Skip to content
Back to skills

Downshift Layering

ASecurity

Use before adding or changing a Downshift feature, adapter, hook, command or policy. Enforces the layering rule so no change serves only one harness.

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added November 10, 2026
ai-agents

Works with

  • claude code

Security analysis

A100/100

Scanned November 10, 2026

npx -y skills add tiagovilasboas/downshift --skill downshift-layering --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Downshift Layering?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Downshift Layering
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tiagovilasboas-downshift-layering/badge)](https://www.skillsdirectory.com/skills/tiagovilasboas-downshift-layering)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: downshift-layering
description: Use before adding or changing a Downshift feature, adapter, hook, command or policy. Enforces the layering rule so no change serves only one harness.
---

# Downshift layering

Rule (AGENTS.md): behaviour in shared layers; adapters only parse, declare `HarnessCapabilities` and emit the wire response; harness facts are capability data; test at the shared layer.

Before coding, read [docs/contrib/layering.md](../../../docs/contrib/layering.md) and run its two checklists. If you are editing more than one adapter for the same logic, stop and move the logic down.

This file is a Claude Code bridge to the same text every other harness reads in AGENTS.md.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.