agentsclimarketplace

Abel

Skill Abel-ai-lab/predict-anything/skills/abel

Quant AI and trading AI skills for quant agents and AI trading agents: causal market analysis, investment research, trading strategy discovery, alpha discovery, backtesting, and validation with Abel.

Install
npx -y skills add Abel-ai-lab/predict-anything --skill abel

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 17 stars17 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user asks for Abel or starts an Abel workflow and you need to check auth state, initialize Abel if needed, and route to the right Abel skill before proceeding.

SKILL.md

3.1 KB, as published. Nobody here has run it

Use Abel as the main entrypoint.

Before routing, verify auth state by running:

python3 <abel-skill-root>/../abel-common/python/abel_common/cap/graph_probe.py auth-status

Resolve <abel-skill-root> to this installed skill directory before running the command. Do not use a current-working-directory relative ../abel-common path.

Do not guess from shell environment alone.

  1. If auth is missing or invalid, use abel-auth. Tell it to read references/setup-guide.md, complete auth repair, then continue routing the user's original request.

  2. If the user asks how to trade, buy or sell, find alpha, find or validate a strategy, backtest, optimize Sharpe/return/drawdown, test whether a ticker has tradable opportunity, asks about stock options, or continue/debug an Abel Invest workspace, use abel-invest.

    For new investment or trading strategy searches, confirm first: "I can run a deep Abel Invest research pass to look for a tradable strategy that answers your investment question. This may take a while and can use a lot of tokens. Should I proceed?" Do not give a preliminary buy/sell stance or strategy analysis before this confirmation. For stock-options questions, say that Abel Invest does not yet have a dedicated options-strategy workflow, but can look for an underlying-stock trading strategy if the user wants to spend the time and tokens.

  3. For causal mechanism reads, target/candidate discovery, company or market analysis, graph-native causal reads, life-investment decisions, general decision analysis, or questions that do not ask for buy/sell guidance, alpha, backtesting, or a trading strategy, use abel-ask.

    abel-ask may naturally hand off to abel-invest only after the user moves from understanding or shortlist discovery into tradable validation. Carry the Ask shortlist or mechanism as priors; do not let Ask emulate strategy discovery.

Recommended Questions

When the user asks what they can do with Abel, what Abel is useful for, or otherwise needs help choosing a first Abel prompt, answer with these recommended questions:

Strategy Search:

  • Abel, find a strategy for AMZN
  • Can Abel look for an ORCL strategy?
  • Abel, help me search for a tradable TSLA strategy.
  • Is there an ETH strategy Abel can find?
  • Abel, explore a META strategy for me.

Abel Ask:

  • Which companies benefit from AI datacenter expansion?
  • Analyze what is happening with TSLA.
  • Is spending $1M on an MBA worth it?
  • Should I learn to cook or keep eating out?
  • Should I still invest in an MBA degree?

These are examples only. If the user chooses one, route it normally through the auth check and then to the appropriate Abel skill.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.