Refine Dev
CheckedRefine Dev optimizes code snippets by suggesting improvements for readability and efficiency, boosting developer productivity.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add itechmeat/llm-code --skill refine-dev -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
itechmeat
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned itechmeat/llm-code at 7ae8a00524.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 7ae8a00524
- Manifest
- skills/refine-dev/SKILL.md
- Scanned
- 11 files, 2,973 lines
About this skill
What it does
This skill enables AI agents to assist in building enterprise CRUD (Create, Read, Update, Delete) applications using the Refine.dev framework. It provides a headless React framework with built-in data fetching, routing, authentication, and access control, allowing developers to focus on application logic rather than boilerplate setup. The agent can help define resources, configure data providers, and generate basic app structures for rapid development.
When to use it
- When building CRUD applications that require robust data management and user authentication.
- For quickly scaffolding a new Refine.dev project with a REST or GraphQL API backend.
- To assist in defining resources (entities like posts, users, products) within the application.
- When needing help configuring routing and integrating with React Router.
Key capabilities
- Data Provider Configuration: Assists in setting up adapters for various backends (REST, GraphQL).
- Resource Definition: Helps define entities (resources) with associated CRUD operations (list, create, edit, show).
- Hook Utilization: Guides the use of Refine hooks like
useList,useOne,useCreate,useUpdate, anduseDelete. - Routing Integration: Facilitates integration with React Router for managing application routes.
- Authentication Support: Helps configure authentication providers for login, logout, and permissions management.
Example prompts
- "Generate a basic Refine app structure using Vite and Mantine, connecting to
https://api.example.com." - "Define a 'posts' resource with list, create, edit, and show routes in my Refine application."
- "How do I use the
useListhook to fetch data for a list view in Refine?"
Tips & gotchas
- UI Library Consistency: Refine.dev recommends sticking with a single UI library (like Mantine) once selected.
- Data Provider Reliance: Always utilize Refine hooks (
useList,useCreate, etc.) for data operations; avoid bypassing the data provider directly. - Dynamic API URLs: Avoid hardcoding API URLs; configure them within the data provider instead.