search
Search claims and sources using natural language queries. Use when looking for related claims or finding existing analysis.
Discover Testing & security skills, compare source repositories and read the instructions for each workflow.
Search claims and sources using natural language queries. Use when looking for related claims or finding existing analysis.
Mutation testing patterns for JavaScript and TypeScript using Stryker. Use when analyzing JavaScript/TypeScript branch code to find weak or missing tests, verifying test effectiveness in JS/TS projects, or stre...
Iteratively optimize prompt files against AgentV evaluation datasets by analyzing failures and refining instructions.
Mutation testing patterns for Python using mutmut. Use when analyzing Python code to find weak or missing tests, verifying pytest effectiveness, strengthening Python test suites, or validating TDD workflows in...
Analyze and improve test code quality using Kent Beck's Test Desiderata framework. Use when analyzing test files, reviewing test code, identifying test quality issues, suggesting test improvements, or when aske...
Phase DEBRIEF - Tests + QA + Release
Default behavior pattern that automatically delegates implementation tasks to specialized sub-agents while keeping the main conversation focused on architecture, design, and strategy. Use when receiving ANY imp...
Generate LLM skills from documentation, codebases, and GitHub repositories
Local tool system for API integrations and automation. Use when connecting to external services, fetching data from APIs, or performing tasks that require credentials or network access.
Tinybird Code agent tools and prompts for working with Tinybird projects, datafiles, queries, deployments, and tests.
This skill should be used when the user asks to "build a Solana program", "write Anchor code", "create a PDA", "work with SPL tokens", "test with anchor-bankrun", "fuzz test with Trident", "secure my Solana pro...
Copy the last assistant response as markdown to the clipboard
Generate videos using Google Veo models via the nano-banana CLI. Use this skill when the user asks to create, generate, animate, or produce videos with AI. Supports text-to-video, image-to-video animation, dial...
Generate and edit images using Google Gemini image models. Use this skill when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-i...
Typst 学术论文助手(支持中英文论文、会议/期刊投稿)。 领域:深度学习、时间序列、工业控制、计算机科学。 触发词(可独立调用任意模块): - "compile", "编译", "typst compile" → 编译模块 - "format", "格式检查", "li...
Creates and updates Claude Code skills following best practices. Guides through requirements gathering, design, content generation, and validation. Handles both new skill creation and refactoring existing skill...
Extract comment locations from code files for analysis. Use when cleaning comments, auditing code documentation, or analyzing comment patterns. Supports Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, Ru...
Write maximally terse agent prompts from scratch. Use when creating new agent specs, command prompts, or instruction sets. Teaches structure-first composition with compression-by-default patterns.
Create, validate, and troubleshoot Mermaid.js diagrams. Use when generating flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, state diagrams, or any visualization. Handles diagram valida...
Isolated git worktree workflow for coding agents. Handles worktree creation, atomic commits, branch publishing, optional PR creation, and cleanup. Use when implementing code changes that need branch isolation....
Generate browser-viewable HTML previews from markdown, plain text, and Mermaid diagrams. Auto-validates diagrams, applies professional styling, and opens in default browser. Use when agents need to preview docu...
Provides reusable templates for generating comprehensive codebase knowledge bases including architecture diagrams, concept maps, and module documentation. Supports both single-project and monorepo structures. U...
A sample skill for testing - must be at least 20 characters
Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-adviso...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.