# Logics Backlog Groomer > Groom and promote a Logics request into a backlog item. Use when a request is clear enough to define scope, acceptance criteria, and priority, and Codex should create `logics/backlog/*.md` aligned with the Logics format. Use when this capability is needed. - Skill: `tomevault-io/logics-backlog-groomer` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/logics-backlog-groomer` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/logics-backlog-groomer/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Product & Planning - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/logics-backlog-groomer --- # Request → Backlog Examples use `python ...` as the canonical cross-platform launcher. If your environment only exposes `python3` or `py -3`, substitute that launcher. ## Do - Read the source request and extract: problem, users impacted, constraints, and success signal. - Define `# Scope` (In/Out) to reduce ambiguity. - Write objective `# Acceptance criteria` (testable checks). - Set `# Priority` (Impact/Urgency) and add dependencies/risks in `# Notes`. - Create the backlog doc: - `python logics/skills/logics.py flow promote request-to-backlog logics/request/.md` - Or `python logics/skills/logics.py flow new backlog --title "..."` ## Outcome A backlog item is “ready” when an engineer could implement it without guessing the intended behavior. --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/alexago83) — claim your Tome and manage your conversions.