Test Omnigent’s Cursor SDK integration against a live local server. Build test agents, run real conversations, and check authentication, model selection, and tool connections while investigating empty responses or bridge processes left after shutdown.
- Test Cursor authentication and real responses
- Verify file operations and sub-agent delegation
- Investigate invalid models and empty output
omnigent-ai/omnigent☆ 10.9KUpdated Oct 19, 2026
Review past local Cursor sessions, identify recurring tasks, and propose changes to a project skill. Changes are tested on separate validation tasks and staged for review before adoption, with backups of existing files.
- Turn recurring Cursor tasks into a reusable skill
- Review proposed edits and validation scores before adoption
- Try the workflow without provider calls using mock
microsoft/SkillOpt☆ 18.6KUpdated Oct 19, 2026
Create specialized assistants for Cursor that work with their own context, separate from the main conversation. Define responsibilities, instructions, output formats, model choices, and execution settings for reusable workflows such as verification, debugging, and documentation.
- Creating an assistant to verify completed work
- Defining a specialist for debugging and test failures
- Creating a read-only security audit assistant
tech-leads-club/agent-skills☆ 7.1KUpdated Oct 17, 2026
Check skills before distributing them to Codex or Cursor. Identify unsupported metadata fields, Claude-specific variables in shell examples, and inconsistencies between source skills and their installation copies using the project's compatibility checker.
- Check a new skill before opening a pull request
- Review skill copies for Codex or Cursor
- Investigate compatibility findings from CI
affaan-m/ECC☆ 283.9KUpdated Oct 16, 2026
Set up claude-mem in Cursor with a local or remote worker, the process that runs its work. Follow configuration steps for remote inference through cmem.ai or a local observer using the host's login.
- Installing claude-mem with a local worker in Cursor
- Connecting Cursor to a remote claude-mem worker
- Configuring host-login or cmem.ai inference
thedotmack/claude-mem☆ 101.8KUpdated Oct 19, 2026
Delegate a coding task to the Cursor Agent CLI (`cursor-agent`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use Cursor to implement/fix/refactor" — or wants to run a queue of coding tasks through Cursor while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
The English summary is being prepared. Showing the original description.
amElnagdy/delegate-skills☆ 2.4KUpdated Oct 15, 2026
Expert in Cursor AI IDE - the leading AI-powered code editor. Covers Rules files for project-specific AI behavior, Plan Mode for structured development, Background Agents for parallel work, and advanced features like voice mode and browser integration. Essential for developers maximizing AI-assisted coding productivity. Use when "cursor ai, cursor rules, .cursorrules, cursor composer, cursor agent, plan mode, background agent, cursor tips, cursor, ide, ai-coding, editor, productivity, agent, developer-tools" mentioned.
The English summary is being prepared. Showing the original description.
omer-metin/skills-for-antigravity☆ 168Updated Jan 22, 2026
Build command-line interfaces for graphical applications in Cursor using the CLI-Anything workflow. It supports creating and extending these interfaces, running tests, checking required criteria, and listing tools through slash commands or natural-language requests.
- Build a command-line interface for a graphical application
- Extend an existing CLI to cover more operations
- Run tests and validate a CLI implementation
HKUDS/CLI-Anything☆ 55.1KUpdated Sep 22, 2026
Design oversized cursor animation for HyperFrames launch videos. Guide viewers toward interface actions, make clicks trigger the next animation, and connect scenes through deliberate pointer movement, with guidance on size, appearance, entry, targeting, and exit.
- Guide attention through a product interface video
- Trigger typing or transitions with a click
- Add purposeful movement to a static scene
heygen-com/hyperframes☆ 67.5KUpdated Oct 19, 2026
Add cursor-following water-ripple distortion to existing images using Shaders components. Preserve page content and layout while integrating lazy loading, accessible image fallbacks, and static display when WebGPU is unavailable or reduced motion is enabled.
- Adding cursor ripples to a hero image
- Adding interactive distortion to gallery images
- Replacing a cursor-driven spotlight reveal
MengTo/Skills☆ 6.8KUpdated Oct 18, 2026
Set up the official Google Ads MCP Server, a connector that lets AI assistants retrieve campaign data and reporting metrics through natural language. The guide covers installation, credentials, client configuration, and connection checks.
- Connecting Claude Code or Cursor to Google Ads
- Configuring API credentials and environment variables
- Testing campaign queries in natural language
google/skills☆ 21.4KUpdated Oct 17, 2026
Import existing notes and agent instructions into LifeOS by splitting content into sections and proposing destinations. Review uncertain classifications, approve selected groups, and retain source information alongside the imported material.
- Importing Obsidian or Notion exports into LifeOS
- Moving notes from an older LifeOS installation
- Reviewing and importing CLAUDE.md or Cursor rules
danielmiessler/LifeOS☆ 19.5KUpdated Sep 4, 2026
Build MCP Apps that display interactive json-render interfaces inside clients such as Claude and ChatGPT. The skill covers a Node.js server, a React view, and packaging the interface into a single HTML file.
- Build an interactive UI inside an MCP client
- Add json-render tools to an existing MCP server
- Package a React interface into one HTML file
vercel-labs/json-render☆ 18.7KUpdated Oct 14, 2026
Create clickable links that open conversations, files, folders, or settings directly in apps such as Codex, Cursor, and VS Code. Check supported formats, format links for Slack, and provide alternatives when direct links are unavailable.
- Share a link to a Codex conversation
- Open a file at a specific line from Slack
- Check whether an app supports direct links
composio-community/awesome-codex-skills☆ 17KUpdated Jul 26, 2026
Repair the Cursor editor when it crashes, fails to launch, or new Agent chats break. Use with a Request ID, fresh logs, CursorRule.parse_error or invalid UTF8 in skill frontmatter, or a better-sqlite3 NODE_MODULE_VERSION mismatch. Finds a reproducible cause, applies a narrow reversible fix and proves it with two new chats. Triggers: /cursor-repair, Cursor won't start, Cursor agent broken.
The English summary is being prepared. Showing the original description.
tonydzi/second-brain-starter-kit☆ 9Updated Oct 16, 2026
Route requests from OpenClaw to external coding agents such as Claude Code or Cursor. Start or continue sessions using ACP, a protocol for connecting agents, or relay prompts directly through acpx while preserving conversation context.
- Starting a Claude Code session in a thread
- Continuing work with an external coding agent
- Relaying prompts directly through acpx
openclaw/openclaw☆ 392.5KUpdated Oct 19, 2026
Search past coding sessions across Claude Code, Codex, and Cursor to recover earlier attempts, failed approaches, decisions, and findings. It filters history by topic and time, then summarizes technical details relevant to the question.
- Recovering approaches tried in earlier sessions
- Reviewing past debugging attempts and failures
- Summarizing recent work across coding agents
slopus/happy☆ 24.2KUpdated Oct 19, 2026
Build software with Cursor, the AI-powered code editor. Use when a user asks to configure Cursor rules, set up .cursorrules files, use Composer for multi-file edits, integrate MCP servers, or optimize AI-assisted coding workflows.
The English summary is being prepared. Showing the original description.
TerminalSkills/skills☆ 172Updated Oct 14, 2026
Use when working with Cursor — cursor AI-powered editor management and team analytics. Covers team seat management, usage tracking, model configuration, rules file analysis, project settings review, and workspace configuration. Use when managing Cursor team licenses, reviewing AI feature adoption, or analyzing Cursor workspace and rules configurations.
The English summary is being prepared. Showing the original description.
cloudthinker-ai/CloudSkills☆ 6Updated Apr 5, 2026
独立した作業をheadless Cursor CLIへ委任し、一時Sprintで実行・監視・検収する。永続PLANが必要な場合はcursor-agent-delegateを使う。
The English summary is being prepared. Showing the original description.
ryryo/dot-claude-dev☆ 3Updated Oct 18, 2026
Connect a remote AI agent to your browser by generating a setup key and connection instructions. The connected agent receives its own tab, with an option to narrow its default page access.
- Connecting a remote agent to a browser
- Sharing browser access with Codex or Cursor
- Limiting page access when pairing an agent
garrytan/gstack☆ 136.9KUpdated Oct 19, 2026
Turn a supplied quote into an animated video-intro scene in a single HTML file. Text appears character by character with a glowing cursor, colored trails, and light flares, with space for a source or chapter label.
- Introducing a video with an animated quote
- Creating a glowing title scene for a chapter
- Adding a source label beneath an opening quote
nexu-io/open-design☆ 102.5KUpdated Oct 19, 2026
Fetch current library documentation with the ctx7 CLI to check API usage while coding. The skill also guides Context7 MCP setup, which connects documentation access to Claude Code, Cursor, or OpenCode, and covers login and authentication options.
- Fetch current documentation for a library
- Check API signatures while writing code
- Set up Context7 for an AI coding agent
upstash/context7☆ 63.3KUpdated Oct 19, 2026
Find past discussions across existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats by title, workspace, or message text. With explicit authorization, send follow-up work to a specific supported chat; Gemini CLI supports search only.
- Finding a conversation using a remembered phrase
- Recalling what an agent previously said
- Sending follow-up work to a specific chat
screenpipe/screenpipe☆ 22KUpdated Oct 19, 2026