Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Improved privacy documentation: clarified message handling, LLM provider transmission, and added security recommendations for sensitive conversations
What This Skill Does
Fetches recent Telegram message history at the start of each session so the agent has context from prior conversations. Toggle on or off anytime via slash commands, with manual fetch available for on-demand retrieval. State is stored locally in a JSON file, no external credentials required.
Unlike memory files alone, this pulls actual message content at session start rather than relying on manually written summaries.
When to use it
- Resuming a multi-day project discussion without re-explaining context
- Fetching the last 10 messages before a task handoff
- Disabling auto-fetch during a sensitive conversation
- Manually pulling 50 messages to catch up after a long absence
- Checking how many messages were last fetched with a status command
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: catch me up on what we discussed yesterday
- 1Check memory/telegram-context.json for enabled state
- 2Call message tool with action: list and fetchCount from stored settings
- 3Retrieve last 20 Telegram messages from the current chat
- 4Summarize the retrieved messages for the context window
- 5Present a continuity summary to the user
A summary of recent Telegram conversation history, scoped to the current chat