Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Builds Model Context Protocol (MCP) servers for Claude with tools, resources, and prompts. Use when users request "create MCP server", "build Claude tool", "MCP integration", or "custom Claude tools".
A skill for obtaining live financial data through the XTick API, including Chinese mainland stocks, exchange-traded funds, indexes, and Hong Kong stocks. It also covers company figures, technical indicators, and market-trend data.
Build and revise iteration-safe HTML slide decks with polished visuals, motion, testing, and web/PDF/static delivery. Use only for HTML slide projects.
Use when handing off an in-progress session to another agent or a future session — ending a session with unfinished work, "pick up where I left off", passing a task to a fresh agent/another window/codex, running low on context, or persisting intent + learnings before context is lost. Covers both dropping a baton…
A skill that connects to an agent-memory service over HTTP, allowing an agent to search, save, buffer, flush, update, and inspect stored conversation or task memories.
Improve decision quality by clarifying the real problem, exposing hidden assumptions, reasoning from fundamental facts, reducing unnecessary complexity, and ending with a cleaner recommendation or next step. Use when the user is confused, comparing options, overcomplicating a problem, questioning assumptions, trying…
Generate an ink-wash editorial poster prompt and the matching bitmap image from a user's theme, sentence, object, mood, article idea, photo, content brief, poem, memory, event, place, or other creative material. Use when the user wants a quiet, spacious, tactile ink-wash poster, cover, cultural visual, or…
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative…
UI/UX patterns and guidelines derived from official Frappe apps (CRM, Helpdesk, HRMS). Use when designing interfaces for custom Frappe applications to ensure consistency with the ecosystem.
Use when performing a behavior-preserving architectural cleanup or refactor on a codebase and you need strict guardrails against changing functionality, building a framework, or rewriting tests to fit the new design.
This skill should be used when the user asks research questions, needs information lookup, wants comparisons, asks "what is", "how does", "explain", "compare", "best practices", "latest developments", or any query requiring web search, documentation lookup, or synthesis of multiple sources. Provides optimal routing…
Write the intention of this project in .hod/PROJECT.md. Use when the user asks to set up this project for a coding agent, when .hod/PROJECT.md holds the text that hod init wrote, or when a task needs the command that installs the dependencies, the command that runs the tests or the command that starts the program and…
Generate a production-ready system prompt for a ForgeChat WhatsApp AI agent (order bot, booking bot, lead-capture bot, etc.) AND, when a ForgeChat MCP connector is available, build/configure that agent directly in ForgeChat over MCP. Use this skill WHENEVER the user wants to "write a prompt for an agent", "build a…
Transform people in uploaded street, travel, lifestyle, casual, or commercial-space photos into clean BLACK INK or colorful editorial-chibi illustrations while preserving the original photographic environment, pose, clothing, accessories, and scene relationships. Use when the user asks to illustrate, cartoonize, or…
Use this skill as a router and knowledge graph for McKinsey/BCG-style consulting methods. Use when the user asks for structured problem solving, MECE issue trees, hypothesis-driven analysis, strategy, operations, execution, stakeholder management, consulting communication, proposals, high-pressure corporate…
You're a member of a CircleChat workspace. Humans and other agents share the same space — same channels, same DMs, same reactions. Everything you do here happens through the channel described below — not through tool or function calls.
Activate, upgrade, test, and benchmark the 7-tool token-saving stack (context-mode, claude-mem, RTK, pxpipe, graphify, caveman, ponytail). Reports per-tool + per-provider (Codex, Gemini, Kimi, opencode, GitHub Copilot CLI) token savings, wires the stack into Copilot, and detects conflicts that would erase the gains.
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: