Quant Research¶
Quantitative trading, factor research, backtesting, and live-execution workflows. Distinct from the Finance hub (which covers banking / capital markets / equity research / fund admin) — overlap is mostly on the data-source side.
Skills in this repo¶
Local¶
| Skill | One-line | Notes |
|---|---|---|
quantatitive-factor-researcher |
Python quant-research persona for factor engineering, backtesting, cross-validation, and Sharpe / IR / Tracking Error metrics. | Anchor skill of this hub. |
vectorbt |
OSS/PRO library development, release-aligned XDG docs, migration checks, and optional MCP. | quantitative-finance group |
nautilus-trader |
v1 Cython / v2 Rust-PyO3 generation detection, git-tag docs cache, event-driven backtests, sandbox/live-trading gates. | quantitative-finance group |
Vendored¶
| Skill | Upstream | Series |
|---|---|---|
| none yet |
External skills (manual install)¶
Status enum (single source of truth across the catalog)
Every external-skill or MCP entry below carries a status: value:
| Status | Meaning | Where it links |
|---|---|---|
vendored |
Already in vendor.yaml. |
Link to the skills/vendor/<name>/ (or series) entry. |
deferred |
Open TODO P? item — under consideration. |
Link to the TODO.md anchor. |
skipped |
Looked at, chose not to vendor. | Inline reason required (1 sentence). |
evaluated |
Read but no decision recorded. Effectively "tracked." | Inline 1-line note describing what was learned. |
wishlist |
Surfaced but not yet evaluated. | No link required; default for fresh discoveries. |
Status changes are explicit edits — see the Adding catalog
entries workflow doc (under Workflows in the nav) for the
wishlist → deferred → vendored recipe.
Manual install for non-vendored skills
When a skill is not in vendor.yaml, you can still install it directly
from upstream via the npx skills CLI:
# Whole-repo install (if SKILL.md sits at repo root or skills/)
npx skills@latest add <owner>/<repo>
# Subpath install (when the skill is nested)
npx skills@latest add <owner>/<repo>/<path-to-skill-dir>
# Cherry-pick by name
npx skills@latest add <owner>/<repo> -s <skill-name>
# Force deep discovery (skill nested >1 level inside skills/)
npx skills@latest add <owner>/<repo> --full-depth -s <skill-name>
For Anthropic-style plugin marketplaces (e.g.
anthropics/financial-services,
anthropics/knowledge-work-plugins), use the Claude Code plugin
commands instead:
For MCP servers, see the per-entry "Auth & install" section in the MCP wiki — install commands vary by transport (HTTP / stdio / SSE) and host (Claude Code / Claude Desktop / Cursor / Managed Agents).
| Skill / Plugin | Upstream | Status | Why this status | Install hint |
|---|---|---|---|---|
| VectorBT Backtesting Skills | marketcalls/vectorbt-backtesting-skills | skipped |
Evaluated OSS workflow; OpenAlgo indicator defaults do not match this library-focused skill. | Upstream instructions |
| NautilusTrader docs skill | aysuio/nt-skill | skipped |
No license; assumes hosted latest docs track the installed release, which fails during the v1 → v2 RC period. |
Upstream instructions |
| NautilusTrader skill | clay584/nautilus-trader-skill | skipped |
No license; verified against 1.228.0 and teaches the v1 TradingNode API. |
Upstream instructions |
MCP servers¶
| Name | Upstream | Status | Auth | Records |
|---|---|---|---|---|
| Financial Datasets MCP | docs.financialdatasets.ai/mcp-server |
wishlist |
OAuth 2.1 + API key | Per-MCP page |
Backlog (TODO P? items)¶
See the P? lane in TODO.md:
[?/L]Tardis SDK skill — historical market data workflows, access assumptions, and example-driven guidance.[?/L]Financial data sources skill set — provider comparison (cross-listed in Finance).
See also¶
- Finance — banking, capital markets, equity research workflows.
- AI/ML Research — for the experiment tracking + notebook ecosystem (
mlflow-tracking,marimo-batch-mlflow) that quant projects often layer on. docs/skills/quantatitive-factor-researcher.md,vectorbt.md, andnautilus-trader.md— the local skill pages.