Skip to content
Review tool permissions
crm-automation
OpenClawClaudeCodexHermes Agent

Telegram Lead Qualification

Review inbound Telegram conversations and organize promising leads with CRM tags, companies, and next steps.

Example request

Illustrative scenario, not an executed run.

Review these five inbound chats. Explain which look like qualified leads and suggest tags and next steps before applying them.

Expected result

A lead-by-lead review with evidence from the conversation and suggested CRM updates; uncertain details remain questions.

Before you start

  1. Connect Telegram and select the personal or team context you intend to use.
  2. Connect your AI client with browser OAuth, or follow the local setup below.
  3. 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-lead-qualification

Use this skill to turn Telegram conversation context into a qualified CRM lead record.

Rules

  • Read enough recent context before making a qualification.
  • Prefer AI suggestions for tags, company, and tasks before persisting.
  • Use explicit lead-stage tags such as Lead, Qualified, Partner, Customer, or Investor.
  • Keep the qualification reason concise and tied to conversation evidence.
  • Do not send Telegram messages.

Flow

  1. Use dialogs_list to find candidate chats when no peer is specified.
  2. Use chat_read to inspect recent context.
  3. Use tags_suggest, company_suggest, and tasks_suggest.
  4. Use summary_refresh when the chat lacks current context.
  5. Apply tags, company links, and tasks only when requested or when policy allows automatic CRM writes.
  6. Return the qualification, evidence, next action, and any persisted changes.

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.
Chiho.ai Telegram CRM workspace
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.
Local tgchats command-line workflow

Cloud MCP

Required scopes:

  • telegram.read
  • crm.write

Useful tools:

  • dialogs_list
  • chat_read
  • tags_suggest
  • company_suggest
  • tasks_suggest
  • tags_set
  • company_link
  • tasks_add
  • summary_refresh

Cloud Telegram reads and CRM metadata are separate. If dialogs_list or chat_read can see a peer but CRM tools report that chat metadata is unavailable, 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 lead tags, company links, tasks, or summaries.

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 -- inbox --limit 50 --json
  • npm run dev -- chat <peer> --limit 50 --json
  • npm run dev -- tags suggest <peer> --json
  • npm run dev -- company suggest <peer> --json
  • npm run dev -- tasks suggest <peer> --json
  • add --apply only when the user approves CRM writes.

Templates

Formatted preview from the packaged JSON asset.

Lead stage tags

tags

Lead
Qualified
Partner
Customer
Investor

notes

Use the narrowest stage supported by the conversation.

Examples

Formatted preview from the packaged JSON asset.

Examples 1

prompt

Qualify my recent inbound Telegram leads and show the top follow-ups.

tools

dialogs_list
chat_read
tags_suggest
company_suggest
tasks_suggest

Examples 2

prompt

Qualify @alice as a lead and apply the CRM updates if the evidence is strong.

tools

chat_read
tags_suggest
company_suggest
tasks_suggest
tags_set
company_link
tasks_add

Keep building your workflow

Read the related Telegram workflow guide

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