit a personal Skill's content (name, description, instructions, display name, category, icon).
+- Endpoint: `PUT /api/sandbox/agent/skills/[id]`.
+- Only `personal` scope Skills can be edited via CLI.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+- At least one editable field must be provided (`--name` / `--description` / `--instructions` / `--display-name` / `--category` / `--icon-emoji` / `--icon-color`).
+- `--name` must be 1–80 chars when provided.
+- `--instructions` supports `@-` to read from stdin (useful for piping long instruction text).
+- `--category` must be one of the market category keys when provided.
+- 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
+# Edit instructions only
+ae-cli agent +edit-skill --id <skill-cuid> --instructions "Updated instructions..." --yes
+
+# Edit name and description
+ae-cli agent +edit-skill --id <skill-cuid> --name new-name --description "New description" --yes
+
+# Instructions from stdin
+echo "You are a helpful assistant..." | \
+  ae-cli agent +edit-skill --id <skill-cuid> --instructions @- --yes
+
+# Dry-run to inspect the request before executing
+ae-cli agent +edit-skill --dry-run --id <skill-cuid> --name new-name
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+| `--name` | No* | New Skill name (1–80 chars) |
+| `--description` | No* | New Skill description |
+| `--instructions` | No* | New instructions (use `@-` to read from stdin) |
+| `--display-name` | No* | New display name (max 100) |
+| `--category` | No* | Market category key (see above) |
+| `--icon-emoji` | No* | Market icon emoji (e.g. `robot`) |
+| `--icon-color` | No* | Market icon color (e.g. `#1E76F0`) |
+
+\* At least one of these must be provided.
+
+## Decision Rules
+- Use `+list-skills` to confirm the Skill ID before editing.
+- If the user provides long instruction text, pipe it via stdin with `--instructions @-`.
+- Use `--dry-run` first to verify the request shape before executing.
+- Editing a Skill does not change its scope; company/system Skills are read-only via CLI.
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-skills` to verify the Skill ID and scope.
+- `409` / name conflict: use `--name` with a different name, or consider `+upload-skill` with `--auto-rename`.
+
+## Recommended Chaining
+- `+list-skills` → confirm `id` → `+edit-skill` → `+get-skill-content` (verify)

package/skills/ae-agent/references/get-agent.md

@@ -0,0 +1,37 @@
+# agent +get-agent (Get Agent Details)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Agents / read**
+
+## Use Cases
+- Fetch full details of a single Agent by ID (system visible to all; company to same company; personal to owner).
+- Use this to confirm an Agent's current model, MCP, Skill, and enabled state before updating or deleting.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Agent record ID (CUID) via `+list-agents` — do not guess.
+- Read operation — no confirmation prompt.
+
+## Command
+```bash
+ae-cli agent +get-agent --id <agent-cuid>
+ae-cli agent +get-agent --id <agent-cuid> --format table
+ae-cli agent +get-agent --dry-run --id <agent-cuid>
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Agent record ID (CUID) |
+
+## Decision Rules
+- When the user references an Agent by name, resolve it to an ID with `+list-agents` first, then call `+get-agent` for full details.
+- Use `--format table` for a scannable single-record view.
+- The returned `item` includes the resolved model, MCP/Skill ID lists, and the current user's enabled preference (for system/company Agents).
+
+## Next Steps on Failure
+- `404` / `Agent 不存在`: the Agent does not exist, is deleted, or is not visible to you (personal Agent owned by another user). Re-run `+list-agents` to discover visible IDs.
+- Auth error: run `ae-cli auth login`.
+
+## Recommended Chaining
+- `+list-agents` → confirm `id` → `+get-agent` (inspect) → `+update-agent` / `+del-agent` / `+create-automation --agent-id <id>`

package/skills/ae-agent/references/get-skill-content.md

@@ -0,0 +1,36 @@
+# agent +get-skill-content (Read Skill Content)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Skills / read**
+
+## Use Cases
+- Read a Skill's SKILL.md text content.
+- Endpoint: `GET /api/sandbox/agent/skills/[id]/content`.
+- Returns the raw SKILL.md file content as JSON `{ item: { ... } }`.
+
+## Mandatory Rules (MUST)
+- `--id` is required. Obtain the real Skill record ID (CUID) via `+list-skills` — do not guess.
+
+## Command
+```bash
+ae-cli agent +get-skill-content --id <skill-cuid>
+ae-cli agent +get-skill-content --dry-run --id <skill-cuid>
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--id` | Yes | Skill record ID (CUID) |
+
+## Decision Rules
+- Use `+list-skills` to confirm the Skill ID before reading.
+- The returned content is the SKILL.md text — useful for inspecting or backing up a Skill's instructions.
+- Read operation: no confirmation prompt needed.
+
+## Next Steps on Failure
+- `404` / not found: re-run `+list-skills` to verify the Skill ID.
+- `file_not_found`: the Skill record exists but the SKILL.md file is missing on disk — use `+rescan-skills` (root) to sync.
+
+## Recommended Chaining
+- `+list-skills` → confirm `id` → `+get-skill-content` → `+edit-skill` (if changes needed)

package/skills/ae-agent/references/list-agents.md

@@ -0,0 +1,40 @@
+# agent +list-agents (List Agents)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Agents / read**
+
+## Use Cases
+- List Agents visible to the current user (personal / company / system scopes).
+- Returns an array of Agent summaries; key fields include `id`, `name`, `description`, `scope`.
+- Use this to discover a real Agent ID before creating an automation with `--agent-id` or `--agent-name`.
+
+## Mandatory Rules (MUST)
+- Do not guess Agent IDs. Always call `+list-agents` first when an Agent reference is needed.
+- If the user references an Agent by name, match the name against the returned list before proceeding.
+
+## Command
+```bash
+ae-cli agent +list-agents
+ae-cli agent +list-agents --scope personal
+ae-cli agent +list-agents --scope company --q "daily" --format table
+ae-cli agent +list-agents --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--scope` | No | Filter by scope: `personal` \| `company` \| `system` |
+| `--q` | No | Search by Agent name or description |
+
+## Decision Rules
+- When the user needs an Agent ID for `+create-automation` (`--agent-id` / `--agent-name`), call this first.
+- If many Agents are returned, summarize by `id`, `name`, and `scope` to help the user pick the right one.
+- `--scope personal` shows only the user's own Agents; `company` / `system` show shared resources.
+
+## Next Steps on Failure
+- Empty result: confirm account permissions and the active AE host.
+- Auth error: run `ae-cli auth login`.
+
+## Recommended Chaining
+- `+list-agents` → confirm `agent-id` → `+create-automation`

package/skills/ae-agent/references/list-attachments.md

@@ -0,0 +1,42 @@
+# agent +list-attachments (List Attachments)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Attachments / read**
+
+## Use Cases
+- List the current user's attachments (paginated).
+- Endpoint: `GET /api/sandbox/agent/attachments`.
+- Returns an array of attachment summaries; key fields include `id`, `name`, `type`, `size`.
+
+## Mandatory Rules (MUST)
+- `--type` must be `image` or `document` when provided.
+
+## Command
+```bash
+ae-cli agent +list-attachments
+ae-cli agent +list-attachments --type image --format table
+ae-cli agent +list-attachments --q "report" --page 1 --page-size 20
+ae-cli agent +list-attachments --dry-run --type document
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--q` | No | Search keyword |
+| `--type` | No | Filter by type: `image` \| `document` |
+| `--page` | No | Page number (default 1) |
+| `--page-size` | No | Page size (default 20, max 10000) |
+
+## Decision Rules
+- When the user needs an attachment ID for `+del-attachment`, call this first.
+- `--type image` filters to image attachments; `--type document` filters to documents.
+- Use `--format table` for a scannable overview.
+
+## Next Steps on Failure
+- `--type must be image or document`: use one of the two values.
+- Empty result: no attachments match the filter.
+
+## Recommended Chaining
+- `+list-attachments` → confirm `id` → `+del-attachment`
+- `+add-attachment` (upload) → `+list-attachments` (verify)

package/skills/ae-agent/references/list-automations.md

@@ -0,0 +1,41 @@
+# agent +list-automations (List Automations)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Automations / read**
+
+## Use Cases
+- List the current user's Agent automation tasks.
+- Returns an array of automation summaries; key fields include `id`, `name`, `status`, `schedule`/`cronExpression`.
+- Use this to discover a real automation ID before `+update-automation`.
+
+## Mandatory Rules (MUST)
+- Do not guess automation IDs. Always call `+list-automations` first when an automation ID is needed.
+- Do not surface raw automation IDs, raw JSON, or concrete detail paths in user-facing replies — use the ID only internally for subsequent commands.
+
+## Command
+```bash
+ae-cli agent +list-automations
+ae-cli agent +list-automations --status active
+ae-cli agent +list-automations --q "daily" --limit 20 --format table
+ae-cli agent +list-automations --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--q` | No | Keyword for automation name or instruction |
+| `--status` | No | `active` \| `paused` |
+| `--limit` | No | Maximum number of automations to return, 1–10000 |
+
+## Decision Rules
+- When the user wants to pause, resume, rename, or edit an automation, call this first to find the target ID.
+- `--status active` lists only enabled automations; `--status paused` lists paused ones.
+- If many automations are returned, summarize by `name` and `status` to help the user pick the right one.
+
+## Next Steps on Failure
+- Empty result: confirm the user has created automations on the active AE host.
+- Auth error: run `ae-cli auth login`.
+
+## Recommended Chaining
+- `+list-automations` → confirm `id` → `+update-automation`

package/skills/ae-agent/references/list-mcp-credentials.md

@@ -0,0 +1,65 @@
+# agent +list-mcp-credentials (List MCP Credentials)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **MCP Credentials / read**
+
+## Use Cases
+- List the current user's per-user credentials for system-scope MCP servers.
+- Endpoint: `GET /api/sandbox/agent/mcp-credentials`.
+- Returns one entry per system MCP server, with the user's credential (or `null` if none exists).
+
+## Mandatory Rules (MUST)
+- No flags required — lists all system MCP servers and the current user's credential status.
+- Only system-scope MCP servers are included; personal/company credentials are managed via the MCP server config and OAuth flow.
+
+## Command
+```bash
+# List all system MCP credentials
+ae-cli agent +list-mcp-credentials
+
+# Dry-run to inspect the request
+ae-cli agent +list-mcp-credentials --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| (none) | — | — |
+
+## Decision Rules
+- If the user wants to check which system MCP servers have credentials configured, use this command.
+- Each item shows `mcpServerId`, `mcpServerName`, and a `credential` object (or `null`).
+- The `credential` object includes `authType`, `enabled`, `expiresAt`, and whether a token is stored — but the token itself is not returned in plaintext here (use `+mcp-token` for that).
+
+## Response Shape
+```json
+{
+  "items": [
+    {
+      "mcpServerId": "clxxx",
+      "mcpServerName": "te-mcp",
+      "credential": {
+        "mcpServerId": "clxxx",
+        "userId": "uyyy",
+        "authType": "oauth",
+        "enabled": true,
+        "expiresAt": "2026-07-06T13:00:00.000Z",
+        "hasToken": true
+      }
+    },
+    {
+      "mcpServerId": "clzzz",
+      "mcpServerName": "other-mcp",
+      "credential": null
+    }
+  ]
+}
+```
+
+## Next Steps on Failure
+- `401` / auth expired: run `ae-cli auth login`.
+
+## Recommended Chaining
+- `+list-mcp-credentials` (check) → `+set-mcp-credential` (set) or `+auto-provision-mcp-credentials` (bulk)
+- `+list-mcp-credentials` → `+mcp-token` (get plaintext token for useMcpToken servers)

package/skills/ae-agent/references/list-mcp-market.md

@@ -0,0 +1,58 @@
+# agent +list-mcp-market (List MCP Market)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Market (browse) / read**
+
+## Use Cases
+- List MCP servers from the market (system / company / personal scopes).
+- Endpoint: `GET /api/sandbox/agent/mcp-servers/market`.
+- Supports filtering by scope, category, search, and sort, with pagination.
+- Use this to discover MCP servers before adding one with `+add-mcp`.
+
+## Mandatory Rules (MUST)
+- `--scope` must be one of the market scopes when provided (see below).
+- `--category` must be one of the market category keys when provided (see below).
+- `--sort` must be one of the sort options when provided (see below).
+
+## Market Scope
+`all | system | company | custom` (`custom` = personal; `all` = system + company + personal)
+
+## Market Category Keys
+`ae_preset | dev_tool | search_tool | data_query | content_gen | enterprise | life | automation | other`
+
+## Sort Options
+`newest | calls | likes` (`calls` sorts MCP by call count)
+
+## Command
+```bash
+ae-cli agent +list-mcp-market
+ae-cli agent +list-mcp-market --scope company --category dev_tool --sort calls --format table
+ae-cli agent +list-mcp-market --search "weather" --sort newest
+ae-cli agent +list-mcp-market --limit 20 --offset 0
+ae-cli agent +list-mcp-market --dry-run --scope system
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--scope` | No | Market scope (see above; default `all`) |
+| `--category` | No | Category key (see above) |
+| `--search` | No | Fuzzy search on name/displayName/description/url |
+| `--sort` | No | Sort option (see above; default `newest`) |
+| `--limit` | No | Page size (1–100, default 50) |
+| `--offset` | No | Page offset (>=0, default 0) |
+
+## Decision Rules
+- When the user wants to browse available MCP servers, call this first.
+- `--scope company` shows same-company MCP servers; `--scope system` shows built-in ones; `--scope custom` shows personal ones.
+- Use `--sort calls` to find the most-used MCP servers.
+- Use `--format table` for a scannable overview.
+
+## Next Steps on Failure
+- `--scope must be one of...`: use one of the market scope values.
+- `--category must be one of...`: use one of the category keys.
+- Empty result: widen filters (remove `--category` / `--scope`).
+
+## Recommended Chaining
+- `+list-mcp-market` (browse) → `+add-mcp` (add to personal) → `+list-mcps` (verify)

package/skills/ae-agent/references/list-mcps.md

@@ -0,0 +1,37 @@
+# agent +list-mcps (List MCP Servers)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **MCP Servers / read**
+
+## Use Cases
+- List MCP servers visible to the current user (personal / company / system scopes).
+- Returns an array of MCP server summaries; key fields include `id`, `name`, `url`, `scope`, `enabled`.
+
+## Mandatory Rules (MUST)
+- Do not guess MCP server record IDs. Always call `+list-mcps` first when an ID is needed.
+
+## Command
+```bash
+ae-cli agent +list-mcps
+ae-cli agent +list-mcps --scope personal --format table
+ae-cli agent +list-mcps --scope company
+ae-cli agent +list-mcps --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--scope` | No | Filter by scope: `personal` \| `company` \| `system` |
+
+## Decision Rules
+- When the user needs an MCP server ID for `+del-mcp` / `+toggle-mcp` / `+set-mcp-meta`, call this first.
+- Use `--format table` for a scannable overview of many servers.
+
+## Next Steps on Failure
+- Empty result: confirm account permissions and the active AE host.
+- Auth error: run `ae-cli auth login`.
+
+## Recommended Chaining
+- `+list-mcps` → confirm `id` → `+toggle-mcp` / `+del-mcp` / `+set-mcp-meta`
+- `+list-mcp-market` (browse) → `+add-mcp` (add) → `+list-mcps` (verify)

package/skills/ae-agent/references/list-models.md

@@ -0,0 +1,38 @@
+# agent +list-models (List Models)
+
+> **Prerequisite:** Follow the Global AE CLI Rules in [`../SKILL.md`](../SKILL.md).
+
+Domain: **Models / read**
+
+## Use Cases
+- List models visible to the current user (personal / company / system scopes).
+- Returns an array of model summaries; key fields include `id`, `modelId`, `displayName`, `scope`, `enabled`.
+- The current selected model (from the runtime env) is annotated when available.
+
+## Mandatory Rules (MUST)
+- Do not guess model record IDs. Always call `+list-models` first when a model ID is needed.
+
+## Command
+```bash
+ae-cli agent +list-models
+ae-cli agent +list-models --scope personal --format table
+ae-cli agent +list-models --scope company
+ae-cli agent +list-models --dry-run
+```
+
+## Parameters
+| Parameter | Required | Description |
+|---|---|---|
+| `--scope` | No | Filter by scope: `personal` \| `company` \| `system` |
+
+## Decision Rules
+- When the user needs a model record ID for `+create-automation --model`, call this first.
+- `--scope personal` shows only the user's own custom models; `company` / `system` show shared models.
+- Use `--format table` for a scannable overview of many models.
+
+## Next Steps on Failure
+- Empty result: confirm account permissions and the active AE host.
+- Auth error: run `ae-cli auth login`.
+
+## Recommended Chaining
+- `+list-models` → confirm model ID → `+create-automation --model <id>` or `+toggle-model` / `+del-model`