From tlg
Use when user wants to delete, remove, or unsend Telegram messages from a chat, either for everyone or just for themselves.
How this skill is triggered — by the user, by Claude, or both
Slash command
/tlg:delete-messagesThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Delete one or multiple messages from a chat. By default deletes for everyone.
Delete one or multiple messages from a chat. By default deletes for everyone.
Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
~/.local/share/gramjs/<profile>.session
/tlg:setup first/usr/bin/env bash << 'EOF'
SCRIPT="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/cc-skills/plugins/tlg}/scripts/tg-cli.ts"
# Delete for everyone (default)
bun "$SCRIPT" delete <chat> <message_id>
# Delete multiple messages
bun "$SCRIPT" delete <chat> 12345,12346,12347
# Delete only for yourself
bun "$SCRIPT" delete <chat> <message_id> --self-only
# Find message IDs first
bun "$SCRIPT" read <chat> -n 10
EOF
| Parameter | Type | Description |
|---|---|---|
| chat | string/int | Chat containing messages |
| message_ids | string | Message ID(s), comma-separated |
--self-only | flag | Delete only for yourself (default: for everyone) |
read <chat> -n N to find message IDsdelete <chat> <ids>After this skill completes, check before closing:
Only update if the issue is real and reproducible — not speculative.
npx claudepluginhub terrylica/cc-skills --plugin tlgGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.