# Intake Classification

> Intake Classification

- Skill: `onfire7777/intake-classification` (Agent Skill)
- Install (CLI): `npx skillmds@latest add onfire7777/intake-classification`
- Raw SKILL.md: https://api.skillmd.com/api/skills/onfire7777/intake-classification/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: onfire7777 (https://skillmd.com/u/onfire7777)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/onfire7777/intake-classification

---


# Intake Classification

Purpose: Convert a request into a bounded work item.

1. Identify user goal, technical goal, risk, and affected areas.
2. Write testable acceptance criteria.
3. Decide whether R&D, frontend, and backend are needed.
4. Push ambiguity into open questions or proposal risks.

Checklist:

- Scope in and out are clear.
- Acceptance criteria are testable.
- Routing flags match the work.
- Risk level is justified.

Positive example: bug fix with backend only and one regression test.
Negative example: broad "improve app" routed to every team with no criteria.

Failure modes: oversized scope, untestable criteria, hidden risk.