How do I install the Alternative Data Pipeline skill?

Run npx skillmds@latest add knuckles-team/alternative-data-pipeline 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 Alternative Data Pipeline 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 Alternative Data Pipeline?

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 Alternative Data Pipeline free to use?

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

Who published Alternative Data Pipeline?

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

Alternative Data Pipeline by knuckles-team

Name: Alternative Data Pipeline
Author: Knuckles-Team

Alternative Data Pipeline

Discover, fetch, and normalize non-traditional (web/news-sourced) market-data signals by composing the catalog's research and finance atomic skills. Use when a quant researcher needs alternative data ingested and quality-checked before using it in a factor or backtest pipeline; this workflow does not place trades or score signal predictiveness.

Knuckles-Team 2d39f5f 2 files · 2.4 KB Updated Sep 17, 2026

File contents

Alternative Data Pipeline Workflow

Compose the named atomic skills without adding data-vendor logic here.

Inputs

Provide the target instruments/universe, alt-data source categories (news, filings, web-published datasets), lookback window, and any excluded sources.

Steps

Step 0: web-search [skill: web-search]

Invoke $web-search with the workflow inputs to locate candidate alternative-data sources.

Expected: alt_data_source_packet

Step 1: web-crawler [skill: web-crawler] [depends_on: Step 0]

Invoke $web-crawler with alt_data_source_packet to fetch the full content of the discovered sources.

Expected: raw_alt_data_documents

Step 2: quant-data-ingest [skill: quant-data-ingest] [depends_on: Step 1]

Invoke $quant-data-ingest with raw_alt_data_documents and the workflow inputs to normalize records into the Timeseries Memory backend.

Expected: normalized_alt_dataset

Step 3: data-quality-auditor [skill: data-quality-auditor] [depends_on: Step 2]

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

Expected: quality_report

Output

Return normalized_alt_dataset and quality_report. Do not place or recommend trades from this data alone.

Execution

Run first: Step 0 — $web-search.
After level 0: Step 1 — $web-crawler.
After level 1: Step 2 — $quant-data-ingest.
After level 2: Step 3 — $data-quality-auditor.

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: alternative-data-pipelinedescription: Discover, fetch, and normalize non-traditional (web/news-sourced) market-data signals by composing the catalog's research and finance atomic skills. Use when a quant researcher needs alternative data ingested and quality-checked before using it in a factor or backtest pipeline; this workflow does not place trades or score signal predictiveness.license: MIT---# Alternative Data Pipeline WorkflowCompose the named atomic skills without adding data-vendor logic here.## InputsProvide the target instruments/universe, alt-data source categories (news, filings,web-published datasets), lookback window, and any excluded sources.## Steps### Step 0: web-search [skill: web-search]Invoke `$web-search` with the workflow inputs to locate candidatealternative-data sources.Expected: `alt_data_source_packet`### Step 1: web-crawler [skill: web-crawler] [depends_on: Step 0]Invoke `$web-crawler` with `alt_data_source_packet` to fetch the fullcontent of the discovered sources.Expected: `raw_alt_data_documents`### Step 2: quant-data-ingest [skill: quant-data-ingest] [depends_on: Step 1]Invoke `$quant-data-ingest` with `raw_alt_data_documents` and theworkflow inputs to normalize records into the Timeseries Memory backend.Expected: `normalized_alt_dataset`### Step 3: data-quality-auditor [skill: data-quality-auditor] [depends_on: Step 2]Invoke `$data-quality-auditor` with `normalized_alt_dataset` and thedeclared rule set.Expected: `quality_report`## OutputReturn `normalized_alt_dataset` and `quality_report`. Do not place or recommendtrades from this data alone.## Execution- **Run first:** Step 0 — `$web-search`.- **After level 0:** Step 1 — `$web-crawler`.- **After level 1:** Step 2 — `$quant-data-ingest`.- **After level 2:** Step 3 — `$data-quality-auditor`.**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