Loading...
Loading...
Found 3,207 Skills
WPS Presentation Smart Assistant: Control PPTs via natural language to solve pain points such as layout beautification, content generation, and animation settings
Arquiteto de Dados especialista em PostgreSQL, Supabase e modelagem multi-tenant para a plataforma PAPO
Comprehensive toolkit for validating, linting, and securing Dockerfiles. Use this skill when validating Dockerfile syntax, checking security best practices, optimizing image builds. Applies to all Dockerfile variants (Dockerfile, Dockerfile.prod, Dockerfile.dev, etc.).
Generates minimal macOS Seatbelt sandbox configurations. Use when sandboxing, isolating, or restricting macOS applications with allowlist-based profiles.
Manage a structured task list using a Markdown file in the workspace. Track progress on complex multi-step tasks. File-based — just Read and Write the todo file.
Read, watch, and listen to video/audio files. Use Gemini for native video understanding, or extract key frames + Whisper transcription as fallback. Use when a user sends a video/audio and asks about its content, what's in it, what someone said, etc.
Generate songs and music using AI (ACE-Step, local). Use when users ask to: sing a song, create music, make a beat, write and perform a song, generate BGM, etc. Covers requests like 'sing a song', 'write me a song', 'sing me a song', 'create a rap about coding', 'make a song about cats'.
Deploy applications to Vercel with automatic framework detection
Route53 Record Manager - Auto-activating skill for AWS Skills. Triggers on: route53 record manager, route53 record manager Part of the AWS Skills skill category.
Xss Vulnerability Scanner - Auto-activating skill for Security Fundamentals. Triggers on: xss vulnerability scanner, xss vulnerability scanner Part of the Security Fundamentals skill category.
Write Twitter/X posts and threads. Use when asked to write, create, draft, or produce a tweet, Twitter post, X post, Twitter thread, or tweetstorm. Also use when user mentions Twitter or X in a social media writing context. Outputs publish-ready tweets and threads with proper formatting.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.