Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Fetches recent Telegram messages at session start to maintain conversation context across sessions, with toggle and manual fetch commands.
Fetches recent Telegram messages at session start to maintain conversation context across sessions, with toggle and manual fetch commands.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Provides conversational continuity by fetching recent Telegram messages at session start. When enabled, the agent automatically retrieves message history to maintain context across disconnected sessions.
Created by @fourthdensity
/telegram-context on — Enable automatic history fetching /telegram-context off — Disable automatic fetching /telegram-context status — Show current settings /telegram-context fetch [n] — Manually fetch last n messages (default: 20)
The skill auto-detects Telegram channels — no configuration needed State is stored in memory/telegram-context.json Only activates when the current channel is Telegram
When a session starts in Telegram: Check memory/telegram-context.json for enabled state If enabled, fetch recent messages via message tool Provide history as context for the conversation Update lastFetch timestamp
memory/telegram-context.json: { "enabled": true, "fetchCount": 20, "lastFetch": "2025-01-15T10:30:00Z" }
Enable/disable: // Read current state read: memory/telegram-context.json // Update state write: memory/telegram-context.json { "enabled": true/false, "fetchCount": 20, "lastFetch": "2025-01-15T10:30:00Z" } Manual fetch: message: { action: "list", limit: 20 // or user-specified count } // Provide results as context summary
At the start of each Telegram session: Check if memory/telegram-context.json exists If enabled, call message tool with action: "list" Summarize recent messages for context window Acknowledge continuity to user (optional)
The skill uses OpenClaw's built-in message tool with: action: "list" — limited to the current Telegram chat only No access to other chats, channels, or external Telegram accounts Requires the OpenClaw gateway to have Telegram channel permissions already configured
Data Handling: Only fetches from the current chat (never cross-chats or other Telegram conversations) Message content is included in the agent's context window and sent to the configured LLM provider No message content is stored in telegram-context.json — only settings and timestamps Message content may appear in OpenClaw session logs (depends on your logging configuration) Recommendations for Sensitive Conversations: Use manual fetch (/telegram-context fetch) instead of auto-fetch Set low fetchCount (5-10) to minimize context exposure Disable the skill entirely when discussing sensitive topics: /telegram-context off Be aware that fetched messages become part of the conversation history sent to AI models User Control: Full toggle on/off anytime — no persistence beyond your control No external credentials or API keys required No binaries installed — pure instruction-based skill
Telegram-only (other channels not supported) Requires appropriate message permissions via OpenClaw gateway Large history may need summarization to fit context window Fetched messages are sent to your configured LLM provider — review your threat model for sensitive conversations
Set fetchCount to 10-30 for most use cases (balance context vs. tokens) Use /telegram-context fetch 50 when you need deep context for a specific task Works best alongside MEMORY.md for long-term persistence
Messaging, meetings, inboxes, CRM, and teammate communication surfaces.
Largest current source with strong distribution and engagement signals.