zeroagent-studio / rules
sakurablush/zeroagent-studio/.cursor/rules/zeroagent-security-auditor.mdc
Security audit for ZeroAgent Studio. Use when reviewing API keys, scraped content, CORS proxies, speech, or dependencies.
The rules real projects give Cursor's agent, from .cursor/rules.
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.
sakurablush/zeroagent-studio/.cursor/rules/zeroagent-security-auditor.mdc
Security audit for ZeroAgent Studio. Use when reviewing API keys, scraped content, CORS proxies, speech, or dependencies.
wchen02/cursor-agent-learning/.cursor/rules/human-in-the-loop.mdc
When and how to use human-in-the-loop (HITL) in agent workflows; apply before merge, deploy, release, or applying security fixes.
darknecrocities/SkillBuilder/.cursor/rules/security.mdc
Security hardening and vulnerability defense skill. Enforces OWASP Top 10 mitigations, zero hardcoded secrets, input sanitization, and SQL parameterization.
darknecrocities/SkillBuilder/.cursor/rules/world-class-engineering.mdc
A rigorous engineering skill for architecture, implementation, refactoring, AI/ML integration, testing, security, code review, and production-quality software delivery.
galyarderlabs/galyarder-framework/.cursor/rules/code-reviewer.mdc
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
AlessandroMartini/Awesome_IA_Rules/.cursor/rules/core/01-core-engineering.mdc
Core enterprise architecture, Zero-Trust security, error/log proximity rule, observability, and testing standards
darknecrocities/SkillBuilder/.cursor/rules/gcp.mdc
Google Cloud Platform architecture, Cloud Run serverless deployment, Pub/Sub, Secret Manager, Cloud SQL, and IAM least-privilege security.
HermeticOrmus/linux-sysadmin-skills/.cursor/rules/linux-sysadmin.mdc
Linux sysadmin workflows for Debian/Ubuntu (apt, systemd, journalctl) covering security, performance, diagnose, monitor, maintain. Confirm before destructive operations.
encoreshao/encore-skills/.cursor/rules/review-code.mdc
Pre-MR self-review — first confirm the problem is actually solved, then check for security, correctness, and simplicity
rustic-ai/codeprism/.cursor/rules/rust-advanced.mdc
Enterprise-grade patterns for production systems including security, complex architecture, and deployment. Use this for high-stakes applications requiring authentication, comprehensive testing, and production deployment.
michele-prandina/ClaudE2E/.cursor/rules/agents/head-of-engineering.mdc
Head of Engineering persona — architecture decisions, technical feasibility, stack governance. Use when discussing tech stack, ADRs, performance, security, or system design.
galyarderlabs/galyarder-framework/.cursor/rules/iso-42001-ai-governance.mdc
AI governance audit using ISO 42001 standard. Ensures AI systems are developed and deployed responsibly with risk management, ethics, security, transparency, and compliance best practices.
sordi-ai/skill-everything/.cursor/rules/docker.mdc
Apply when writing or reviewing Dockerfiles, docker compose files, or container build pipelines. Covers layer caching, multi-stage builds, security hardening, and compose conventions.
darknecrocities/SkillBuilder/.cursor/rules/aws.mdc
Amazon Web Services resilient cloud architecture, serverless Lambda execution, S3 bucket security, DynamoDB single-table design, and IAM least privilege.
openlit/openlit/.cursor/rules/pr-validation.mdc
PR validation workflow (security, functionality and shortcomings, scale testing with mock data, hard-coded strings, CE/EE docs and code separation, reusable components, design principles, cross-agent verification). Apply only when the user explicitly asks to validate a PR or run the validation workflow. When a PR looks ready, ask "Your PR looks ready. Should I run the validation workflow?" instead of starting it.
Ratimon/openquok-monorepo/.cursor/rules/security-guidelines.mdc
Security — no service client in client code, no SUPABASE_SECRET_KEY on client, RLS, correct Supabase client per context, rate limit config, SSR state rules (no authenticationRepository in server load, ssr = false for protected routes)
raye-deng/open-code-review/.cursor/rules/open-code-review.mdc
Open Code Review - AI code quality gate for detecting hallucinated packages, stale APIs, context breaks, security anti-patterns, and over-engineering in AI-generated code.
darknecrocities/SkillBuilder/.cursor/rules/devops.mdc
Architect, implement, and maintain secure cloud infrastructure on GCP/AWS, multi-stage non-root Docker containers, Terraform IaC, CI/CD pipelines, and OpenTelemetry observability.
KangaKode/universal-agent-bootstrap/.cursor/rules/code-reviewer.mdc
Code review quality gate — enforces architecture, code quality, and security conventions. Use proactively after any code change.
KangaKode/universal-agent-bootstrap/.cursor/rules/red-team.mdc
Adversarial security gate — blocks commits with secrets, injection vulnerabilities, SSRF, and authorization failures. Run before every commit.
Instruction files for Cursor's agent, kept in .cursor/rules/ as .mdc files.
A rule can apply only to files matching a pattern, or only when the agent asks for it. AGENTS.md always applies.
Copy the .mdc file into your project's .cursor/rules/ directory and adjust its globs.
Open a rule to see its discussion. Reports from people and their agents are coming.