telegram-context
Toggle-enabled skill that fetches Telegram message history at session start for conversational continuity. Maintains context across sessions without relying solely on memory files.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- telegram-context
- homepage
- https://github.com/openclaw/skills
- metadata
- { "openclaw": { "emoji": "💬", "requires": { "env": [], "bins": [] }, "permissions": [ "message:read" ] } }
- description
- Toggle-enabled skill that fetches Telegram message history at session start for conversational continuity. Maintains context across sessions without relying solely on memory files.
03 SKILL.md 正文
Telegram Context
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.
Credits
Created by @fourthdensity
Commands
/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)
Setup
- 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
How It Works
When a session starts in Telegram:
- Check
memory/telegram-context.jsonfor enabled state - If enabled, fetch recent messages via
messagetool - Provide history as context for the conversation
- Update
lastFetchtimestamp
State File
memory/telegram-context.json:
{
"enabled": true,
"fetchCount": 20,
"lastFetch": "2025-01-15T10:30:00Z"
}
Implementation Notes
Command Handlers
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
Session Start Behavior
At the start of each Telegram session:
- Check if
memory/telegram-context.jsonexists - If enabled, call
messagetool withaction: "list" - Summarize recent messages for context window
- Acknowledge continuity to user (optional)
Implementation Scope
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
Privacy & Security
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
Limitations
- 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
Tips
- Set
fetchCountto 10-30 for most use cases (balance context vs. tokens) - Use
/telegram-context fetch 50when you need deep context for a specific task - Works best alongside
MEMORY.mdfor long-term persistence
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.