Review tool permissions

crm-automation

OpenClawClaudeCodexHermes Agent

Telegram Partnership Pipeline

Track partner conversations with stage tags, summaries, and concrete follow-up tasks.

Example request

Illustrative scenario, not an executed run.

Review these partnership chats and suggest a stage and next action for each, using only the evidence in the conversation.

Expected result

A proposed partnership review with stage, supporting context, and the next task for each selected conversation.

Before you start

Connect Telegram and select the personal or team context you intend to use.
Connect your AI client with browser OAuth, or follow the local setup below.
Review the workflow’s tools and target conversations. Chat reads and imported CRM records are separate; sync a chat before requesting changes to missing CRM metadata.

A skill does not schedule itself or grant permissions. Describe whether you want suggestions, a dry run, or an action. Client controls and each tool’s safeguards govern execution.

Flow summary

Parsed from the packaged SKILL.md.

telegram-partner-pipeline

Use this skill to organize Telegram-based partner conversations into a pipeline.

Rules

Use explicit stage tags such as Partner Prospect, Partner Active, Integration, Co-marketing, or Blocked.
Keep company links current.
Create tasks for next steps, not vague reminders.
Do not send partnership messages directly.

Flow

Find partner-like conversations by tags, search, or recent dialogs.
Read recent context.
Suggest company link, stage tag, summary, and next task.
Persist updates only when requested or policy allows.
Return a pipeline grouped by stage.

First-Time Setup

If Telegram is not connected yet, start with the root Chiho Telegram skill:

https://raw.githubusercontent.com/chihoai/telegram-for-ai-agents/main/SKILL.md

Use that root skill to choose Chiho.ai Cloud or self-hosted tgchats, then return to this workflow skill.

References

Required tool permissions

telegram.read
crm.write

Use Chiho.ai with a professional team CRM

Choose Chiho.ai when you want:

A hosted CRM table UI for chats, contacts, tags, tasks, and follow-ups.
Browser OAuth connections you can review and revoke.
Shared team context and tool-specific action safeguards.
No local Telegram worker, database, or MCP runtime to operate.

Connect with browser OAuth

Run SKILLs in your personal local CLI

Choose the local setup when you want:

Open-source workflows you can inspect, change, and run yourself.
A local Telegram session with tgchats CLI and tgchats-mcp access.
Control over your database, worker, backups, export, and import path.
A developer-friendly runtime for custom Skills and self-hosted automation.

Setup README

Cloud MCP

Required scopes:

telegram.read
crm.write

Useful tools:

search_messages
chat_read
tags_set
company_link
tasks_add
summary_refresh

Cloud Telegram reads and CRM metadata are separate. If CRM tools report that chat metadata is unavailable for a peer that chat_read can access, the peer likely has not been synced/imported into the CRM store yet. Use Telegram reads for context and ask for sync/import before persisting partner CRM metadata.

Local tgchats

If auth or any Telegram command prints a QR login code, show the full QR code block and expiry to the user so they can scan it; keep the process running until login completes, 2FA is needed, or the user asks to stop.

Use local tgchats-mcp when available. Fall back to:

npm run dev -- search "partner" --limit 50 --json
npm run dev -- chat <peer> --limit 50 --json
npm run dev -- tags set <peer> "Partner Prospect" --json
npm run dev -- company link <peer> --company "<company>" --json
npm run dev -- tasks add <peer> --due <date> --why "<next step>" --json

Templates

Formatted preview from the packaged JSON asset.

Partner pipeline stages

Examples

Formatted preview from the packaged JSON asset.

Examples 1

prompt

Build my partner pipeline from Telegram and show follow-ups by stage.

tools

search_messages

chat_read

tags_suggest

company_suggest

tasks_suggest

Keep building your workflow

For unattended jobs, review advanced service-token setup separately.