MCP App StoreMCP App StoreProvides practical guidance for using the simulang CLI and the @simular-ai/simulang-js runtime to author, run, and debug desktop automation scripts in TypeScript or JavaScript. Covers first-time setup (permissions on macOS), running modes (interactive REPL, headless, version pinning), API inspection via 'simulang which', and common pitfalls.
Invoke this skill when the user mentions simulang, is editing .ts/.mts/.js/.mjs/.simulang scripts that import simulang-js, or needs help with running, troubleshooting, or versioning simulang scripts. Useful for permission troubleshooting on macOS, choosing the correct simulang-js version, and recommending run flags.
Agents capable of invoking CLI commands, running Node scripts, and reading local project files (Copilot/GitHub-code-style agents, Claude Code, Codex, Gemini CLI) will work well with this skill.
simulang is a CLI skill for desktop automation using TypeScript/JavaScript via the simulang-js library. The SKILL.md is well-written with clear trigger conditions, version pinning docs, common pitfalls, and API lookup guidance. Two bundled .mjs scripts (postinstall and setup-permissions) were skipped by the runner due to .mjs extension but are clean on manual review — proper error handling, no destructive commands, no exfiltration risk.
@simular-ai/simulang-jspostinstall.mjs auto-runs on npm install but has good safety rails (bails if dist/ missing, catches all errors, never non-zero exit). setup-permissions.mjs shells out to /usr/sbin/screencapture but only on macOS and only to trigger TCC permission prompts — legitimate use. No security concerns.
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.