How do I install the Feature Store Builder skill?

Run npx skillmds@latest add knuckles-team/feature-store-builder in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Feature Store Builder safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Feature Store Builder?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Feature Store Builder free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Feature Store Builder?

Knuckles-Team (@knuckles-team) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Feature Store Builder by knuckles-team

Name: Feature Store Builder
Author: Knuckles-Team

Feature Store Builder

Ingest market data, validate it, document it as a data dictionary, and profile it, producing a curated, documented feature dataset. Use when a researcher needs a reusable, documented feature store built from raw market data; this workflow does not train or select a model.

Knuckles-Team 354fda6 2 files · 2.3 KB Updated Sep 17, 2026

File contents

Feature Store Builder Workflow

Compose the named atomic skills without adding model-training logic here.

Inputs

Provide the asset universe, date range, and desired feature fields.

Steps

Step 0: quant-data-ingest [skill: quant-data-ingest]

Invoke $quant-data-ingest with the workflow inputs to ingest raw market data.

Expected: normalized_market_dataset

Step 1: data-quality-auditor [skill: data-quality-auditor] [depends_on: Step 0]

Invoke $data-quality-auditor with normalized_market_dataset and the declared rule set.

Expected: quality_report

Step 2: data-dictionary-builder [skill: data-dictionary-builder] [depends_on: Step 1]

Invoke $data-dictionary-builder with normalized_market_dataset and quality_report to document each field.

Expected: feature_data_dictionary

Step 3: dataset-profiler [skill: dataset-profiler] [depends_on: Step 2]

Invoke $dataset-profiler with normalized_market_dataset to produce a structural and statistical profile.

Expected: feature_profile

Output

Return normalized_market_dataset, feature_data_dictionary, and feature_profile as the assembled feature store. Does not train or select a model.

Execution

Run first: Step 0 — $quant-data-ingest.
After level 0: Step 1 — $data-quality-auditor.
After level 1: Step 2 — $data-dictionary-builder.
After level 2: Step 3 — $dataset-profiler.

Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.

---name: feature-store-builderdescription: Ingest market data, validate it, document it as a data dictionary, and profile it, producing a curated, documented feature dataset. Use when a researcher needs a reusable, documented feature store built from raw market data; this workflow does not train or select a model.license: MIT---# Feature Store Builder WorkflowCompose the named atomic skills without adding model-training logic here.## InputsProvide the asset universe, date range, and desired feature fields.## Steps### Step 0: quant-data-ingest [skill: quant-data-ingest]Invoke `$quant-data-ingest` with the workflow inputs to ingest rawmarket data.Expected: `normalized_market_dataset`### Step 1: data-quality-auditor [skill: data-quality-auditor] [depends_on: Step 0]Invoke `$data-quality-auditor` with `normalized_market_dataset` andthe declared rule set.Expected: `quality_report`### Step 2: data-dictionary-builder [skill: data-dictionary-builder] [depends_on: Step 1]Invoke `$data-dictionary-builder` with `normalized_market_dataset` and`quality_report` to document each field.Expected: `feature_data_dictionary`### Step 3: dataset-profiler [skill: dataset-profiler] [depends_on: Step 2]Invoke `$dataset-profiler` with `normalized_market_dataset` to producea structural and statistical profile.Expected: `feature_profile`## OutputReturn `normalized_market_dataset`, `feature_data_dictionary`, and`feature_profile` as the assembled feature store. Does not train or select a model.## Execution- **Run first:** Step 0 — `$quant-data-ingest`.- **After level 0:** Step 1 — `$data-quality-auditor`.- **After level 1:** Step 2 — `$data-dictionary-builder`.- **After level 2:** Step 3 — `$dataset-profiler`.**Execution:** If graph-os is reachable, offload the whole DAG via `graph_orchestrate action=execute_workflow` (or the `kg-delegate` skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet `depends_on` in parallel, then their dependents.

Frequently asked questions