Skip to content

/help

List available commands the user can invoke. Works from CLI or messaging channels. Triggers on /help, /commands, /agent:help, "qué comandos puedo usar", "help commands".

shell
$ npx -y skills add crisandrews/ClawCode --skill help --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/help
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

List available commands the user can invoke. Works from CLI or messaging channels. Triggers on /help, /commands, /agent:help, "qué comandos puedo usar", "help commands".

SKILL.md

help.SKILL.md
name: help
description: List available commands the user can invoke. Works from CLI or messaging channels. Triggers on /help, /commands, /agent:help, "qué comandos puedo usar", "help commands".
user-invocable: true

Help — list commands

Show a concise, LIVE list of all available commands. Never hardcode — always pull from the `list_commands` MCP tool so recently installed or removed skills are reflected.

Steps

1. **Detect the surface.** If the incoming message has a `<channel source="...">` marker, you're on a messaging channel. Otherwise you're on CLI or WebChat.

2. **Call `list_commands`** with the right format:

  • **CLI / WebChat:** `list_commands({ format: "table", includeTools: false })` — grouped markdown, readable.
  • **Messaging (WhatsApp, Telegram, Discord, iMessage):** `list_commands({ format: "compact", includeTools: false })` — one line per command, mobile-friendly.

Leave `includeTools: false` for the user-facing help — MCP tools are agent-invoked, not user-typed. Users who want the internals can ask "what MCP tools do you have?" and you call with `includeTools: true`.

3. **Print the output** from the tool as-is. Do not rewrite or reorder.

4. **Adapt formatting to the channel** after the tool output:

  • WhatsApp: strip `**bold**` → `*bold*`, remove markdown headers if too noisy
  • Telegram: keep `**bold**` or convert to HTML
  • Discord: markdown as-is
  • iMessage: strip markdown to plain text
  • CLI / WebChat: markdown as-is

5. **Append a short native-tools note** at the end (only on CLI):

   Native Claude Code commands (CLI only): /status /usage /cost /compact /clear /mcp /model /help

Example flows

CLI user asks `/help`

Call `list_commands({ format: "table", includeTools: false })`. Print the returned markdown. Append the native-tools note.

WhatsApp user says "what can you do?"

Call `list_commands({ format: "compact", includeTools: false })`. Convert any `**bold**` to `*bold*`. Don't include the native-tools note (doesn't apply).

Notes

  • `/help` and `/commands` are aliases.
  • Keep the response short on mobile channels. `compact` format handles that.
  • If the user wants the internals ("tools", "MCP"), call with `includeTools: true` so they see them too.
  • If nothing comes back, something's wrong with the install — suggest `/agent:doctor`.
Read more
Read it on GitHub ↗
Ships withcrisandrews-agent

Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a service mode for 24/7 runs. Imports from OpenClaw.

Get the whole plugin, auto-invoked
Stats
61
Stars
0
Views
14
Forks
Active
Maintenance
TypeScript
Language
MIT
License
2d ago
Last commit
3mo ago
Created

Repo: crisandrews/ClawCode

Other skills on crisandrews-agent.