Initial commit: OpenClaw Skill Collection

6 custom skills (assign-task, dispatch-webhook, daily-briefing,
task-capture, qmd-brain, tts-voice) with technical documentation.
Compatible with Claude Code, OpenClaw, Codex CLI, and OpenCode.

openclaw-knowhow-skill/docs/reference/cli/agent.md

@@ -0,0 +1,19 @@
+# agent
+
+# `openclaw agent`
+
+Run an agent turn via the Gateway (use `--local` for embedded).
+Use `--agent <id>` to target a configured agent directly.
+
+Related:
+
+* Agent send tool: [Agent send](/tools/agent-send)
+
+## Examples
+
+```bash
+openclaw agent --to +15555550123 --message "status update" --deliver
+openclaw agent --agent ops --message "Summarize logs"
+openclaw agent --session-id 1234 --message "Summarize inbox" --thinking medium
+openclaw agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
+```

openclaw-knowhow-skill/docs/reference/cli/agents.md

@@ -0,0 +1,29 @@
+# agents
+
+# `openclaw agents`
+
+Manage isolated agents (workspaces + auth + routing).
+
+## Key Features
+
+**Agent Management Commands:**
+The tool supports several operations including listing agents, adding new ones to specific workspaces, configuring identities, and deleting agents.
+
+**Identity Configuration:**
+Each agent workspace can contain an `IDENTITY.md` file at its root. Agents can be customized with fields such as name, theme, emoji, and avatar. Avatar files can reference workspace-relative paths, URLs, or data URIs.
+
+**Identity Setup Methods:**
+Users can load identity settings from an `IDENTITY.md` file or override specific properties directly via command-line arguments.
+
+**Configuration Structure:**
+Identity information is stored in the configuration under `agents.list[].identity`, containing customizable display properties that personalize each agent's presentation.
+
+## Commands
+
+```bash
+openclaw agents list
+openclaw agents add <name> --workspace <path>
+openclaw agents delete <id>
+```
+
+Related concepts: multi-agent routing and agent workspace architecture.

openclaw-knowhow-skill/docs/reference/cli/approvals.md

@@ -0,0 +1,44 @@
+# approvals
+
+# `openclaw approvals`
+
+Manage exec approvals for the **local host**, **gateway host**, or a **node host**.
+By default, commands target the local approvals file on disk. Use `--gateway` to target the gateway, or `--node` to target a specific node.
+
+Related:
+
+* Exec approvals: [Exec approvals](/tools/exec-approvals)
+* Nodes: [Nodes](/nodes)
+
+## Common commands
+
+```bash
+openclaw approvals get
+openclaw approvals get --node <id|name|ip>
+openclaw approvals get --gateway
+```
+
+## Replace approvals from a file
+
+```bash
+openclaw approvals set --file ./exec-approvals.json
+openclaw approvals set --node <id|name|ip> --file ./exec-approvals.json
+openclaw approvals set --gateway --file ./exec-approvals.json
+```
+
+## Allowlist helpers
+
+```bash
+openclaw approvals allowlist add "~/Projects/**/bin/rg"
+openclaw approvals allowlist add --agent main --node <id|name|ip> "/usr/bin/uptime"
+openclaw approvals allowlist add --agent "*" "/usr/bin/uname"
+
+openclaw approvals allowlist remove "~/Projects/**/bin/rg"
+```
+
+## Notes
+
+* `--node` uses the same resolver as `openclaw nodes` (id, name, ip, or id prefix).
+* `--agent` defaults to `"*"`, which applies to all agents.
+* The node host must advertise `system.execApprovals.get/set` (macOS app or headless node host).
+* Approvals files are stored per host at `~/.openclaw/exec-approvals.json`.

openclaw-knowhow-skill/docs/reference/cli/browser.md

@@ -0,0 +1,52 @@
+# browser
+
+# `openclaw browser`
+
+Manage browser control servers and enable automated browser interactions.
+
+## Overview
+
+OpenClaw's browser command manages browser control servers and enables automated browser interactions. The system supports two primary browser profiles:
+
+- **openclaw**: Launches a dedicated, isolated Chrome instance managed by OpenClaw
+- **chrome**: Controls existing Chrome tabs through a Chrome extension relay
+
+## Key Capabilities
+
+The tool supports standard browser automation tasks including:
+- Tab management (list, open, focus, close)
+- Navigation
+- Screenshots and snapshots
+- UI element interaction through reference-based automation
+
+## Usage Patterns
+
+Common operations include:
+
+- Managing tabs (list, open, focus, close)
+- Visual capture via snapshots and screenshots
+- Programmatic actions like clicking and typing on referenced UI elements
+- Remote browser control through node host proxies when browsers run on different machines
+
+## Commands
+
+```bash
+openclaw browser status
+openclaw browser start
+openclaw browser stop
+openclaw browser screenshot
+openclaw browser snapshot
+openclaw browser navigate <url>
+openclaw browser click --ref <ref>
+openclaw browser type --ref <ref> --text "content"
+```
+
+## Configuration
+
+Users can create custom browser profiles with specific names and colors, and specify profiles via the `--browser-profile` flag. Standard options include timeout settings, gateway URLs, and output formatting.
+
+## Extension Integration
+
+The Chrome extension relay allows manual attachment of existing Chrome tabs, requiring installation through the unpacked extension method rather than auto-attachment.
+
+For comprehensive setup details, see additional guides covering remote access, security considerations, and Tailscale integration.

openclaw-knowhow-skill/docs/reference/cli/channels.md

@@ -0,0 +1,73 @@
+# channels
+
+# `openclaw channels`
+
+Manage chat channel accounts and their runtime status on the Gateway.
+
+Related docs:
+
+* Channel guides: [Channels](/channels/index)
+* Gateway configuration: [Configuration](/gateway/configuration)
+
+## Common commands
+
+```bash
+openclaw channels list
+openclaw channels status
+openclaw channels capabilities
+openclaw channels capabilities --channel discord --target channel:123
+openclaw channels resolve --channel slack "#general" "@jane"
+openclaw channels logs --channel all
+```
+
+## Add / remove accounts
+
+```bash
+openclaw channels add --channel telegram --token <bot-token>
+openclaw channels remove --channel telegram --delete
+```
+
+Tip: `openclaw channels add --help` shows per-channel flags (token, app token, signal-cli paths, etc).
+
+## Login / logout (interactive)
+
+```bash
+openclaw channels login --channel whatsapp
+openclaw channels logout --channel whatsapp
+```
+
+## Troubleshooting
+
+* Run `openclaw status --deep` for a broad probe.
+* Use `openclaw doctor` for guided fixes.
+* `openclaw channels list` prints `Claude: HTTP 403 ... user:profile` → usage snapshot needs the `user:profile` scope. Use `--no-usage`, or provide a claude.ai session key (`CLAUDE_WEB_SESSION_KEY` / `CLAUDE_WEB_COOKIE`), or re-auth via Claude Code CLI.
+
+## Capabilities probe
+
+Fetch provider capability hints (intents/scopes where available) plus static feature support:
+
+```bash
+openclaw channels capabilities
+openclaw channels capabilities --channel discord --target channel:123
+```
+
+Notes:
+
+* `--channel` is optional; omit it to list every channel (including extensions).
+* `--target` accepts `channel:<id>` or a raw numeric channel id and only applies to Discord.
+* Probes are provider-specific: Discord intents + optional channel permissions; Slack bot + user scopes; Telegram bot flags + webhook; Signal daemon version; MS Teams app token + Graph roles/scopes (annotated where known). Channels without probes report `Probe: unavailable`.
+
+## Resolve names to IDs
+
+Resolve channel/user names to IDs using the provider directory:
+
+```bash
+openclaw channels resolve --channel slack "#general" "@jane"
+openclaw channels resolve --channel discord "My Server/#support" "@someone"
+openclaw channels resolve --channel matrix "Project Room"
+```
+
+Notes:
+
+* Use `--kind user|group|auto` to force the target type.
+* Resolution prefers active matches when multiple entries share the same name.

openclaw-knowhow-skill/docs/reference/cli/configure.md

@@ -0,0 +1,28 @@
+# configure
+
+# `openclaw configure`
+
+Interactive prompt to set up credentials, devices, and agent defaults.
+
+Note: The **Model** section now includes a multi-select for the
+`agents.defaults.models` allowlist (what shows up in `/model` and the model picker).
+
+Tip: `openclaw config` without a subcommand opens the same wizard. Use
+`openclaw config get|set|unset` for non-interactive edits.
+
+Related:
+
+* Gateway configuration reference: [Configuration](/gateway/configuration)
+* Config CLI: [Config](/cli/config)
+
+Notes:
+
+* Choosing where the Gateway runs always updates `gateway.mode`. You can select "Continue" without other sections if that is all you need.
+* Channel-oriented services (Slack/Discord/Matrix/Microsoft Teams) prompt for channel/room allowlists during setup. You can enter names or IDs; the wizard resolves names to IDs when possible.
+
+## Examples
+
+```bash
+openclaw configure
+openclaw configure --section models --section channels
+```

openclaw-knowhow-skill/docs/reference/cli/cron.md

@@ -0,0 +1,36 @@
+# cron
+
+# `openclaw cron`
+
+Manage cron jobs for the Gateway scheduler.
+
+Related:
+
+* Cron jobs: [Cron jobs](/automation/cron-jobs)
+
+Tip: run `openclaw cron --help` for the full command surface.
+
+Note: isolated `cron add` jobs default to `--announce` delivery. Use `--no-deliver` to keep
+output internal. `--deliver` remains as a deprecated alias for `--announce`.
+
+Note: one-shot (`--at`) jobs delete after success by default. Use `--keep-after-run` to keep them.
+
+## Common edits
+
+Update delivery settings without changing the message:
+
+```bash
+openclaw cron edit <job-id> --announce --channel telegram --to "123456789"
+```
+
+Disable delivery for an isolated job:
+
+```bash
+openclaw cron edit <job-id> --no-deliver
+```
+
+Announce to a specific channel:
+
+```bash
+openclaw cron edit <job-id> --announce --channel slack --to "channel:C1234567890"
+```

openclaw-knowhow-skill/docs/reference/cli/dashboard.md

@@ -0,0 +1,10 @@
+# dashboard
+
+# `openclaw dashboard`
+
+Open the Control UI using your current auth.
+
+```bash
+openclaw dashboard
+openclaw dashboard --no-open
+```

openclaw-knowhow-skill/docs/reference/cli/directory.md

@@ -0,0 +1,57 @@
+# directory
+
+# `openclaw directory`
+
+Directory lookups for channels that support it (contacts/peers, groups, and "me").
+
+## Common flags
+
+* `--channel <name>`: channel id/alias (required when multiple channels are configured; auto when only one is configured)
+* `--account <id>`: account id (default: channel default)
+* `--json`: output JSON
+
+## Notes
+
+* `directory` is meant to help you find IDs you can paste into other commands (especially `openclaw message send --target ...`).
+* For many channels, results are config-backed (allowlists / configured groups) rather than a live provider directory.
+* Default output is `id` (and sometimes `name`) separated by a tab; use `--json` for scripting.
+
+## Using results with `message send`
+
+```bash
+openclaw directory peers list --channel slack --query "U0"
+openclaw message send --channel slack --target user:U012ABCDEF --message "hello"
+```
+
+## ID formats (by channel)
+
+* WhatsApp: `+15551234567` (DM), `1234567890-1234567890@g.us` (group)
+* Telegram: `@username` or numeric chat id; groups are numeric ids
+* Slack: `user:U…` and `channel:C…`
+* Discord: `user:<id>` and `channel:<id>`
+* Matrix (plugin): `user:@user:server`, `room:!roomId:server`, or `#alias:server`
+* Microsoft Teams (plugin): `user:<id>` and `conversation:<id>`
+* Zalo (plugin): user id (Bot API)
+* Zalo Personal / `zalouser` (plugin): thread id (DM/group) from `zca` (`me`, `friend list`, `group list`)
+
+## Self ("me")
+
+```bash
+openclaw directory self --channel zalouser
+```
+
+## Peers (contacts/users)
+
+```bash
+openclaw directory peers list --channel zalouser
+openclaw directory peers list --channel zalouser --query "name"
+openclaw directory peers list --channel zalouser --limit 50
+```
+
+## Groups
+
+```bash
+openclaw directory groups list --channel zalouser
+openclaw directory groups list --channel zalouser --query "work"
+openclaw directory groups members --channel zalouser --group-id <id>
+```

openclaw-knowhow-skill/docs/reference/cli/dns.md

@@ -0,0 +1,17 @@
+# dns
+
+# `openclaw dns`
+
+DNS helpers for wide-area discovery (Tailscale + CoreDNS). Currently focused on macOS + Homebrew CoreDNS.
+
+Related:
+
+* Gateway discovery: [Discovery](/gateway/discovery)
+* Wide-area discovery config: [Configuration](/gateway/configuration)
+
+## Setup
+
+```bash
+openclaw dns setup
+openclaw dns setup --apply
+```

openclaw-knowhow-skill/docs/reference/cli/docs.md

@@ -0,0 +1,10 @@
+# docs
+
+# `openclaw docs`
+
+Search the live docs index.
+
+```bash
+openclaw docs browser extension
+openclaw docs sandbox allowHostControl
+```

openclaw-knowhow-skill/docs/reference/cli/doctor.md

@@ -0,0 +1,35 @@
+# doctor
+
+# `openclaw doctor`
+
+Health checks + quick fixes for the gateway and channels.
+
+Related:
+
+* Troubleshooting: [Troubleshooting](/gateway/troubleshooting)
+* Security audit: [Security](/gateway/security)
+
+## Examples
+
+```bash
+openclaw doctor
+openclaw doctor --repair
+openclaw doctor --deep
+```
+
+Notes:
+
+* Interactive prompts (like keychain/OAuth fixes) only run when stdin is a TTY and `--non-interactive` is **not** set. Headless runs (cron, Telegram, no terminal) will skip prompts.
+* `--fix` (alias for `--repair`) writes a backup to `~/.openclaw/openclaw.json.bak` and drops unknown config keys, listing each removal.
+
+## macOS: `launchctl` env overrides
+
+If you previously ran `launchctl setenv OPENCLAW_GATEWAY_TOKEN ...` (or `...PASSWORD`), that value overrides your config file and can cause persistent "unauthorized" errors.
+
+```bash
+launchctl getenv OPENCLAW_GATEWAY_TOKEN
+launchctl getenv OPENCLAW_GATEWAY_PASSWORD
+
+launchctl unsetenv OPENCLAW_GATEWAY_TOKEN
+launchctl unsetenv OPENCLAW_GATEWAY_PASSWORD
+```

openclaw-knowhow-skill/docs/reference/cli/gateway.md

@@ -0,0 +1,43 @@
+# gateway
+
+# `openclaw gateway`
+
+The Gateway serves as OpenClaw's WebSocket server managing channels, nodes, sessions, and hooks. All subcommands operate under the `openclaw gateway` namespace.
+
+## Running the Gateway
+
+Launch a local Gateway with:
+
+```bash
+openclaw gateway
+```
+
+Key startup requirements include setting `gateway.mode=local` in configuration, though `--allow-unconfigured` bypasses this for development. The system blocks loopback binding without authentication as a safety measure.
+
+## Query Commands
+
+Gateway queries use WebSocket RPC with flexible output formatting (human-readable by default, JSON via `--json` flag).
+
+**Available commands:**
+- `gateway health`: checks Gateway connectivity
+- `gateway status`: displays service status plus optional RPC probe
+- `gateway probe`: comprehensive debug command scanning configured and localhost gateways
+- `gateway call <method>`: low-level RPC helper for custom operations
+
+## Service Management
+
+Standard lifecycle commands include:
+
+```bash
+openclaw gateway install
+openclaw gateway start
+openclaw gateway stop
+openclaw gateway restart
+openclaw gateway uninstall
+```
+
+## Gateway Discovery
+
+The `gateway discover` command scans for Gateway beacons using multicast DNS-SD (`_openclaw-gw._tcp`). Discovery records include details like WebSocket ports, SSH configuration, and TLS fingerprints when applicable.
+
+Related documentation sections: Bonjour configuration, discovery protocols, and system configuration settings.

openclaw-knowhow-skill/docs/reference/cli/health.md

@@ -0,0 +1,16 @@
+# health
+
+# `openclaw health`
+
+Fetch health from the running Gateway.
+
+```bash
+openclaw health
+openclaw health --json
+openclaw health --verbose
+```
+
+Notes:
+
+* `--verbose` runs live probes and prints per-account timings when multiple accounts are configured.
+* Output includes per-agent session stores when multiple agents are configured.

openclaw-knowhow-skill/docs/reference/cli/hooks.md

@@ -0,0 +1,34 @@
+# hooks
+
+# `openclaw hooks`
+
+Manage event-driven automations for gateway commands and startup events.
+
+## Core Commands
+
+**Listing and Information:**
+- `openclaw hooks list` displays all discovered hooks with readiness status
+- `openclaw hooks info <name>` provides detailed information about specific hooks
+- `openclaw hooks check` shows overall eligibility summary
+
+**Management:**
+- `openclaw hooks enable <name>` activates a hook in your config
+- `openclaw hooks disable <name>` deactivates a hook
+- `openclaw hooks install <path-or-spec>` adds new hook packs from local directories, archives, or npm
+- `openclaw hooks update <id>` refreshes installed npm-based hook packs
+
+## Available Bundled Hooks
+
+The system includes four pre-built hooks:
+
+1. **session-memory** - Saves session context when `/new` command executes, storing output to `~/.openclaw/workspace/memory/`
+
+2. **command-logger** - Records all command events to a centralized audit file at `~/.openclaw/logs/commands.log`
+
+3. **soul-evil** - Swaps `SOUL.md` content with `SOUL_EVIL.md` during specified windows or randomly
+
+4. **boot-md** - Executes `BOOT.md` upon gateway startup (triggered by `gateway:startup` event)
+
+## Important Notes
+
+After enabling or disabling hooks, restart your gateway for changes to take effect. Plugin-managed hooks cannot be toggled directly through these commands - manage the parent plugin instead.

openclaw-knowhow-skill/docs/reference/cli/index.md

@@ -0,0 +1,171 @@
+# Complete CLI Reference Documentation
+
+## Overview
+
+This documentation provides comprehensive reference material for OpenClaw's command-line interface, detailing all available commands, options, and usage patterns.
+
+## Core Structure
+
+The CLI organizes functionality through a primary command with subcommands:
+
+```
+openclaw [--dev] [--profile <name>] <command>
+```
+
+### Global Options
+
+The system supports several flags applicable across commands:
+- `--dev`: Isolates state to `~/.openclaw-dev` with shifted default ports
+- `--profile <name>`: Isolates state to `~/.openclaw-<name>`
+- `--no-color`: Disables ANSI styling
+- `--version`: Displays version information
+
+### Output Formatting
+
+ANSI colors and progress indicators only render in TTY sessions. OSC-8 hyperlinks render as clickable links in supported terminals; otherwise we fall back to plain URLs.
+
+## Command Categories
+
+### Setup & Configuration
+
+**`setup`** initializes configuration and workspace with options for workspace path, wizard mode, and remote gateway configuration.
+
+**`onboard`** provides an interactive wizard supporting multiple flows (quickstart, advanced, manual) with authentication provider selection and gateway binding options.
+
+**`configure`** launches an interactive configuration wizard for models, channels, skills, and gateway settings.
+
+**`config`** offers non-interactive helpers for retrieving, setting, or removing configuration values using dot/bracket path notation.
+
+**`doctor`** performs health checks and applies quick fixes for configuration, gateway, and legacy services.
+
+### Channel Management
+
+**`channels`** manages chat channel accounts across platforms including WhatsApp, Telegram, Discord, Slack, Signal, iMessage, and Microsoft Teams.
+
+Subcommands include:
+- `list`: Display configured channels
+- `status`: Check gateway reachability
+- `add`: Wizard-style or non-interactive setup
+- `remove`: Disable or delete configurations
+- `login`/`logout`: Interactive authentication (platform-dependent)
+- `logs`: Display recent channel activity
+
+### Skill & Plugin Management
+
+**`skills`** lists available skills and readiness information:
+- `list`: Enumerate all skills
+- `info <name>`: Display specific skill details
+- `check`: Summary of ready versus missing requirements
+
+**`plugins`** manages extensions and their configuration:
+- `list`: Discover available plugins
+- `install`: Add plugins from various sources
+- `enable`/`disable`: Toggle activation
+- `doctor`: Report load errors
+
+### Messaging & Agent Control
+
+**`message`** provides unified outbound messaging with subcommands for sending, polling, reacting, editing, deleting, and managing permissions across channels.
+
+**`agent`** executes a single agent turn via the Gateway with options for message content, destination, session tracking, and verbose output.
+
+**`agents`** manages isolated agent workspaces:
+- `list`: Display configured agents
+- `add`: Create new isolated agent
+- `delete`: Remove agent and prune state
+
+### Gateway Operations
+
+**`gateway`** runs the WebSocket Gateway with binding, authentication, and Tailscale options.
+
+Gateway service management includes:
+- `status`: Probe gateway health
+- `install`: Install service
+- `start`/`stop`/`restart`: Control service state
+
+**`logs`** tails Gateway file logs via RPC, with support for colorized structured output in TTY sessions and JSON formatting.
+
+### System & Monitoring
+
+**`status`** displays linked session health and recent recipients with options for comprehensive diagnostics and provider usage information.
+
+**`health`** fetches current health status from the running Gateway.
+
+**`sessions`** lists stored conversation sessions with filtering by activity duration.
+
+**`system`** manages system-level operations:
+- `event`: Enqueue system events
+- `heartbeat`: Control heartbeat functionality
+- `presence`: List system presence entries
+
+### Model Configuration
+
+**`models`** manages AI model selection and authentication:
+- `list`: Enumerate available models
+- `status`: Display current configuration
+- `set`: Designate primary model
+- `scan`: Discover new models with filtering options
+- `auth`: Configure authentication credentials
+- `aliases`: Create model shortcuts
+- `fallbacks`: Define backup models
+
+### Automation
+
+**`cron`** manages scheduled jobs with support for:
+- Time-based scheduling (`--at`, `--every`, `--cron`)
+- System events or messaging payloads
+- Job lifecycle management (enable/disable/edit)
+
+### Node Management
+
+**`node`** operates headless node hosts or manages them as background services.
+
+**`nodes`** communicates with Gateway-paired nodes supporting:
+- Status monitoring and connection filtering
+- Command invocation with timeout control
+- Camera operations (snap, clip)
+- Canvas and screen management
+- Location tracking
+
+### Browser Control
+
+**`browser`** controls dedicated Chrome/Brave/Edge/Chromium instances:
+
+Management: `status`, `start`, `stop`, `reset-profile`, `profiles`, `create-profile`, `delete-profile`
+
+Inspection: `screenshot`, `snapshot` with format and selector options
+
+Actions: `navigate`, `click`, `type`, `press`, `hover`, `drag`, `select`, `upload`, `fill`, `dialog`, `wait`, `evaluate`, `console`, `pdf`
+
+### Additional Tools
+
+**`memory`** enables vector search over markdown files:
+- `status`: Display index statistics
+- `index`: Rebuild index
+- `search`: Execute semantic queries
+
+**`approvals`** manages approval configurations with allowlist operations.
+
+**`security`** provides audit functionality with optional deep probing and automatic fixes.
+
+**`tui`** opens an interactive terminal user interface connected to the Gateway.
+
+**`docs`** searches live documentation.
+
+## Reset & Cleanup
+
+**`reset`** clears local configuration and state with scoping options (config only, config+credentials+sessions, or full reset).
+
+**`uninstall`** removes the gateway service and associated data while preserving the CLI installation.
+
+**`update`** manages version upgrades.
+
+## Color Palette
+
+OpenClaw employs a distinctive color scheme for terminal output:
+- accent (#FF5A2D): headings, labels, primary highlights
+- accentBright (#FF7A3D): command names, emphasis
+- success (#2FBF71): success states
+- error (#E23D2D): errors, failures
+
+This reference encompasses the complete command taxonomy with emphasis on practical usage patterns and option availability across the OpenClaw platform.

openclaw-knowhow-skill/docs/reference/cli/logs.md

@@ -0,0 +1,18 @@
+# logs
+
+# `openclaw logs`
+
+Tail Gateway file logs over RPC (works in remote mode).
+
+Related:
+
+* Logging overview: [Logging](/logging)
+
+## Examples
+
+```bash
+openclaw logs
+openclaw logs --follow
+openclaw logs --json
+openclaw logs --limit 500
+```

openclaw-knowhow-skill/docs/reference/cli/memory.md

@@ -0,0 +1,34 @@
+# memory
+
+# `openclaw memory`
+
+Semantic memory indexing and search operations through the active memory plugin system.
+
+## Core Functionality
+
+This tool provides three primary capabilities:
+
+1. **Status Monitoring**: Check memory system health with `openclaw memory status`
+2. **Indexing**: Build or rebuild the semantic index via `openclaw memory index`
+3. **Search**: Query indexed content with `openclaw memory search`
+
+## Examples
+
+```bash
+openclaw memory status
+openclaw memory status --deep
+openclaw memory index
+openclaw memory search "query terms"
+```
+
+## Key Command Options
+
+Users can scope operations to individual agents using `--agent <id>` or apply verbose logging with the `--verbose` flag for detailed diagnostic output.
+
+## Advanced Features
+
+The `--deep` flag enables probes for vector + embedding availability, while combining `--deep --index` triggers automatic reindexing when the storage is marked as dirty. The system also respects extra paths configured through `memorySearch.extraPaths`.
+
+## Plugin Architecture
+
+Memory functionality depends on the active memory plugin (defaulting to `memory-core`), which can be disabled by setting `plugins.slots.memory = "none"`.

openclaw-knowhow-skill/docs/reference/cli/message.md

@@ -0,0 +1,233 @@
+# message
+
+# `openclaw message`
+
+Single outbound command for sending messages and channel actions
+(Discord/Google Chat/Slack/Mattermost (plugin)/Telegram/WhatsApp/Signal/iMessage/MS Teams).
+
+## Usage
+
+```
+openclaw message <subcommand> [flags]
+```
+
+Channel selection:
+
+* `--channel` required if more than one channel is configured.
+* If exactly one channel is configured, it becomes the default.
+* Values: `whatsapp|telegram|discord|googlechat|slack|mattermost|signal|imessage|msteams` (Mattermost requires plugin)
+
+Target formats (`--target`):
+
+* WhatsApp: E.164 or group JID
+* Telegram: chat id or `@username`
+* Discord: `channel:<id>` or `user:<id>` (or `<@id>` mention; raw numeric ids are treated as channels)
+* Google Chat: `spaces/<spaceId>` or `users/<userId>`
+* Slack: `channel:<id>` or `user:<id>` (raw channel id is accepted)
+* Mattermost (plugin): `channel:<id>`, `user:<id>`, or `@username` (bare ids are treated as channels)
+* Signal: `+E.164`, `group:<id>`, `signal:+E.164`, `signal:group:<id>`, or `username:<name>`/`u:<name>`
+* iMessage: handle, `chat_id:<id>`, `chat_guid:<guid>`, or `chat_identifier:<id>`
+* MS Teams: conversation id (`19:...@thread.tacv2`) or `conversation:<id>` or `user:<aad-object-id>`
+
+Name lookup:
+
+* For supported providers (Discord/Slack/etc), channel names like `Help` or `#help` are resolved via the directory cache.
+* On cache miss, OpenClaw will attempt a live directory lookup when the provider supports it.
+
+## Common flags
+
+* `--channel <name>`
+* `--account <id>`
+* `--target <dest>` (target channel or user for send/poll/read/etc)
+* `--targets <name>` (repeat; broadcast only)
+* `--json`
+* `--dry-run`
+* `--verbose`
+
+## Actions
+
+### Core
+
+* `send`
+  * Channels: WhatsApp/Telegram/Discord/Google Chat/Slack/Mattermost (plugin)/Signal/iMessage/MS Teams
+  * Required: `--target`, plus `--message` or `--media`
+  * Optional: `--media`, `--reply-to`, `--thread-id`, `--gif-playback`
+  * Telegram only: `--buttons` (requires `channels.telegram.capabilities.inlineButtons` to allow it)
+  * Telegram only: `--thread-id` (forum topic id)
+  * Slack only: `--thread-id` (thread timestamp; `--reply-to` uses the same field)
+  * WhatsApp only: `--gif-playback`
+
+* `poll`
+  * Channels: WhatsApp/Discord/MS Teams
+  * Required: `--target`, `--poll-question`, `--poll-option` (repeat)
+  * Optional: `--poll-multi`
+  * Discord only: `--poll-duration-hours`, `--message`
+
+* `react`
+  * Channels: Discord/Google Chat/Slack/Telegram/WhatsApp/Signal
+  * Required: `--message-id`, `--target`
+  * Optional: `--emoji`, `--remove`, `--participant`, `--from-me`, `--target-author`, `--target-author-uuid`
+  * Note: `--remove` requires `--emoji` (omit `--emoji` to clear own reactions where supported; see /tools/reactions)
+  * WhatsApp only: `--participant`, `--from-me`
+  * Signal group reactions: `--target-author` or `--target-author-uuid` required
+
+* `reactions`
+  * Channels: Discord/Google Chat/Slack
+  * Required: `--message-id`, `--target`
+  * Optional: `--limit`
+
+* `read`
+  * Channels: Discord/Slack
+  * Required: `--target`
+  * Optional: `--limit`, `--before`, `--after`
+  * Discord only: `--around`
+
+* `edit`
+  * Channels: Discord/Slack
+  * Required: `--message-id`, `--message`, `--target`
+
+* `delete`
+  * Channels: Discord/Slack/Telegram
+  * Required: `--message-id`, `--target`
+
+* `pin` / `unpin`
+  * Channels: Discord/Slack
+  * Required: `--message-id`, `--target`
+
+* `pins` (list)
+  * Channels: Discord/Slack
+  * Required: `--target`
+
+* `permissions`
+  * Channels: Discord
+  * Required: `--target`
+
+* `search`
+  * Channels: Discord
+  * Required: `--guild-id`, `--query`
+  * Optional: `--channel-id`, `--channel-ids` (repeat), `--author-id`, `--author-ids` (repeat), `--limit`
+
+### Threads
+
+* `thread create`
+  * Channels: Discord
+  * Required: `--thread-name`, `--target` (channel id)
+  * Optional: `--message-id`, `--auto-archive-min`
+
+* `thread list`
+  * Channels: Discord
+  * Required: `--guild-id`
+  * Optional: `--channel-id`, `--include-archived`, `--before`, `--limit`
+
+* `thread reply`
+  * Channels: Discord
+  * Required: `--target` (thread id), `--message`
+  * Optional: `--media`, `--reply-to`
+
+### Emojis
+
+* `emoji list`
+  * Discord: `--guild-id`
+  * Slack: no extra flags
+
+* `emoji upload`
+  * Channels: Discord
+  * Required: `--guild-id`, `--emoji-name`, `--media`
+  * Optional: `--role-ids` (repeat)
+
+### Stickers
+
+* `sticker send`
+  * Channels: Discord
+  * Required: `--target`, `--sticker-id` (repeat)
+  * Optional: `--message`
+
+* `sticker upload`
+  * Channels: Discord
+  * Required: `--guild-id`, `--sticker-name`, `--sticker-desc`, `--sticker-tags`, `--media`
+
+### Roles / Channels / Members / Voice
+
+* `role info` (Discord): `--guild-id`
+* `role add` / `role remove` (Discord): `--guild-id`, `--user-id`, `--role-id`
+* `channel info` (Discord): `--target`
+* `channel list` (Discord): `--guild-id`
+* `member info` (Discord/Slack): `--user-id` (+ `--guild-id` for Discord)
+* `voice status` (Discord): `--guild-id`, `--user-id`
+
+### Events
+
+* `event list` (Discord): `--guild-id`
+* `event create` (Discord): `--guild-id`, `--event-name`, `--start-time`
+  * Optional: `--end-time`, `--desc`, `--channel-id`, `--location`, `--event-type`
+
+### Moderation (Discord)
+
+* `timeout`: `--guild-id`, `--user-id` (optional `--duration-min` or `--until`; omit both to clear timeout)
+* `kick`: `--guild-id`, `--user-id` (+ `--reason`)
+* `ban`: `--guild-id`, `--user-id` (+ `--delete-days`, `--reason`)
+  * `timeout` also supports `--reason`
+
+### Broadcast
+
+* `broadcast`
+  * Channels: any configured channel; use `--channel all` to target all providers
+  * Required: `--targets` (repeat)
+  * Optional: `--message`, `--media`, `--dry-run`
+
+## Examples
+
+Send a Discord reply:
+
+```bash
+openclaw message send --channel discord \
+  --target channel:123 --message "hi" --reply-to 456
+```
+
+Create a Discord poll:
+
+```bash
+openclaw message poll --channel discord \
+  --target channel:123 \
+  --poll-question "Snack?" \
+  --poll-option Pizza --poll-option Sushi \
+  --poll-multi --poll-duration-hours 48
+```
+
+Send a Teams proactive message:
+
+```bash
+openclaw message send --channel msteams \
+  --target conversation:19:abc@thread.tacv2 --message "hi"
+```
+
+Create a Teams poll:
+
+```bash
+openclaw message poll --channel msteams \
+  --target conversation:19:abc@thread.tacv2 \
+  --poll-question "Lunch?" \
+  --poll-option Pizza --poll-option Sushi
+```
+
+React in Slack:
+
+```bash
+openclaw message react --channel slack \
+  --target C123 --message-id 456 --emoji "check"
+```
+
+React in a Signal group:
+
+```bash
+openclaw message react --channel signal \
+  --target signal:group:abc123 --message-id 1737630212345 \
+  --emoji "check" --target-author-uuid 123e4567-e89b-12d3-a456-426614174000
+```
+
+Send Telegram inline buttons:
+
+```bash
+openclaw message send --channel telegram --target @mychat --message "Choose:" \
+  --buttons '[ [{"text":"Yes","callback_data":"cmd:yes"}], [{"text":"No","callback_data":"cmd:no"}] ]'
+```

openclaw-knowhow-skill/docs/reference/cli/models.md

@@ -0,0 +1,73 @@
+# models
+
+# `openclaw models`
+
+Model discovery, scanning, and configuration (default model, fallbacks, auth profiles).
+
+Related:
+
+* Providers + models: [Models](/providers/models)
+* Provider auth setup: [Getting started](/start/getting-started)
+
+## Common commands
+
+```bash
+openclaw models status
+openclaw models list
+openclaw models set <model-or-alias>
+openclaw models scan
+```
+
+`openclaw models status` shows the resolved default/fallbacks plus an auth overview.
+When provider usage snapshots are available, the OAuth/token status section includes
+provider usage headers.
+Add `--probe` to run live auth probes against each configured provider profile.
+Probes are real requests (may consume tokens and trigger rate limits).
+Use `--agent <id>` to inspect a configured agent's model/auth state. When omitted,
+the command uses `OPENCLAW_AGENT_DIR`/`PI_CODING_AGENT_DIR` if set, otherwise the
+configured default agent.
+
+Notes:
+
+* `models set <model-or-alias>` accepts `provider/model` or an alias.
+* Model refs are parsed by splitting on the **first** `/`. If the model ID includes `/` (OpenRouter-style), include the provider prefix (example: `openrouter/moonshotai/kimi-k2`).
+* If you omit the provider, OpenClaw treats the input as an alias or a model for the **default provider** (only works when there is no `/` in the model ID).
+
+### `models status`
+
+Options:
+
+* `--json`
+* `--plain`
+* `--check` (exit 1=expired/missing, 2=expiring)
+* `--probe` (live probe of configured auth profiles)
+* `--probe-provider <name>` (probe one provider)
+* `--probe-profile <id>` (repeat or comma-separated profile ids)
+* `--probe-timeout <ms>`
+* `--probe-concurrency <n>`
+* `--probe-max-tokens <n>`
+* `--agent <id>` (configured agent id; overrides `OPENCLAW_AGENT_DIR`/`PI_CODING_AGENT_DIR`)
+
+## Aliases + fallbacks
+
+```bash
+openclaw models aliases list
+openclaw models fallbacks list
+```
+
+## Auth profiles
+
+```bash
+openclaw models auth add
+openclaw models auth login --provider <id>
+openclaw models auth setup-token
+openclaw models auth paste-token
+```
+
+`models auth login` runs a provider plugin's auth flow (OAuth/API key). Use
+`openclaw plugins list` to see which providers are installed.
+
+Notes:
+
+* `setup-token` prompts for a setup-token value (generate it with `claude setup-token` on any machine).
+* `paste-token` accepts a token string generated elsewhere or from automation.

openclaw-knowhow-skill/docs/reference/cli/nodes.md

@@ -0,0 +1,48 @@
+# nodes
+
+# `openclaw nodes`
+
+Manage paired devices and enable invocation of node capabilities.
+
+## Overview
+
+The `openclaw nodes` command manages paired devices and enables invocation of node capabilities. This includes listing nodes, approving pending connections, checking status, and executing commands remotely.
+
+## Key Commands
+
+**Listing and Status:**
+
+```bash
+openclaw nodes list
+openclaw nodes list --pending
+openclaw nodes list --connected
+openclaw nodes status <id|name|ip>
+```
+
+The tool provides commands to display pending and paired nodes, with options to filter by connection status or timeframe. Users can retrieve only currently-connected nodes or those connecting within specified durations like 24 hours or 7 days.
+
+**Execution:**
+
+Remote command execution is available through two approaches:
+
+```bash
+openclaw nodes invoke <id|name|ip> --method <method> --params <json>
+openclaw nodes run <id|name|ip> -- <command>
+```
+
+The `invoke` command uses structured parameters, while the `run` command uses shell-style syntax. The system supports both direct commands and raw shell strings.
+
+## Important Features
+
+**Exec-style Defaults:**
+The `nodes run` command mirrors standard execution behavior by reading configuration from `tools.exec.*` settings and implementing approval workflows before invoking system commands.
+
+**Customization Options:**
+Users can specify working directories, environment variables, command timeouts, and security levels. Additional flags allow requiring screen recording permissions and agent-scoped approvals.
+
+**Node Identification:**
+Commands accept node references by ID, name, or IP address for flexible targeting.
+
+## Notes
+
+A compatible node must advertise `system.run` capabilities, such as a macOS companion application or headless node host.

openclaw-knowhow-skill/docs/reference/cli/onboard.md

@@ -0,0 +1,36 @@
+# onboard
+
+# `openclaw onboard`
+
+Interactive onboarding wizard (local or remote Gateway setup).
+
+## Related guides
+
+* CLI onboarding hub: [Onboarding Wizard (CLI)](/start/wizard)
+* CLI onboarding reference: [CLI Onboarding Reference](/start/wizard-cli-reference)
+* CLI automation: [CLI Automation](/start/wizard-cli-automation)
+* macOS onboarding: [Onboarding (macOS App)](/start/onboarding)
+
+## Examples
+
+```bash
+openclaw onboard
+openclaw onboard --flow quickstart
+openclaw onboard --flow manual
+openclaw onboard --mode remote --remote-url ws://gateway-host:18789
+```
+
+Flow notes:
+
+* `quickstart`: minimal prompts, auto-generates a gateway token.
+* `manual`: full prompts for port/bind/auth (alias of `advanced`).
+* Fastest first chat: `openclaw dashboard` (Control UI, no channel setup).
+
+## Common follow-up commands
+
+```bash
+openclaw configure
+openclaw agents add <name>
+```
+
+Note: `--json` does not imply non-interactive mode. Use `--non-interactive` for scripts.

openclaw-knowhow-skill/docs/reference/cli/pairing.md

@@ -0,0 +1,16 @@
+# pairing
+
+# `openclaw pairing`
+
+Approve or inspect DM pairing requests (for channels that support pairing).
+
+Related:
+
+* Pairing flow: [Pairing](/start/pairing)
+
+## Commands
+
+```bash
+openclaw pairing list whatsapp
+openclaw pairing approve whatsapp <code> --notify
+```

openclaw-knowhow-skill/docs/reference/cli/plugins.md

@@ -0,0 +1,43 @@
+# plugins
+
+# `openclaw plugins`
+
+Manage gateway extensions that load in-process.
+
+## Overview
+
+The OpenClaw plugins system manages gateway extensions that load in-process. Bundled plugins ship with OpenClaw but start disabled. Use `plugins enable` to activate them.
+
+## Key Commands
+
+```bash
+openclaw plugins list
+openclaw plugins info <name>
+openclaw plugins enable <name>
+openclaw plugins disable <name>
+openclaw plugins install <path-or-spec>
+openclaw plugins install <path> --link
+openclaw plugins update <id>
+openclaw plugins update --all
+openclaw plugins doctor
+```
+
+## Installation Requirements
+
+Plugins must include a manifest file (`openclaw.plugin.json`) containing inline JSON Schema specifications. Missing/invalid manifests or schemas prevent the plugin from loading and fail config validation.
+
+## Installation Methods
+
+Users can install plugins via:
+
+1. **Direct path or specification**: `openclaw plugins install <path-or-spec>`
+2. **Linked local directory**: Using the `--link` flag to reference a local folder without copying
+3. **Supported archive formats**: ZIP, TGZ, TAR.GZ, and TAR files
+
+## Security Considerations
+
+Treat plugin installs like running code. Prefer pinned versions.
+
+## Update Capabilities
+
+Updates apply only to plugins installed from npm and tracked in the configuration. A dry-run option allows users to preview changes before applying them.

openclaw-knowhow-skill/docs/reference/cli/reset.md

@@ -0,0 +1,28 @@
+# reset
+
+# `openclaw reset`
+
+Clear local configuration and state (CLI remains).
+
+## Overview
+
+The `openclaw reset` command clears local configuration and state while preserving the CLI installation itself.
+
+## Examples
+
+```bash
+openclaw reset
+openclaw reset --dry-run
+openclaw reset --scope config+creds+sessions --yes --non-interactive
+```
+
+## Key Options
+
+* `--dry-run`: Preview changes without applying them
+* `--scope`: Specify what to reset (config, credentials, sessions)
+* `--yes`: Skip confirmation prompts
+* `--non-interactive`: Run without user interaction
+
+## Purpose
+
+This command helps users clear their local settings and stored data while keeping the CLI tool itself installed and functional.

openclaw-knowhow-skill/docs/reference/cli/sandbox.md

@@ -0,0 +1,44 @@
+# sandbox
+
+# `openclaw sandbox`
+
+Manage Docker-based isolated containers for secure agent execution.
+
+## Overview
+
+The OpenClaw sandbox system manages Docker-based isolated containers for secure agent execution. The CLI provides tools to inspect, list, and recreate these containers when configurations or images change.
+
+## Key Commands
+
+**`openclaw sandbox explain`** displays effective sandbox settings, including mode, scope, workspace access, and tool policies with relevant configuration paths.
+
+**`openclaw sandbox list`** enumerates all sandbox containers, showing their operational status, Docker image details, creation time, idle duration, and associated session/agent information.
+
+**`openclaw sandbox recreate`** forcefully removes containers to trigger fresh initialization with current images and configurations. Supports filtering by session, agent, or container type.
+
+## Examples
+
+```bash
+openclaw sandbox explain
+openclaw sandbox list
+openclaw sandbox recreate
+openclaw sandbox recreate --session <id>
+openclaw sandbox recreate --agent <id>
+```
+
+## Primary Use Cases
+
+After updating Docker images or modifying sandbox configuration settings, the recreate command ensures containers reflect these changes rather than persisting with outdated configurations. This addresses a core issue: existing containers continue running with old settings while the system waits up to 24 hours for automatic pruning.
+
+## Configuration Location
+
+Sandbox settings reside in `~/.openclaw/openclaw.json` under `agents.defaults.sandbox`, with per-agent overrides available in `agents.list[].sandbox`. Key parameters include:
+
+* Execution mode (off/non-main/all)
+* Scope level (session/agent/shared)
+* Docker image specification
+* Pruning thresholds
+
+## Related Resources
+
+See additional documentation covering broader sandboxing concepts, agent workspace configuration, and the doctor command for sandbox diagnostics verification.

openclaw-knowhow-skill/docs/reference/cli/security.md

@@ -0,0 +1,21 @@
+# security
+
+# `openclaw security`
+
+Security tools (audit + optional fixes).
+
+Related:
+
+* Security guide: [Security](/gateway/security)
+
+## Audit
+
+```bash
+openclaw security audit
+openclaw security audit --deep
+openclaw security audit --fix
+```
+
+The audit warns when multiple DM senders share the main session and recommends **secure DM mode**: `session.dmScope="per-channel-peer"` (or `per-account-channel-peer` for multi-account channels) for shared inboxes.
+
+It also warns when small models (`<=300B`) are used without sandboxing and with web/browser tools enabled.

openclaw-knowhow-skill/docs/reference/cli/sessions.md

@@ -0,0 +1,16 @@
+# sessions
+
+# `openclaw sessions`
+
+List stored conversation sessions.
+
+```bash
+openclaw sessions
+openclaw sessions --active 120
+openclaw sessions --json
+```
+
+Notes:
+
+* The `--active` flag filters sessions by activity duration (in minutes).
+* Use `--json` for programmatic consumption.

openclaw-knowhow-skill/docs/reference/cli/setup.md

@@ -0,0 +1,29 @@
+# setup
+
+# `openclaw setup`
+
+Initialize the OpenClaw configuration file and agent workspace environment.
+
+## Overview
+
+The `openclaw setup` command establishes `~/.openclaw/openclaw.json` and sets up the agent workspace.
+
+## Basic Usage
+
+```bash
+openclaw setup
+openclaw setup --workspace ~/.openclaw/workspace
+```
+
+## Wizard Mode
+
+To launch the interactive onboarding wizard during setup:
+
+```bash
+openclaw setup --wizard
+```
+
+## Related Resources
+
+* Getting started guide: [Getting Started](/start/getting-started)
+* Onboarding wizard documentation: [Onboarding](/start/onboarding)

openclaw-knowhow-skill/docs/reference/cli/skills.md

@@ -0,0 +1,20 @@
+# skills
+
+# `openclaw skills`
+
+Inspect skills (bundled + workspace + managed overrides) and see what's eligible vs missing requirements.
+
+Related:
+
+* Skills system: [Skills](/tools/skills)
+* Skills config: [Skills config](/tools/skills-config)
+* ClawHub installs: [ClawHub](/tools/clawhub)
+
+## Commands
+
+```bash
+openclaw skills list
+openclaw skills list --eligible
+openclaw skills info <name>
+openclaw skills check
+```

openclaw-knowhow-skill/docs/reference/cli/status.md

@@ -0,0 +1,20 @@
+# status
+
+# `openclaw status`
+
+Diagnostics for channels + sessions.
+
+```bash
+openclaw status
+openclaw status --all
+openclaw status --deep
+openclaw status --usage
+```
+
+Notes:
+
+* `--deep` runs live probes (WhatsApp Web + Telegram + Discord + Google Chat + Slack + Signal).
+* Output includes per-agent session stores when multiple agents are configured.
+* Overview includes Gateway + node host service install/runtime status when available.
+* Overview includes update channel + git SHA (for source checkouts).
+* Update info surfaces in the Overview; if an update is available, status prints a hint to run `openclaw update` (see [Updating](/install/updating)).

openclaw-knowhow-skill/docs/reference/cli/system.md

@@ -0,0 +1,32 @@
+# system
+
+# `openclaw system`
+
+System-level helpers for the Gateway: enqueue system events, control heartbeats, and view presence.
+
+## Key Capabilities
+
+**System Events**: Enqueue messages that inject into prompts as system lines, with options to trigger immediately or await the next scheduled heartbeat.
+
+**Heartbeat Management**: Enable, disable, or check the status of periodic heartbeat events.
+
+**Presence Monitoring**: Display current system presence entries including nodes and instance statuses.
+
+## Commands
+
+```bash
+openclaw system event --text "message" --mode now
+openclaw system event --text "message" --mode next-heartbeat
+openclaw system heartbeat status
+openclaw system heartbeat enable
+openclaw system heartbeat disable
+openclaw system presence
+```
+
+## Notable Parameters
+
+The system event command accepts text content, execution mode selection (`now` or `next-heartbeat`), and optional JSON output formatting. Similarly, heartbeat and presence commands support JSON output for programmatic use.
+
+## Requirements
+
+A running Gateway reachable by your current config (local or remote) is necessary. Note that system events are temporary rather than persisting across restarts.

openclaw-knowhow-skill/docs/reference/cli/tui.md

@@ -0,0 +1,17 @@
+# tui
+
+# `openclaw tui`
+
+Open the terminal UI connected to the Gateway.
+
+Related:
+
+* TUI guide: [TUI](/tui)
+
+## Examples
+
+```bash
+openclaw tui
+openclaw tui --url ws://127.0.0.1:18789 --token <token>
+openclaw tui --session main --deliver
+```

openclaw-knowhow-skill/docs/reference/cli/uninstall.md

@@ -0,0 +1,11 @@
+# uninstall
+
+# `openclaw uninstall`
+
+Uninstall the gateway service + local data (CLI remains).
+
+```bash
+openclaw uninstall
+openclaw uninstall --all --yes
+openclaw uninstall --dry-run
+```

openclaw-knowhow-skill/docs/reference/cli/update.md

@@ -0,0 +1,39 @@
+# update
+
+# `openclaw update`
+
+Manage OpenClaw updates across stable, beta, and development channels.
+
+## Overview
+
+The `openclaw update` command manages OpenClaw updates across stable, beta, and development channels. This tool handles version switching while maintaining configuration integrity.
+
+## Key Capabilities
+
+The update system supports multiple installation methods. When switching channels explicitly, OpenClaw also keeps the install method aligned with your chosen channel - dev uses git checkouts, while stable/beta use npm distribution tags.
+
+## Primary Commands
+
+```bash
+openclaw update
+openclaw update status
+openclaw update wizard
+openclaw update --channel beta
+openclaw update --channel dev
+```
+
+## Important Safeguards
+
+The update process includes verification steps:
+
+* For git-based installations, the system requires a clean worktree (no uncommitted changes) before proceeding.
+* Downgrades require confirmation because older versions can break configuration.
+
+## Update Workflow Details
+
+For dev channel users, the system performs preflight checks in a temporary workspace and can walk back up to 10 commits to find the newest clean build if the latest version has issues. All update paths conclude with running `openclaw doctor` as a validation step.
+
+## Additional Options
+
+* `--no-restart`: Skip Gateway service restart
+* `--json`: Output machine-readable results for automation purposes

openclaw-knowhow-skill/docs/reference/cli/voicecall.md

@@ -0,0 +1,44 @@
+# voicecall
+
+# `openclaw voicecall`
+
+Plugin-provided voice call functionality (requires voice-call plugin).
+
+## Overview
+
+The `voicecall` command is a plugin-provided feature available when the voice-call plugin is installed and enabled.
+
+## Key Commands
+
+```bash
+# Check call status
+openclaw voicecall status --call-id <id>
+
+# Initiate a call
+openclaw voicecall call --to "+15555550123" --message "Hello" --mode notify
+
+# Continue a call
+openclaw voicecall continue --call-id <id> --message "Any questions?"
+
+# End a call
+openclaw voicecall end --call-id <id>
+```
+
+## Webhook Exposure
+
+Expose webhooks using Tailscale:
+
+```bash
+# Serve mode
+openclaw voicecall expose --mode serve
+
+# Funnel mode
+openclaw voicecall expose --mode funnel
+
+# Disable exposure
+openclaw voicecall unexpose
+```
+
+## Security Guidance
+
+Only expose the webhook endpoint to networks you trust. Prefer Tailscale Serve over Funnel when feasible due to security considerations.