Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Make your AI agent learn and improve automatically. Reviews sessions, extracts learnings, updates memory files, and compounds knowledge over time. Set up nightly review loops that make your agent smarter every day.
Make your AI agent learn and improve automatically. Reviews sessions, extracts learnings, updates memory files, and compounds knowledge over time. Set up nightly review loops that make your agent smarter every day.
Use this skill when coordinating work across Ghostex panes or agent sessions through the Ghostex CLI: creating terminal or agent panes, listing sessions, checking agent status, sending messages to other agent sessions, reading the last lines from another session, focusing/sleeping/waking/killing sessions, or using Ghostex commands instead of raw zmx/tmux control.
Use this skill when adding, configuring, or troubleshooting agent access to Ghostex embedded CEF browser panes through the Ghostex Browser Use MCP workflow. It covers CLI installation, MCP config, page selection, console logs, DOM snapshots, clicks, fills, key presses, screenshots, and the CEF remote debugging port used by `ghostex browser mcp`.
Use this skill to execute a multi-phase coding task with a Fable-planned, Codex-implemented, Fable-verified pipeline inside Ghostex: the invoking session plans inline and writes a phase plan file, launches one Codex (gpt-5.6) worker pane per phase through the Ghostex CLI, then launches a Fable verifier pane that checks every acceptance criterion, and spawns targeted Codex fixer panes for any findings until verification passes or the fix loop cap is reached.
Background memory organ for AI agents. Runs separately from the main agent—encoding, decaying, and reinforcing memories automatically. Just like the real hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023).
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context across sessions, or when managing decisions/preferences/tasks with multiple memory backends working together.