Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
28.025 de skill-uri din 1.126 de depozite · actualizat acum 14 minute
2.924 de skill-uri
- systematic-debuggingBlackBeltTechnology/pi-agent-dashboardRoot-cause a bug already in front of you, instead of guessing at fixes. Use on triggers like "root cause this", "why is this failing", "debug systematically", "this test is flaky", "it works locally but not in CI", or when a fix attempt has already failed once. Enforces a phased evidence-first process before any code change. Not a feature-build or ship workflow.InginerieFără avertismente★ 331↓ —
- amazon-review-analyzernexscope-ai/Amazon-SkillsDeep Amazon review analysis for competitive intelligence and product improvement. Extract sentiment patterns, recurring complaints, feature requests, and competitive insights from customer feedback. Turn reviews into actionable product development and marketing strategies. Use when the user asks about review analysis, customer feedback, product complaints, sentiment analysis, or what customers think about products.InginerieFără avertismente★ 798↓ —
- pixi-jsMindrally/skillsExpert guidance for Pixi.js game development with TypeScript, focusing on high-performance web and mobile gamesInginerieFără avertismente★ 286↓ —
- omero-integrationforyourhealth111-pixel/Vibe-SkillsMicroscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.InginerieFără avertismente★ 3,8 K↓ —
- glasserlingxling/awesome-skills-cnSearch, inspect, and run third-party data APIs through one CLI when the environment has no suitable integration.InginerieFără avertismente★ 319↓ —
- deep-learning-pythonMindrally/skillsGuidelines for deep learning development with PyTorch, Transformers, Diffusers, and Gradio for LLM and diffusion model work.InginerieFără avertismente★ 286↓ —
- electron-developmentMindrally/skillsElectron development guidelines for building cross-platform desktop applications with JavaScript/TypeScriptInginerieFără avertismente★ 286↓ —
- hz-react-native-expometa-quest/agentic-toolsBuild and iterate on React Native apps for Meta VR / Horizon OS with Expo. Covers the fast dev loop — install Expo Go from the Meta Horizon Store, run a Metro dev server, load its bundle URL on the headset, and get live Fast Refresh — plus the full development-build path with the expo-horizon-core config plugin, prebuild, Quest product flavors, and the Horizon-forked libraries (location, notifications, IAP). Use when the user wants to build or run a Meta VR app in React Native/Expo, load a JS bundle URL on a headset, set up expo-horizon-core, or get live reload on device. Build path: Standard Android with React Native; use hz-quest-verify-first if the path is unclear.InginerieFără avertismente★ 233↓ —
- hz-metavrx-layout-sdkmeta-quest/agentic-toolsBuild multi-window Meta Horizon OS experiences with the MetaVrx Layout SDK in Jetpack Compose or React Native. Covers framework selection, setup, anchoring, semantic offsets, window promotion, fallback, priority, lifecycle, and theming. Use for apps that need multiple app-owned panels without an immersive scene. Build path: Standard Android, including React Native; use hz-quest-verify-first if the path is unclear, and do not use this skill for immersive Spatial SDK scenes.InginerieFără avertismente★ 233↓ —
- typescript-strictBlackBeltTechnology/pi-agent-dashboardTypeScript strict mode patterns with interfaces, type guards, generics, and utility types. Use when defining types, creating type-safe functions, handling nullable values, or implementing generic components.InginerieFără avertismente★ 331↓ —
- code-communitiesathola/claude-night-marketDetects architectural clusters and coupling boundaries via community detection on the code graph. Use when identifying module groupings or refactoring targets.InginerieFără avertismente★ 343↓ —
- todoist-cliDoist/todoist-cliManage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the `td` CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.InginerieFără avertismente★ 324↓ —
- null-safetyrrezartprebreza/spring-boot-skillsUse when annotating nullability in Spring Boot 3 / Spring Framework 6 code, integrating Kotlin, or adding static nullability checks without assuming Spring Framework 7 JSpecify defaults.InginerieFără avertismente★ 325↓ —
- log-error-digestzebbern/claude-code-guideAnalyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or get distribution stats.InginerieFără avertismente★ 4,7 K↓ —
- night-market-change-controlathola/claude-night-marketClassify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.InginerieFără avertismente★ 343↓ —
- code-vuln-auditzebbern/claude-code-guideScan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded passwords, or code security checks.InginerieFără avertismente★ 4,7 K↓ —
- session-managementathola/claude-night-marketManages Claude Code sessions with naming, checkpointing, and resume strategies. Use when organizing long-running work or resuming across sessions.InginerieFără avertismente★ 343↓ —
- performance-reviewathola/claude-night-marketDetects time and space complexity hotspots via AST scan. Use when code feels slow, before performance-sensitive merges, or to find O(n²) regressions.InginerieFără avertismente★ 343↓ —
- night-market-build-and-envathola/claude-night-marketRebuild the dev environment: uv, Python tiers, pins, traps. Use when onboarding or toolchain breaks. Do not use for daily commands; use night-market-operations.InginerieFără avertismente★ 343↓ —
- python-asyncathola/claude-night-marketAsync Python patterns via asyncio and aiohttp for I/O-bound concurrency. Use when adding async APIs, handling concurrent I/O, or debugging async code.InginerieFără avertismente★ 343↓ —
- gemini-delegationathola/claude-night-marketDelegates tasks to Gemini CLI implementing delegation-core for Google's models. Use when delegation-core selects Gemini or 1M+ token context is needed.InginerieFără avertismente★ 343↓ —
- code-to-diagramzebbern/claude-code-guideAnalyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a module diagram from source code.InginerieFără avertismente★ 4,7 K↓ —
- citation-managementbrycewang-stanford/Auto-Empirical-Research-SkillsUse when adding citations to a .bib file, importing references by DOI, cleaning a bibliography, detecting duplicate entries, or normalizing citation keys. Uses direct .bib manipulation with CrossRef API for metadata resolution — no external tool dependencies.InginerieFără avertismente★ 4,8 K↓ —
- auto-review-loop-minimaxbrycewang-stanford/Auto-Empirical-Research-SkillsAutonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".InginerieFără avertismente★ 4,8 K↓ —