MCP App StoreMCP App Store
from superconfig20
Run and manage long-running commands inside tmux sessions; capture scrollback and reuse idle sessions for builds, tests, and parallel work.
Provides commands and patterns to run long-running processes inside tmux sessions, capture their output (including full scrollback), and manage multiple parallel jobs using sessions/windows/panes. Concrete use cases include starting build servers, running tests that take minutes, or running background processes you want to inspect later.
Use this skill when you need to start a process that outlives a single shell call, want to examine interactive output after a run finishes, or need to run multiple long-running commands in parallel without losing their logs. Avoid for short one-shot commands or cases where structured stdout/stderr separation is required.
claude-), patterns to find or create idle sessions, sending commands with a unique completion marker and polling capture-pane until it appears, capturing visible or full scrollback, running parallel jobs via multiple sessions or windows, and cleanup commands. Example bash snippets are provided for each pattern.This skill is best used by agents that can run shell commands and manage long-running processes (Bash/terminal-capable agents such as Claude Code, Copilot-style CLIs, or any agent with shell exec capabilities).
A comprehensive tmux reference skill covering session/window/pane management, scripting layouts, configuration, and automation patterns. Pure knowledge skill with no executable scripts — all code is inline bash examples. Well-structured with clear sections, good security notes about send-keys targeting, and practical idiomatic functions. Lacks the scripts/ or references/ directory structure expected by the skill spec.
Solid tmux reference. The automation patterns (ensure_session, run_bg, wait_for_output, kill_bg_windows) are genuinely useful. Security notes are present and appropriate. Would benefit from actual runnable scripts in scripts/ directory and a references/ dir for advanced topics. The grep injection in wait_for_output is a minor concern but low-risk in typical agent usage.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.