
Improve AI application with evaluation-driven development
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling

Improve AI application with evaluation-driven development

Generate Excalidraw diagrams from natural language descriptions


Build agentic solutions on Microsoft Foundry, GitHub and Azure: hosted agents, toolbox tools and skills, Foundry IQ grounding and a React/Fa

Use this skill when a user needs a screenshot, website thumbnail, full-page capture, or PDF of a public HTTP(S) webpage saved as a local art

Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10

Export Markdown containing Mermaid code fences to Word (.docx) with embedded SVG diagrams and PNG fallbacks

Convert Markdown files to professionally formatted Word (.docx) documents with embedded PNG images — pure JavaScript, no external tools requ

Prepare, validate, submit, and monitor Windows desktop apps in Microsoft Partner Center

A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph

Manage DNS records for domains registered with Namecheap via their API

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model

Saves cloud-model context by briefing one bounded, read-heavy sub-task (more than about 25 KB of prose, or many files that no single command

capability to parse Simplicité logs from a raw `.txt` file, filter fields to reduce noise, and output the result as structured JSON.

Mistake-proof code so misuse cannot be expressed, rather than warning against it

Open a GitHub PR dashboard in the browser


End-to-end skill for building, testing, linting, versioning, and publishing a production-grade Python library to PyPI

Run a complete quality engineering audit on any codebase

Install npm packages in a Docker sandbox environment

Use when a developer wants to find the best GitHub issues to contribute to in a repository

Audit a skill collection before release or investigate installer omissions, archived/template leakage, duplicate identities, and manifest dr

Convert text, markdown, or a summary produced by another skill into a listenable MP3 using local CPU-only neural text-to-speech

Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, r

Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attribut

WebMCP agent skill for curated core coverage or route-by-route parity — inventory an existing web app, integrate approved tools, then inspec


Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase

Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps