Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides structured methods for equity traders and investment analysts to evaluate financial assets. It enables the comparison of research records to track shifts in facts and judgments, while offering focused frameworks for identifying supply-chain chokepoints.
The skills help professionals break down research reports, score option candidate risks, and extract key assumptions from investment documentation to make evidence-based decisions.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Install AlphaGBM Stock Research
Installs: Installs only the alphagbm-stock-research Skill from the AlphaGBM/skills repository into the workspace/client selected in the installer.
Before you start
Python 3.9+ for the bundled runner.
For account-backed research: an AlphaGBM account with ALPHAGBM_API_KEY configured securely in the tool environment; obtain approval before consuming the shared allowance.
In a terminal, run the documented single-skill installation command. When prompted by the installer, choose the intended workspace/client.
Research one stock with supporting and opposing evidence
Uses alphagbm-stock-research
A supported ticker and market suffix if applicable; NVDA is the documented example.
Research style; quality is the documented command example.
An AlphaGBM account with ALPHAGBM_API_KEY configured in the environment.
Explicit approval before consuming the shared research allowance.
Use the alphagbm-stock-research skill to research NVDA using the quality style. Show the research conclusion, supporting evidence, counterevidence, missing data, and what to verify next. Ask for my approval before using the shared research allowance, and do not treat the result as a promise of gains.
Contribution amount; $500 is the documented example.
Frequency and number of periods; monthly for 12 periods is the documented example.
An optional comma-separated supplied price path if a historical cost-basis calculation is wanted.
ALPHAGBM_API_KEY configured in the environment and explicit allowance approval.
Use the alphagbm-dca-plan skill to build a 12-period monthly $500 QQQ contribution plan. Explain the contribution schedule, total capital, cost-basis limitations, and other conditions without predicting returns or placing recurring orders. Ask for my approval before using the shared allowance.
A title, ticker, or topic keyword; semiconductor is the documented example.
Preferred language, such as English or Chinese.
Whether to search original research, institutional views, or both.
Use the alphagbm-research-reader skill to find recent semiconductor research. Separate institutional views from disclosed facts, and report the core summaries, institutions, sources, related assets, dates, language, workflow, and revision. Start with the public catalogue and do not trigger paid analysis.
Claude
Cursor