Top Agent Skills

Audits ECC Tools GitHub App for cost issues like runaway PR creation, quota bypass, premium-model leakage, and duplicate jobs, using an evidence-first workflow.

Scans legacy codebases to extract implicit coding conventions across architecture dimensions, resolves conflicts interactively, and generates an enforceable style rules file.

Design task-local harnesses, eval gates, and reusable skill extraction for adaptive agent workflows.

Optimize content for AI Overviews, ChatGPT, Perplexity, and other AI search systems by improving GEO, AI citations, llms.txt readiness, crawler accessibility, and passage-level citability.

Write defensive, production-grade Bash scripts with strict error handling, safe patterns, and comprehensive testing.

Optimize lead capture, contact, demo request, application, survey, quote, and checkout forms to maximize completion rates while preserving data usefulness.

Diagnose why a page is or is not converting and provide prioritized, evidence-based recommendations for improvement.

Analyzes code for logical errors, race conditions, security vulnerabilities, and algorithmic flaws using structured reasoning across 9 risk categories.

Create, update, or migrate Wear OS projects using Compose Material3, Foundation, and Navigation3 libraries with official component samples and migration guidance.

Add authentication and authorization to a Blazor Web App, handling render modes, Identity pages, and auth state serialization.

Adds an iOS App Clip target to an Expo project, including target setup, associated domains, AASA file hosting, and TestFlight submission.

Search reference implementations and code examples from Adobe's Block Collection and community Block Party for AEM Edge Delivery blocks, plugins, and build tools.

Turn engineering work into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates by mining Copilot CLI session logs, git history, and GitHub PRs.

Performs comprehensive SQL code review across all major databases, analyzing security, performance, maintainability, and anti-patterns.

Analyze Azure resources and IaC files to identify cost optimization opportunities, calculate savings, and create GitHub issues for tracking.

Optimize SQL queries, indexes, and database performance across MySQL, PostgreSQL, SQL Server, and Oracle with execution plan analysis and universal tuning techniques.

Generate a complete MCP server project in Python with tools, resources, and proper configuration using uv and the MCP SDK.

Import existing Azure resources into Terraform using Azure CLI discovery and Azure Verified Modules (AVM).

Diagnoses and resolves slow Qdrant search performance issues including high latency, low throughput, and slow filtered searches.

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes in API designs, configuration schemas, and cryptographic library ergonomics.

Generates minimal macOS Seatbelt sandbox configurations to isolate and restrict applications with allowlist-based profiles.

Deploy and manage projects on Vercel using token-based authentication, without interactive login.

Validate a business idea using the minimalist entrepreneur framework before building anything.

Query blockchain data (balances, token prices, NFT ownership, transfer history, transaction simulation, gas estimates) across Ethereum, Base, Arbitrum, BNB, Polygon, Solana, and more via Alchemy's API, x402, or MPP protocols.

Migrate Mini Apps from MiniKit (OnchainKit) to native Farcaster SDK with async context patterns, hook-by-hook mappings, FrameProvider setup, and manifest configuration.

Integrate with EVM blockchains using viem and wagmi for wallet connection, contract reads/writes, event subscriptions, multicall, and multi-chain support.

Diagnoses and fixes failing installed skills by reading the SKILL.md and error output, classifying the failure, applying the smallest fix, and attaching a verification recipe.

Transforms technical git commits into polished, user-friendly changelogs by analyzing commit history, categorizing changes, and generating customer-ready release notes.

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

Automate Gender API operations through Composio's Gender API toolkit via Rube MCP, with tool discovery and connection management.

Automate Productlane tasks like issue management and feedback tracking through Composio's toolkit via Rube MCP.

Automate Countdown API operations through Composio's Countdown API toolkit via Rube MCP, with dynamic tool discovery and connection management.

Review and fix Swift Concurrency issues in Swift 6.2+ codebases by applying actor isolation, Sendable safety, and modern concurrency patterns with minimal behavior changes.

Extracts second-hand item search results from Goofish (闲鱼), China's largest second-hand marketplace. Input a keyword and optional sort/filter parameters to receive a list of item cards with ID, title, price, image, location, and want-count.

Collects tweets from an X (Twitter) user profile timeline by handle, supporting tweets, replies, or media-only modes, and returns structured data with engagement metrics and pagination.

Extracts structured news data from Google News via the BrowserAct API, including headlines, sources, publication times, and article links.

Extracts structured channel-level and video detail data from a YouTube channel via the BrowserAct API, including metrics like views, likes, comments, and subscriber count.

Collects every tweet in an X (Twitter) conversation thread given a conversation id, returning normalized per-tweet data with text, author, engagement counts, media, hashtags, mentions, and reply mapping.

Fetch Xiaohongshu (RedNote) note details and comments by note ID, returning title, description, author info, engagement stats, tags, and paginated comment list.

Searches Google to discover social media profiles associated with a person, brand, or username, returning platform name, profile URL, username, bio snippet, and follower count across multiple platforms.

Extracts structured video and comment data from YouTube using the BrowserAct API, enabling audience insight, content research, and competitive monitoring without CAPTCHA or IP restrictions.

Extracts YouTube influencer profiles including social links, subscriber counts, and channel stats via the BrowserAct API.

Extract structured best-selling product data from Amazon, including titles, prices, ratings, reviews, sales volume, and promotions, using the BrowserAct API.

Explain machine learning model predictions using SHAP values, compute feature importance, and generate visualizations including waterfall, beeswarm, bar, scatter, force, and heatmap plots.

Build and execute quantum circuits on IBM Quantum hardware, simulators, and third-party providers using the Qiskit framework.

Perform astronomical data analysis with Astropy: coordinate transformations, unit conversions, FITS I/O, cosmological calculations, time handling, table operations, and WCS transformations.

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Access large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

Execute cloud-native incident containment across AWS, Azure, and GCP by isolating compromised resources, revoking credentials, preserving forensic evidence, and applying security group restrictions to prevent lateral movement.

Apply foundational design principles—affordances, signifiers, constraints, mappings, and feedback—to evaluate and improve product usability, bridging the gulfs of execution and evaluation.

Automates PR review and CI auto-fix for GitHub and GitLab using the Composio CLI. Pulls diffs, fetches failing job logs, posts review comments, and loops fix commits until checks go green.

Build chat interfaces in React/Next.js with reusable components for messages, input, typing indicators, and avatars.

Generate videos using Pruna's optimized P-Video and WAN models via the inference.sh CLI, supporting text-to-video, image-to-video, audio input, and multiple resolutions.

Generate and edit videos using Alibaba HappyHorse 1.0 models via the inference.sh CLI, supporting text-to-video, image-to-video, reference-to-video, and video editing with natural language.

Generate and edit images using Alibaba Qwen-Image-2.0 models via the inference.sh CLI, with support for text-to-image, multi-image editing, and text rendering.

Generate images using Google Gemini 3.1 Flash Image Preview via the inference.sh CLI, with support for text-to-image, image editing, multi-image input, and Google Search grounding.

Research companies, industries, or competitor sets using web search and seven analytical lenses to produce structured intelligence for downstream product management tasks.

Create a customer journey map across stages, touchpoints, actions, emotions, and metrics to diagnose broken experiences and align teams on the full customer flow.

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.

Improves multi-step research reliability with structured protocols for source validation, error recovery, and transparent reasoning.

Build, deploy, and manage continuous AI agents using a visual workflow editor or development toolkit.