Skip to main content
Agent skill

Configure Channel

Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Configure Channel when an AI agent needs a reusable SKILL.md workflow for this job: Configure and prove a chat channel with non-interactive one-liners; secrets only as SecretRefs.

When not to use it

Skip Configure Channel when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/configure-channel
# Save SKILL.md to ~/.claude/skills/configure-channel/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/configure-channel/SKILL.md. For a shared project, commit the folder at .claude/skills/configure-channel/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Configure Channel skill for this task: Use Configure Channel when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

68/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
69/100
Practical detail
68/100
Source evidence
63/100
Source signals
72/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Configure a channel

Never print or persist secret values; channel tokens enter config only as SecretRefs, or through the in-session `connect_channel` flow where the operator types the secret into a masked prompt. Never hand-edit config files on disk. Every run ends with the observable Prove result or an exact explanation of why it could not be proven.

## Gather

``` openclaw channels list --all openclaw channels status openclaw config get channels --json # "Config path not found" is normal before first setup ```

Confirm the exact config path before writing — key names differ per channel (`channels.telegram.botToken`, `channels.discord.token`, ...):

``` openclaw config schema --json | jq '.properties.channels.properties.telegram' ```

## Mutate

Confirm the intended account and access changes with the operator before writing. Preserve existing approved allowlist entries, `dmPolicy`, and `groupPolicy` unless their replacement or change is explicitly approved; never broaden access to make a check pass.

Preferred shell path — token staged as an env var on the gateway process or in a `0600` file, wired as a SecretRef (Telegram example):

``` openclaw config set channels.telegram.botToken --ref-provider default --ref-source env --ref-id TELEGRAM_BOT_TOKEN ```

With the bot connected and DM policy `pairing`, ask the operator to DM it. Read `Your Telegram user id` in the pairing reply, or run `openclaw logs --follow` and read `senderUserId` in that sender's `telegram pairing request` entry. Stop following once captured; keep unrelated logs private. If the current policy prevents this flow, use an already verified ID or report the discovery blocker; do not broaden access.

Use the numeric **Telegram user ID**, not a phone number, username, chat/group ID, or bot ID. In this single-user example, `123456789` is a placeholder: replace it with the verified, approved user ID and retain any other approved entries.

``` openclaw config set channels.telegram.allowFrom '["123456789"]' --strict-json ```

Multi-field changes in one validated write:

``` openclaw config patch --stdin <<'JSON' { channels: { telegram: { enabled: true, groupPolicy: "allowlist" } } } JSON ```

In-session alternative: call the `connect_channel` tool action with the channel id — the operator enters the token in a masked prompt, never in chat. Avoid `openclaw channels add --token <value>`: it puts the secret in argv and process listings.

## Repair

``` openclaw doctor --lint openclaw channels status --probe ```

`doctor --lint` can exit `1` for findings: read the report and continue the remaining checks. Ordinary `doctor` and `doctor --non-interactive` can write config/state; do not use them for diagnosis before approval. Apply `openclaw doctor --fix --non-interactive` only after explicit approval, then re-check status.

## Prove

Send one real, clearly labeled test message and confirm delivery from the command result (use `--dry-run` first to inspect the payload):

``` openclaw message send --channel telegram --target <chatId> --message "OpenClaw channel test — please ignore" --dry-run openclaw message send --channel telegram --target <chatId> --message "OpenClaw channel test — please ignore" ```

If sending fails, report the exact account, permission, destination, or network blocker without exposing credentials.

## Report

State the channel and account changed, the exact config paths written (never values), the test destination, and the observed delivery result. List any remaining operator action.

Further reference: https://docs.openclaw.ai/channels/telegram (and the matching page for other channels)

Intended uses

  • Use Configure Channel when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.