The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts using uv run to interact with the Telegram API. The scripts are located in the user's plugin directory at $HOME/.claude/plugins/marketplaces/cc-skills/plugins/tlg/.
[COMMAND_EXECUTION]: Accesses sensitive Telegram session files stored at ~/.local/share/telethon/ to authenticate the user session. This access is necessary for the skill's primary purpose of managing Telegram conversations.
[PROMPT_INJECTION]: The skill facilitates reading external Telegram messages which constitutes an indirect prompt injection surface.
Ingestion points: Telegram messages and dialog names are read into the agent context via the read and dialogs commands in SKILL.md.
Boundary markers: No explicit markers or instructions are provided to the agent to ignore instructions embedded in the retrieved Telegram content.
Capability inventory: The skill has the ability to execute shell commands via uv run as seen in SKILL.md.
Sanitization: No sanitization or validation of the retrieved Telegram content is performed before processing.

list-dialogs