---
name: Claude Toolkit Rules
slug: claude-toolkit-rules
category: AI Engineering
description: "Claude Toolkit Rules sets workspace-wide conventions for Claude Code tasks, including path safety, offering alternatives, and devil's-advocate review. Use it when following the toolkit's planning, workflow, and decision rules."
github: "https://github.com/softspark/ai-toolkit/tree/main/app/skills/claude-toolkit-rules"
language: Python
stars: 170
forks: 20
install: "npx degit https://github.com/softspark/ai-toolkit/tree/main/app/skills/claude-toolkit-rules ~/.claude/skills/claude-toolkit-rules"
installs_to: ~/.claude/skills/claude-toolkit-rules
source_path: app/skills/claude-toolkit-rules/SKILL.md
collection_size: 25
category_size: 3670
collection_url: "https://dirskills.com/collections/softspark/ai-toolkit"
added: 2026-09-08T05:33:49.071Z
last_synced: 2026-09-08T05:33:49.071Z
canonical_url: "https://dirskills.com/skills/claude-toolkit-rules"
---

# Claude Toolkit Rules

Claude Toolkit Rules sets workspace-wide conventions for Claude Code tasks, including path safety, offering alternatives, and devil's-advocate review. Use it when following the toolkit's planning, workflow, and decision rules.

**Install:**

```bash
npx degit https://github.com/softspark/ai-toolkit/tree/main/app/skills/claude-toolkit-rules ~/.claude/skills/claude-toolkit-rules
```

## README

# Claude Toolkit Rules

This rule comes from `app/rules/claude-toolkit-rules.md` in ai-toolkit. It applies to
every task in this workspace, not only when it is loaded.

# Claude Toolkit

Shared AI development toolkit — lifecycle hooks, safety constitution, multi-platform support.

## Skill Tiers

- **Tier 1** — single-agent: `/debug`, `/review`, `/refactor`, `/analyze`, `/docs`, `/plan`, `/explain`, `/tdd`, `/triage-issue`
- **Tier 1.5** — planning: `/write-a-prd` → `/prd-to-plan` → `/prd-to-issues`; design: `/design-an-interface`, `/architecture-audit`, `/refactor-plan`
- **Tier 2** — multi-agent: `/workflow <type>` (feature-development, backend-feature, frontend-feature, api-design, database-evolution, test-coverage, security-audit, debugging, incident-response, spike, codebase-onboarding, performance-optimization, infrastructure-change, application-deploy, proactive-troubleshooting)
- **Tier 3** — custom: `/orchestrate <desc>` (3–6 agents) | `/swarm <mode> <desc>` (map-reduce | consensus | relay)

## Path Safety
- NEVER guess or hallucinate user home directory paths
- Use `~` or `$HOME` instead of a hardcoded `/Users` or `/home` prefix followed
  by a user name. The literal prefix is deliberately not written out here: the
  plugin export scans shipped files for exactly that pattern, so an example of
  the mistake would be indistinguishable from the mistake.
- When an absolute path is needed, run `echo $HOME` first to get the correct value

## User Preferences

- **Style:** Direct & efficient. No pleasantries. Measurable results.
- **Methodology:** Provide >=3 alternatives. Use Socratic questioning.
- **Review:** Apply "Devil's Advocate" critique to decisions.