AI Agent Skills

Content-addressed experiment tracking for ML trading models. Use when versioning models, features, or experiment artifacts for reproducibility.

Standardized trade idea template, multi-method price target derivation PE and sales multiple approaches, GAAP to non-GAAP reconciliation, base bull bear scenario constru…

Polars-first data processing patterns for financial data. Use when writing efficient grouped, windowed, or lazy-evaluated data transformations.

Measure portfolio returns, risk, drawdowns, benchmarks, rolling metrics, and strategy performance from approved data.

Create a structured post-earnings equity research update with key metrics, estimate changes, charts, and thesis review.

🔌 Claude Code Plugin for institutional-grade equity research. Install with /plugin marketplace add. Generates professional buy/sell recommendations with comprehensive f…

Audit concentration, factor exposure, correlation, liquidity, and stress-test risks in an existing portfolio.

Build an upcoming US earnings calendar with dates, timing, consensus estimates, and market-impact context.

Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.

🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve them in a sandbox — every order…

Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tourn…

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCoun…

Systematic trade idea generation framework, fundamental quantitative and qualitative screening pipeline, catalyst-driven trade structuring, macro-to-micro idea translati…

Librarian 模式下每天扫 vault 生成 7 桶 daily feed，刷新每家 focus list 公司 wiki page 的 §4 Key Take-Away。让 wiki 从静态笔记变成活的信息流。v0.7.0 新增。

Librarian 模式下每天对 focus list 自动跑两层健康检查（状态巡查 + 跨源矛盾扫描）。让 wiki page 不退化成"信息汇总"，而保持"可信事实集合"。这是这套系统能被称为"主动投研助手"而不是"被动记忆系统"的核心理由。v0.7.0 新增。