prompts — open-source software health

npm

97Exceptionalhealth index

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.

TypeScript★ 25.2K↓ 2.6M/moSep 16, 2026

MITSep 16, 2026 · metrics 2.10.0

npm

96Exceptionalhealth index

bombshell-dev/clack

Effortlessly build beautiful command-line apps

TypeScript★ 8,058↓ 161M/moSep 17, 2026

Custom licenseSep 17, 2026 · metrics 2.10.0

npm

94Exceptionalhealth index

SBoudrias/Inquirer.js

A collection of common interactive command line user interfaces.

TypeScript★ 21.6K↓ 1B/moSep 16, 2026

MITSep 16, 2026 · metrics 2.10.0

npm

89Excellenthealth index

CodesWhat/portkey-admin-mcp

Portkey Admin API control-plane MCP server with Prisma AIRS interoperability guidance

TypeScript★ 6↓ 2,803/moSep 10, 2026

MITSep 10, 2026 · metrics 2.10.0

npm · PyPI

88Excellenthealth index

mohitagw15856/pm-claude-skills

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-claude-skills add.

HTML · JavaScript · Python★ 1,471↓ 15.5K/moOct 20, 2026

MITOct 20, 2026 · metrics 2.10.0

npm · PyPI

87Excellenthealth index

dynatrace-oss/dt-evals

AI evaluators CLI for your AI apps and Agents - Dynatrace AI Observability

TypeScript★ 51↓ 14.7K/moOct 8, 2026

Apache-2.0Oct 8, 2026 · metrics 2.10.0

npm

80Excellenthealth index

jnMetaCode/agency-agents-zh

🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。

Shell · PowerShell★ 20.7K↓ 3,390/moSep 16, 2026

MITSep 16, 2026 · metrics 2.10.0

npm

78Goodhealth index

sscodeai/agency-agents-ja

323個の即戦力AI専門エージェント — Claude Code/Cursor/Copilot等に対応。SIer/受託開発/SaaS/製造DX/公共分野など日本市場向け114個のオリジナルを含む、agency-agents日本語コミュニティ版

Shell · JavaScript · Python★ 5↓ 9,630/moSep 15, 2026

MITSep 15, 2026 · metrics 2.10.0

npm

78Goodhealth index

stacksjs/clapp

⌘ A modern framework to build powerful & pretty CLI applications.

TypeScript · Zig★ 14↓ 298.8K/moSep 14, 2026

MITSep 14, 2026 · metrics 2.10.0

Packagist

77Goodhealth index

promptphp/deck

A Laravel package for versioned AI prompt management with variable interpolation, performance tracking & A/B testing.

PHP★ 110↓ 3,779/moSep 12, 2026

MITSep 12, 2026 · metrics 2.10.0

crates.io · npm

73Goodhealth index

Dicklesworthstone/charmed_rust

Rust port of the Charm ecosystem (Bubble Tea, Lip Gloss, Bubbles, Wish): Elm-architecture TUIs, CSS-like terminal styling, and SSH app framework

Rust★ 40↓ 40.3K/moOct 21, 2026

Custom licenseOct 21, 2026 · metrics 2.10.0

npm

73Goodhealth index

Texarkanine/inquirerjs-checkbox-search

Filterable multi-select prompt for Inquirer.js

TypeScript · Python★ 1↓ 1,732/moOct 20, 2026

Custom licenseOct 20, 2026 · metrics 2.10.0

npm

73Goodhealth index

rockbenben/ChatGPT-Shortcut

Stop writing prompts from scratch — a searchable prompt library for ChatGPT, Claude, Gemini and Cursor · Русский 한국어 العربية हिन्दी ไทย ｜别再从头写提示词：现成的拿来就用，好用的收进自己的库

TypeScript · JavaScript★ 8,726Aug 28, 2026

MITAug 28, 2026 · metrics 2.10.0

npm

73Goodhealth index

zigrivers/scaffold

A TypeScript CLI that assembles AI-powered prompts at runtime to guide you from "I have an idea" to working software. Scaffold walks you through 54 structured pipeline steps — organized into 15 phases — and Codex, Claude Code, or Gemini handles the research, planning, and implementation for you.

TypeScript · HTML★ 6↓ 1,098/moSep 10, 2026

MITSep 10, 2026 · metrics 2.10.0

npm

71Goodhealth index

CyberCraftBD/power-seo

Power-SEO: AI-powered, enterprise-grade SEO toolkit for React - A modern & best alternative to Yoast, RankMath & AIOSEO for SPA and SSR applications.

TypeScript★ 16↓ 5,250/moOct 19, 2026

MITOct 19, 2026 · metrics 2.10.0

—

71Goodhealth index

c4spar/cliffy

A TypeScript-first, runtime-agnostic command-line toolkit for Deno, Node.js and Bun: featuring a command framework, argument parser, interactive prompts, tables, ANSI utilities, and more.

TypeScript★ 1,179Sep 20, 2026

MITSep 20, 2026 · metrics 2.10.0

67Goodhealth index

maxrodrigo/clai

AI for the Command Line

Go★ 3Sep 8, 2026

MITSep 8, 2026 · metrics 2.10.0

PyPI · npm

67Goodhealth index

ruinosus/dna

DNA — Domain Notation of Anything. A typed, declarative notation for agentic behavior: Kubernetes CRDs, but for agents, skills, souls and protocols.

Python★ 0↓ 5,319/moSep 11, 2026

MITSep 11, 2026 · metrics 2.10.0

PyPI

67Goodhealth index

snoodleboot-io/prompticorn

No repository description published.

Python★ 2↓ 2,479/moSep 14, 2026

No licenseSep 14, 2026 · metrics 2.10.0

npm · Go · crates.io

67Goodhealth index

use-crux/crux

Typed building blocks for everything around your LLM call.

TypeScript · Go★ 0↓ 4,924/moSep 18, 2026

Apache-2.0Sep 18, 2026 · metrics 2.10.0

PyPI

60Moderatehealth index

05satyam/instruct_vault

Git-native prompt linting, testing, versioning, and CI—without a hosted prompt registry.

Python★ 5↓ 91/moOct 18, 2026

Custom licenseOct 18, 2026 · metrics 2.10.0

Go · npm

59Moderatehealth index

Halleck45/promptcc

Cyclomatic complexity, but for LLM prompts. Static analysis that finds the business logic hidden in your prompts, scores it, and gates it in CI. Python, TypeScript, JavaScript, PHP.

Go · HTML★ 12Sep 19, 2026

MITSep 19, 2026 · metrics 2.10.0

PyPI · crates.io · Go +1

57Moderatehealth index