# Regime Detection Pipeline

> Collects pricing indicators, extracts structural features, fits Hidden Markov Model classifiers, and adapts strategy params to structural shifts.

- Skill: `knuckles-team/regime-detection-pipeline` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add knuckles-team/regime-detection-pipeline`
- Raw SKILL.md: https://api.skillmd.com/api/skills/knuckles-team/regime-detection-pipeline/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: Knuckles-Team (https://skillmd.com/u/knuckles-team)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/knuckles-team/regime-detection-pipeline

---


# Regime Detection Pipeline Workflow

**CONCEPT:EE-011**

Collects pricing indicators, extracts structural features, fits Hidden Markov Model classifiers, and adapts strategy params to structural shifts.

## Steps

### Step 1: Data Collector
**Agent**: `data-fetcher`
**Tools**: `graph_query, sx_search`

Collects tick volumes, bid-ask spreads, and rolling volatilities.
Expected: `market-regime-raw-data`

### Step 2: Feature Extractor [depends_on: data-collector]
**Agent**: `compute-engine`
**Tools**: `graph_analyze`

Normalizes features and computes rolling volatility and trend indicators.
Expected: `structured-regime-features`

### Step 3: Hmm Regime Fitter [depends_on: feature-extractor]
**Agent**: `risk-assessor`
**Tools**: `graph_query, graph_analyze`

Fits a Hidden Markov Model (HMM) to classify market state.
Expected: `hmm-state-classifications`

### Step 4: Regime Adapter [depends_on: hmm-regime-fitter]
**Agent**: `report-generator`
**Tools**: `graph_write, document_tools`

Triggers strategy parameters modification based on the detected state.
Expected: `adapted-parameters-configs`

### Step 5: KG Persistence [depends_on: regime-adapter]
**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
- Regime Detection Pipeline 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 — Data Collector
- **After level 0:** Step 2 — Feature Extractor
- **After level 1:** Step 3 — Hmm Regime Fitter
- **After level 2:** Step 4 — Regime Adapter
- **After level 3:** 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.