How do I install the Alpha Factor Mining skill?

Run npx skillmds@latest add knuckles-team/alpha-factor-mining 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 Alpha Factor Mining 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 Alpha Factor Mining?

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 Alpha Factor Mining free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Alpha Factor Mining?

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

Alpha Factor Mining by knuckles-team

Name: Alpha Factor Mining
Author: Knuckles-Team

File contents

Alpha Factor Mining Workflow

CONCEPT:EE-011

Compute momentum, fundamental quality, and news sentiment factor signals in parallel to generate a fused target portfolio.

Steps

Step 1: Technical Alpha

Agent: data-fetcher Tools: graph_query, sx_search

Compute rolling standard momentum, RSI, mean-reversion metrics, and volume-weighted indicators from high-frequency market tick logs. Expected: technical-factors

Step 2: Fundamental Alpha [depends_on: none]

Agent: compute-engine Tools: graph_analyze

Extract historical and recent financial filing data, calculating PE, debt-to-equity ratios, and gross margin momentum. Expected: fundamental-factors

Step 3: Sentiment Alpha [depends_on: none]

Agent: risk-assessor Tools: graph_query, graph_analyze

Perform natural language sentiment extraction from recent financial news stories, earnings call transcripts, and social media feeds. Expected: sentiment-factors

Step 4: Factor Fusion [depends_on: technical-alpha, fundamental-alpha, sentiment-alpha]

Agent: report-generator Tools: graph_write, document_tools

Synthesize the technical, fundamental, and sentiment signals, perform correlation testing to remove multi-collinearity, and run a risk-budgeted mean-variance optimization. Expected: optimized-portfolio-weights

Step 5: KG Persistence [depends_on: Factor Fusion]

Agent: report-generator Tools: graph_write

Persist workflow results as nodes and edges in the Knowledge Graph. Create appropriate typed nodes with metadata and link to existing domain entities.

Output

Alpha Factor Mining results persisted in KG
Structured report (MD/PDF)
Audit trail with timestamps and agent attributions

Execution

Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.

Run first (in parallel): Step 1 — Technical Alpha; Step 2 — Fundamental Alpha; Step 3 — Sentiment Alpha
After level 0: Step 4 — Factor Fusion
After level 1: Step 5 — KG Persistence

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: alpha-factor-miningdescription: Compute momentum, fundamental quality, and news sentiment factor signals in parallel to generate a fused target portfolio.---# Alpha Factor Mining Workflow**CONCEPT:EE-011**Compute momentum, fundamental quality, and news sentiment factor signals in parallel to generate a fused target portfolio.## Steps### Step 1: Technical Alpha**Agent**: `data-fetcher`**Tools**: `graph_query, sx_search`Compute rolling standard momentum, RSI, mean-reversion metrics, and volume-weighted indicators from high-frequency market tick logs.Expected: `technical-factors`### Step 2: Fundamental Alpha [depends_on: none]**Agent**: `compute-engine`**Tools**: `graph_analyze`Extract historical and recent financial filing data, calculating PE, debt-to-equity ratios, and gross margin momentum.Expected: `fundamental-factors`### Step 3: Sentiment Alpha [depends_on: none]**Agent**: `risk-assessor`**Tools**: `graph_query, graph_analyze`Perform natural language sentiment extraction from recent financial news stories, earnings call transcripts, and social media feeds.Expected: `sentiment-factors`### Step 4: Factor Fusion [depends_on: technical-alpha, fundamental-alpha, sentiment-alpha]**Agent**: `report-generator`**Tools**: `graph_write, document_tools`Synthesize the technical, fundamental, and sentiment signals, perform correlation testing to remove multi-collinearity, and run a risk-budgeted mean-variance optimization.Expected: `optimized-portfolio-weights`### Step 5: KG Persistence [depends_on: Factor Fusion]**Agent**: `report-generator`**Tools**: `graph_write`Persist workflow results as nodes and edges in the Knowledge Graph.Create appropriate typed nodes with metadata and link to existing domain entities.## Output- Alpha Factor Mining results persisted in KG- Structured report (MD/PDF)- Audit trail with timestamps and agent attributions## ExecutionRun this workflow as a dependency-ordered DAG. Steps with no unmet `depends_on` run in parallel; dependents run after their prerequisites complete.- **Run first (in parallel):** Step 1 — Technical Alpha; Step 2 — Fundamental Alpha; Step 3 — Sentiment Alpha- **After level 0:** Step 4 — Factor Fusion- **After level 1:** Step 5 — KG Persistence**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

Alpha Factor Mining