agentleFS
G1JoshiG1Joshi/Agent-Skills/skills/tools/cursor/SKILL.md

cursor

Skill15 starsChanged 42 days agoMITView on GitHub

Expert Cursor IDE assistance covering AI pair programming, codebase indexing, custom rules (.cursorrules), Composer, and debugging. Use when maximizing AI-native software development velocity.

  • Reads credentials

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use codex.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • engtySkill

    codex

    Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a .cursorrules file in the project root to permanently align model completions with team conventions.

    line 95
  2. Very specific:

    Use @file, @docs, and @symbol instead of @codebase for targeted tasks to reduce prompt token noise and cost.

    line 96
  3. Distinctive:

    Write ambiguous prompts; specify desired libraries, error handling strategies, and boundary constraints.

    line 104

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cursor

Cursor is an AI-native code editor built on VS Code, featuring multi-file code editing via Cursor Composer, predictive codebase indexing, and contextual code generation.

When to Use

  • AI-First Software Development: Accelerating feature engineering with Cursor IDE, Composer, and multi-file edits.
  • Repository-Level Contextual Reasoning: Using @codebase to search across semantic embeddings of entire projects.
  • Custom Project Guidelines with .cursorrules: Instructing the AI model on architecture, frameworks, and testing standards.
  • Interactive Inline Code Editing: Generating, refactoring, and fixing code directly in the editor buffer via Cmd+K.

Quick Start

Configure repository rules in .cursorrules:

# .cursorrules

- Prefer functional components and hooks in React 19.
- Always use TypeScript with strict null checks.
- Keep helper functions small and pure.
- Include unit tests in Vitest for new features.

Core Concepts

Configuring .cursorrules for Automated Agent Guidelines

Defining persistent project rules for code generation:

# .cursorrules

You are an expert Full-Stack TypeScript and Rust developer.
Always adhere strictly to these conventions:

- Framework: Next.js 15 (App Router), React 19, Tailwind CSS v4.
- Language: Strict TypeScript, no `any`, use `unknown` with type guards.
- Code Style: Functional, immutable, early returns, descriptive error messages.
- State: Favor Server Components and Server Actions over client state.
- Testing: Always write unit tests with Vitest and integration tests with Playwright.
- Do NOT hallucinate dependencies not present in package.json.
- When generating code, omit explanatory conversational filler; output code and brief rationale.

Targeted Context Tagging with @ Directives

Injecting precise context into AI prompt buffers:

Prompt:
@codebase How is authentication token verification handled across our microservice routes?
Inspect @middleware.ts and @src/auth/session.ts to implement a new rate-limited admin route guard.
Ensure compliance with @docs/security-guidelines.md.

Multi-File Composer Refactoring Workflows

Prompting across architectural boundaries:

Prompt in Composer:
Refactor our legacy User REST endpoints to modern Server Actions:
1. Create app/actions/user.ts with Zod input validation schemas.
2. Update app/profile/page.tsx to call the server action with useActionState.
3. Remove old API route handler in app/api/user/route.ts.
4. Add unit test in tests/actions/user.test.ts verifying rejection of invalid email.

Common Patterns

Global and Project .cursorrules Configuration

Problem: Cursor generates responses with generic boilerplate that violates repository architectural rules.
Solution: Define comprehensive repository rules in root .cursorrules.

# .cursorrules

- Prefer TypeScript strict mode with no explicit 'any'.
- Use named exports rather than default exports for React components.
- Colocate unit tests next to source files using the *.test.ts pattern.
- Wrap all external network calls with timeout boundaries.

Best Practices

Do:

  • Create a .cursorrules file in the project root to permanently align model completions with team conventions.
  • Use @file, @docs, and @symbol instead of @codebase for targeted tasks to reduce prompt token noise and cost.
  • Review AI-generated diffs carefully before accepting multi-file Composer changes.
  • Configure .cursorignore to prevent indexing of generated files, .env secrets, and build output directories.

Don't:

  • Prompt the AI with raw database passwords, production API keys, or private customer data.
  • Blindly accept massive multi-file refactors without running automated test suites (npm test).
  • Write ambiguous prompts; specify desired libraries, error handling strategies, and boundary constraints.

Troubleshooting

ErrorCauseSolution
Codebase indexing failedMassive files (node_modules, large binaries) not excluded.Add paths to .cursorignore.
Composer diff cannot be appliedFile edited externally while Cursor was generating code.Re-run prompt using fresh file state.
Cursor tab autocomplete sluggishLarge language server indexing lag in background.Restart Cursor or disable unused language extensions.

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.