This skill should be used when the user asks to "review the prompt", "audit the system prompt", "check prompt quality", "inspect what the LLM sees", "debug prompt issues", or "find prompt engineering problems". Pulls the live rendered prompt via the API, explains how it's composed, and reviews it for issues.
Connect Caspian email for OpenCode: ensure credentials (sandbox or dashboard API key), write caspian.env, connect inbox, enable email in caspian.json. Use when the user wants to link email, set up the agent inbox, or runs /caspian:connect-email.
Use ZulipChat MCP for authorized Zulip messaging, search, drafts, files, and agent session workflows. Apply when the user asks to work in Zulip or connect a coding session to a Zulip topic.
The only Telegram skill your AI agent needs. Read messages, parse channels, download and transcribe voice notes — all via Telethon user API. One session file, zero bots. Use when user says 'read telegram', 'check saved messages', 'fetch from telegram', 'parse channel', 'transcribe voice', 'telegram search', 'check my…
Read, search, and send Telegram messages from any AI agent via the @cyberdrk/tg CLI. Use when the user asks to check inbox, search chats, send a message, look up a contact, list group members, or download media (photos/videos/files) from accessible chats. Works with Claude Code, Cursor, Aider, OpenHands, and any agent…
A bridge between Claude Code and DingTalk, a Chinese workplace chat app. It can send messages to DingTalk groups and listen for mentions that start Claude CLI tasks.
You are a conversion strategist and ICP-fit auditor. You evaluate a website — either by visiting its URL or by reading its source code — to determine whether the copy, structure, messaging, and psychology are correctly aligned with the stated Ideal Customer Profile and their specific awareness stage.
Always active — coordinates with other Claude Code agents via intercom MCP. Automatically checks for messages, announces presence, and communicates to avoid conflicts. Triggers on ANY task start and periodically during work.
Use this skill whenever checking OpenJobs inbox/messages or running the OpenJobs command-center workflow for the active agent. It ensures the exact CLI binary is used, platform health is verified, unread tasks and DM counts are checked, command-center actions are dispatched, webhook health is monitored, oversight…
Skill "docs" from lleontor705/agent-mailbox-mcp, covering agent mailbox mcp — skill guide for ai agents, when to use this skill, quick decision tree, tool patterns and pattern 1: fire and forget.
Read and post Mattermost messages via the mattermost-mcp MCP server — list a channel's posts and threads, search posts, create a post or a threaded reply, and handle file attachments with the domain-typed condensed tools. Use when the agent must read recent conversation in a channel, search for a message, post an…
Score a fresh inbound conversation against a qualification rubric, tag it, and prepare a routing recommendation and reply draft without sending anything.
★not rated 0 2d agoA30 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: