MCP App StoreMCP App StoreThis skill turns the agent into a virtual portfolio manager that runs a daily trading process for a simulated $100,000 account. On the "trade" trigger the agent updates prices, reviews its portfolio, researches market news and tickers, validates symbols, executes buy/sell orders via provided tools, writes a structured diary entry, updates memory, and saves a snapshot. The skill enforces trading rules (no shorting, allowed asset types, max position sizes) and delegates math/validation to helper scripts so the agent focuses on strategy and decision-making.
Use this skill whenever you want the agent to act as a hands-on portfolio manager in a simulated environment — daily rebalancing, idea generation, or competition-style runs against other AI agents. Trigger by sending the single-word prompt: "trade". It's suitable for simulation rounds, backtest-style runs, or live research-driven decision drills.
This skill is implementation-agnostic but expects agents with shell/JS execution (npx/tsx) or similar tool access. Compatible with agent runtimes that can call repository-provided scripts (Copilot/Codex-like toolchains, Node-capable agent runners).
A virtual portfolio manager skill for an AI trading competition. Provides a structured daily process: update prices, review portfolio, research markets, execute trades via local TypeScript tools, write diary entries, and save snapshots. No bundled scripts — relies entirely on external npx tools from the upstash/botstreet repo. Well-documented process with clear steps and trading rules, but tightly coupled to its specific workspace toolchain.
Clean skill with no security concerns. Part of an AI trading competition (botstreet by Upstash). Niche audience but well-structured for its purpose. Lacks scripts/ or references/ directories — all logic is in the SKILL.md instructions.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
WRDS Query & ETL Enforcement
Standards and enforcement guidance for querying WRDS data and running SAS/ETL on the WRDS grid—includes query validation, SGE submission patterns, and performan
Academic Research Search
Search academic literature across multiple sources, deduplicate results, resolve DOIs, and surface trusted papers with concise takeaways.
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.
TradeOS
Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
