cursor
Cursor skills are aimed at developers using Cursor as an editor-native coding assistant. This page tends to surface implementation guides, debugging helpers, review prompts, and automation skills that work well when the agent can read and modify repository files directly.
Skills compatible with cursor
trading-plan-generator
by jamesrochabrun/skills
A comprehensive skill for creating disciplined, rule-based trading plans that help you manage risk, control emotions, and trade consistently.
create-pr
by n8n-io/n8n
Creates GitHub PRs with titles that pass n8n's check-pr-title CI validation.
swift-actor-persistence
by affaan-m/everything-claude-code
Patterns for building thread-safe data persistence layers using Swift actors. Combines in-memory caching with file-backed storage, leveraging the actor model to eliminate data races at compile time.
enterprise-sales
by refoundai/lenny-skills
Help the user navigate enterprise sales using frameworks from 9 product leaders who have closed large enterprise deals at companies from Stripe to Superhuman.
powerpoint-automation
by aktsmm/agent-skills
AI-powered PPTX generation using Orchestrator-Workers pattern.
chaos-engineer
by jeffallan/claude-skills
Source details, install context, and public review data are available on the full page.
project-planning
by jezweb/claude-skills
Specialized planning assistant for web application projects. Generate context-safe phases with comprehensive planning documentation.
flow
by facebook/react
Source details, install context, and public review data are available on the full page.
swift-protocol-di-testing
by affaan-m/everything-claude-code
Patterns for making Swift code testable by abstracting external dependencies (file system, network, iCloud) behind small, focused protocols. Enables deterministic tests without I/O.
frontend-dev-guidelines
by sickn33/antigravity-awesome-skills
(React · TypeScript · Suspense-First · Production-Grade)
mcp-duckgo
by aahl/skills
Source details, install context, and public review data are available on the full page.
mermaid-diagrams
by softaworks/agent-toolkit
Create professional software diagrams using Mermaid's text-based syntax. Mermaid renders diagrams from simple text definitions, making diagrams version-controllable, easy to update, and maintainable alongside code.
written-communication
by refoundai/lenny-skills
Help the user communicate more effectively in writing using frameworks and insights from 38 product leaders.
agent-md-refactor
by softaworks/agent-toolkit
Refactor bloated agent instruction files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) to follow progressive disclosure principles - keeping essentials at root and organizing the rest into linked, categorized files.
read-arxiv-paper
by karpathy/nanochat
Source details, install context, and public review data are available on the full page.
writing-clearly-and-concisely
by softaworks/agent-toolkit
Write with clarity and force. This skill covers what to do (Strunk) and what not to do (AI patterns).
commit-work
by softaworks/agent-toolkit
Source details, install context, and public review data are available on the full page.
crafting-effective-readmes
by softaworks/agent-toolkit
READMEs answer questions your audience will have. Different audiences need different information - a contributor to an OSS project needs different context than future-you opening a config folder.
gemini
by softaworks/agent-toolkit
NEVER use --approval-mode default in background or non-interactive shells (like Claude Code tool calls). It will hang indefinitely waiting for approval prompts that cannot be provided.
humanizer
by softaworks/agent-toolkit
Source details, install context, and public review data are available on the full page.
qa-test-planner
by softaworks/agent-toolkit
A comprehensive skill for QA engineers to create test plans, generate manual test cases, build regression test suites, validate designs against Figma, and document bugs effectively.
session-handoff
by softaworks/agent-toolkit
Creates comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves the long-running agent context exhaustion problem.
c4-architecture
by softaworks/agent-toolkit
Generate software architecture documentation using C4 model diagrams in Mermaid syntax.
codex
by softaworks/agent-toolkit
GPT-5.2 Advantages : 76.3% SWE-bench (vs 72.8% GPT-5), 30% faster on average tasks, better tool handling, reduced hallucinations, improved code quality. Knowledge cutoff: September 30, 2024.