Groom — Testing skill for Claude Code
Critical grooming session for any task or idea — challenge necessity and approach, cover white spots, record decisions into the existing bank structures.
How to install Groom
Installs to ~/.claude/skills/fockus-skill-memory-bank-groom/SKILL.md
mkdir -p ~/.claude/skills/fockus-skill-memory-bank-groom && curl -fsSL https://raw.githubusercontent.com/fockus/skill-memory-bank/HEAD/commands/groom.md -o ~/.claude/skills/fockus-skill-memory-bank-groom/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Groom does
description: Critical grooming session for any task or idea — challenge necessity and approach, cover white spots, record decisions into the existing bank structures. No spec required. allowed-tools: [Bash, Read, Write, AskUserQuestion]
/mb groom
Groom a task with the agent **before** (or during, or after) implementation. Unlike `/mb discuss`, the goal is NOT to produce a spec — it is to cover the white spots: the agent approaches the requirements critically, challenges the u
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Inkline — by inkline - Structures development workflow using pnpm with emphasis on TypeScript and Vue 3 Composition API 1.4k ★
- Grill — Sharpen a fuzzy idea into §G/§C before spec 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Devils Advocate
REQUIRED after completing ANY spec or plan. You MUST challenge assumptions — unchallenged plans fail in produc
Spec Research
Investigate a loose idea before committing to a change. Runs codebase + (optional) web research via subagents,
Axiom — Development Changelog
Purpose: Historical record of Axiom development milestones, TDD testing results, and architectural decisions.
Write Adr.Skill
Record an architecture decision in docs/decisions/ using the ADR template, then commit and reference it from t
Cover Extend
Extend an existing test suite with the minimum additional tests needed to reach full combinatorial coverage.
Spectastic.Design
Produce the design doc for an existing spec — stack, architecture, decisions, risks, ADRs. Use when deciding h
Related Agents
Backlog Grooming
Use when the user needs to groom, refine, or clean up a product backlog. Triggers on: 'groom backlog', 'backlo
Kimi Challenge
Use this agent when Claude wants Kimi to run an adversarial review that challenges the implementation approach
Angela
Adversarially review a plan's architecture, or review a finished diff for architectural soundness and regressi