1,099 boosters for "pi" — open source, verified from GitHub, ready to install
1. Spec compliance first: Follow WHATWG HTML5 spec exactly. No heuristics, no shortcuts. 2. No exceptions in hot paths: Use deterministic control flow, not try/except for branching. 3. No reflective probing: No , , or - all data structures used are deterministic.
"name": "claude-blog", "description": "AI-powered blog skill suite with 30 sub-skills and 5 agents. FLOW framework integration (Find/Optimize/Win, 30 evidence-led prompts), semantic topic-cluster planning + execution, multilingual publishing (translate/localize/locale-audit), Google API integration
"name": "dotnet-skills", "description": "Comprehensive .NET development skills and agents for Claude Code - covering C#, F#, Akka.NET, Aspire, testing frameworks, and specialized tools", "name": "Aaron Stannard",
Halmos is a symbolic execution tool for EVM smart contracts that integrates with Copilot to help developers write and verify property-based tests in Solidity. It enables security-focused developers to automatically find bugs and verify contract correctness using SMT solvers.
"version": "0.25.0", "description": "Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.", "email": "support@datadoghq.com"
把一份 markdown 大纲（或 ）+ 一种视觉风格，直接喂给 OpenAI 官方 Images API（），逐页出图，最后打包成 16:9 .pptx。 所有可用风格都统一放在 下，使用方式完全相同。需要查看风格封面展示时，读取 。 直接给 skill 一个 .pptx 模板，后续所有页都仿这个模板。
Maintain consistent structure across all bot configuration files: Implement multiple exit strategy types: 1. Time-based: Hold for fixed duration
Use this before submission when the empirical story is not yet locked. FSE reviewers are SE empiricists; the evaluation is where a good idea is won or lost. The organizing principle is on subjects and baselines a skeptic would accept.
Heuristic scoring (no AI key configured).
Leverage strings with drizzle types, instead of enums: Only use varchar for ids, similiar to the users table. Otherwise use text. When creating a new table, leverage the id util
These instructions guide GitHub Copilot on how to generate and modify code for the project. State Machine Cat is a tool for visualizing state charts. It parses state machine descriptions and renders them as diagrams. Tests must be created for all new functionality using Mocha and Node's assert modu
A GitHub Copilot instruction set that standardizes CHANGELOG maintenance and Dart/Flutter API documentation for the shadcn/ui Flutter ecosystem. Developers benefit from deterministic, high-quality contribution guidelines that ensure consistency across the project.
  Awesome Claude Code plugins — a curated list of slash commands, subagents, MCP servers, and hooks for Claude Code
1. Vectorization discipline (from logo-vectorizer-minimal-smooth): fit the raster source with the lowest-complexity editable geometry that passes visual QA. 2. Motion discipline (from Disney's 12 Principles of Animation): choreograph that geometry into brand-appropriate motion with evidence-based ti
Use this skill to configure FreeTheAi for a user or another AI agent. FreeTheAi is an OpenAI-compatible gateway with one key, one base URL, and multiple public model aliases. 1. Send the user to . 2. Tell them to run in Discord and complete the modal.
在前端实现组件的时候，要设置合理的长宽，使得布局不臃肿也不拥挤，同时使用全局主题和全局样式，使用纯黑和纯白的组合，保持flutter现代和简洁的风格，尽量使用和创建全局通用组件，并添加相关的说明注释
This skill helps you systematically assess where Bitcoin sits in its market cycle — from extreme fear (accumulation opportunity) to extreme greed (distribution/exit signal). Through a weighted evaluation of 13 on-chain, sentiment, and market indicators, it produces a 0-100 Market Heat Score and acti
A Copilot instruction set that helps reviewers identify breaking API changes in the Microsoft Graph .NET SDK, preventing regressions when library updates occur. Developers and SDK maintainers benefit from automated detection of non-additive signature changes.
You are a senior product designer who creates design language specifications for AI coding assistants (Claude Code, Codex, and compatible tools). You don't design interfaces — you design the system that designs interfaces. Every skill you generate must be opinionated enough that two different sessio
A deduplication skill that intelligently groups and selects canonical versions of duplicate events across multiple data sources using reputation scoring and hash-based matching. Ideal for developers building data aggregation systems, search engines, or multi-source content platforms.
This repository is the reference implementation for the Azure Kubernetes Service (AKS) baseline cluster architecture from Azure Architecture Center. It demonstrates the minimum recommended baseline for most AKS clusters and serves as the starting point for architectural conversations. Adapt it to yo
"description": "Durable, fully-local project memory for Claude Code. Logs every session to .recall/history.md and condenses it into .recall/context.md with a local Python summarizer (TF-IDF + TextRank) — no API key, no external model, nothing leaves your machine. New sessions resume from the saved c
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. FPP (Falcon Player) is a lightweight, optimized sequence player for LED lighting control, designed for Raspberry Pi and BeagleBone SBCs. It speaks E1.31, DDP, DMX, ArtNet, KiNet, Pixelnet, and Rena
Cursor Rules for Metriport provides TypeScript and architectural best practices for developers building with Metriport's healthcare data API, ensuring HIPAA-compliant, maintainable code through enforced naming conventions, functional programming patterns, and code organization standards.
