# Component Classifier

> Classify a RAG request into a constrained execution route by calling the frozen Executor Model. Use inside an Agentic workflow before route-specific retrieval or processing.

- Skill: `docailab/component-classifier` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add docailab/component-classifier`
- Raw SKILL.md: https://api.skillmd.com/api/skills/docailab/component-classifier/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: DocAILab (https://skillmd.com/u/docailab)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/docailab/component-classifier

---


# Classifier Component

Provide the `classifier` capability for an Agentic RAG slot.

## Interface

Input `ClassificationRequest`:

- `query`: original question
- optional `documents`: JSON-compatible candidate documents
- optional `constraints`: routing constraints from the request
- optional `classification_mode`: `retrieval` (default) or `complexity`
- optional `max_tokens`

Output `ClassificationResult`:

- `route`: one of `lexical`, `semantic`, or `hybrid` in `retrieval` mode; one
	of `non-retrieval`, `single-step`, or `multi-step` in `complexity` mode
- `reason`: concise explanation for the selected route
- `confidence`: number between 0 and 1

## Execution

Run `scripts/component.py:run(inputs, context)`. The runtime must provide the frozen `context.call_model(...)`. This Component selects only a constrained route; the Agentic workflow owns the mapping from route to concrete Component slots. Use `complexity` mode for Hybrid Agentic RAG.