cipshadow

Anti Sloppifier — Testing skill for Claude Code

Testing community

Audits a PM work session for AI slop, decision abdication, and thinking replacement.

How to install Anti Sloppifier

Installs to ~/.claude/skills/cipshadow-leverage-and-taste-anti-sloppifier/SKILL.md

Terminal

mkdir -p ~/.claude/skills/cipshadow-leverage-and-taste-anti-sloppifier && curl -fsSL https://raw.githubusercontent.com/cipshadow/leverage-and-taste/HEAD/commands/anti-sloppifier.md -o ~/.claude/skills/cipshadow-leverage-and-taste-anti-sloppifier/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Anti Sloppifier does

description: Audits a PM work session for AI slop, decision abdication, and thinking replacement. Run after strategy, specs, roadmap decisions, or research. Scores 15 habits, applies the slop test, saves a diary entry. model: sonnet user-invocable: true

/anti-sloppifier: AI-Use Self-Audit for PM Work

Goal

Assess whether the user used AI to support their own thinking rather than replace it. Provide friendly, direct, no-bullshit coaching that helps the user get more leverage from A

Alternatives in Testing

Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
Axiom — Development Changelog — Purpose: Historical record of Axiom development milestones, TDD testing results, and architectural decisions 671 ★