skills
agent
Warn
Health Warn
- No license — Repository has no license file
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Community trust — 25 GitHub stars
Code Pass
- Code scan — Scanned 5 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
Purpose
This agent provides AI coding assistants with the rules and architectural methodology for Feature-Sliced Design (FSD) v2.1. It helps developers correctly structure frontend projects, resolve import issues, and integrate the framework with various tools like Next.js and Redux.
Security Assessment
Overall risk is Low. This tool operates purely as a set of instructional guidelines and reference documents for an AI agent. It does not execute shell commands, make external network requests, or access sensitive data. A light code scan found no dangerous patterns and detected zero hardcoded secrets or malicious code. No dangerous permissions are required for its operation.
Quality Assessment
The project is highly maintained, with its most recent push happening today. It demonstrates solid community trust for a specialized methodology tool, backed by 25 GitHub stars. While the automated health check flagged a missing license file, the README explicitly states the tool uses the standard MIT license. The documentation is clear, detailed, and well-structured, making the tool easy to implement and integrate.
Verdict
Safe to use.
This agent provides AI coding assistants with the rules and architectural methodology for Feature-Sliced Design (FSD) v2.1. It helps developers correctly structure frontend projects, resolve import issues, and integrate the framework with various tools like Next.js and Redux.
Security Assessment
Overall risk is Low. This tool operates purely as a set of instructional guidelines and reference documents for an AI agent. It does not execute shell commands, make external network requests, or access sensitive data. A light code scan found no dangerous patterns and detected zero hardcoded secrets or malicious code. No dangerous permissions are required for its operation.
Quality Assessment
The project is highly maintained, with its most recent push happening today. It demonstrates solid community trust for a specialized methodology tool, backed by 25 GitHub stars. While the automated health check flagged a missing license file, the README explicitly states the tool uses the standard MIT license. The documentation is clear, detailed, and well-structured, making the tool easy to implement and integrate.
Verdict
Safe to use.
AI agent skills for applying Feature-Sliced Design (FSD) v2.1 in frontend projects.
README.md
Feature-Sliced Design: Agent Skills
Agent skills that teach AI coding agents Feature-Sliced Design (FSD) v2.1 architectural methodology.
Installation
npx skills add feature-sliced/skills
Available Skills
feature-sliced-design
Apply FSD v2.1 principles when structuring frontend projects. The agent learns layer hierarchy, import rules, the decision framework for code placement, and common patterns.
Use when:
- Setting up or reorganizing a frontend project structure
- Deciding where to place code (pages vs. features vs. entities vs. shared)
- Placing static assets (images, icons, fonts, PDFs) in the right slice or layer
- Grouping closely related slices for navigation as the project grows
- Resolving cross-import issues or evaluating the @x pattern
- Deciding whether to create or remove an entity, or whether to skip the entities layer entirely
- Migrating from FSD v2.0 or a non-FSD codebase
- Integrating FSD with Next.js (App Router or Pages Router), Nuxt, Vite, or Astro
- Implementing auth, API request handling, or state management (Redux, TanStack Query) within FSD
Examples:
Set up FSD project structure with Next.js App Router
Where should I put this auth logic?
These two entities need to import from each other. How do I fix this?
Where should I put hero images for my landing page?
Skill Structure
feature-sliced-design/
SKILL.md Core rules and decision framework
references/
layer-structure.md Detailed folder structures per layer (incl. slice groups)
asset-handling.md Where to place images, icons, fonts, and other static assets
cross-import-patterns.md Cross-import resolution: 4 strategies for features/widgets, @x for entities
excessive-entities.md Keeping the entities layer clean: when to skip, what to extract
migration-guide.md v2.0→v2.1 and non-FSD migration
framework-integration.md Next.js (App Router & Pages Router), Nuxt, Vite/CRA, Astro setup
practical-examples.md Auth, types, API, Redux, TanStack Query (React Query)
The agent reads only SKILL.md by default. Reference files are loaded on demand based on the task.
Contributing
When adding or modifying reference files, keep these constraints in mind:
SKILL.mdbody ≤ 500 lines- Each reference file: 200–500 lines
SKILL.md+ any single reference ≤ 1,000 lines combined- If a reference exceeds 500 lines, split it and update the conditional loading section at the bottom of
SKILL.md
References
License
MIT
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found