← Use cases · Coding agents & IDE assistants
AI agent tools for prompt engineering
Short answer: Our top pick for prompt engineering: ponytail, with the highest AgentPick Score (94/100) among tools tagged "prompt-engineering". Runners-up: caveman (92) and humanizer (82). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | ponytail | Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. | 94/100 | ★ 164k | MIT | 13 Oct 2026 |
| #2 | caveman | 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. | 92/100 | ★ 112k | Apache-2.0 | 14 Oct 2026 |
| #3 | humanizer | Agent skill that removes signs of AI-generated writing from text | 82/100 | ★ 57k | MIT | 28 Sept 2026 |
| #4 | academic-research-skills | Academic Research Skills for Claude Code: research → write → review → revise → finalize | 80/100 | ★ 52k | See repo | 13 Oct 2026 |
| #5 | unstract | LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows | 77/100 | ★ 7.3k | AGPL-3.0 | 14 Oct 2026 |
| #6 | avoid-ai-writing | Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Her… | 76/100 | ★ 5k | MIT | 13 Oct 2026 |
| #7 | apm | Agent Package Manager | 76/100 | ★ 4k | MIT | 14 Oct 2026 |
| #8 | repoprompt-ce | Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI. | 70/100 | ★ 959 | Apache-2.0 | 14 Oct 2026 |
| #9 | drama-skills | 开源 AI 短剧/漫剧创作 skill 合集：剧本、角色资产、分镜 storyboard、图片/视频提示词、审查，适配 Claude Code 与 Codex | Open-source AI short drama / micro-drama skills for Claude Code & Co… | 69/100 | ★ 2.9k | MIT | 14 Oct 2026 |
| #10 | MeiGen-AI-Design-MCP | Supports GPT Image 2, Seedance & ComfyUI, with a 1,400+ prompt library, carefully crafted hooks and a multi-task orchestration system | 69/100 | ★ 1.8k | MIT | 14 Oct 2026 |
| #11 | sepia | De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigr… | 68/100 | ★ 3.2k | MIT | 14 Oct 2026 |
| #12 | stylekit | Open-source visual style library for AI-generated UI — 148 curated styles with design tokens, prompts and MCP. | 面向 AI 生成网页的开源视觉风格库：148 套精选风格，支持 MCP、A… | 63/100 | ★ 607 | MIT | 14 Oct 2026 |
| #13 | OpenContracts | The open document intelligence platform for builders and hackers - DMS for the agentic world | 59/100 | ★ 1.5k | MIT | 13 Oct 2026 |
| #14 | agent-style | 21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro. | 52/100 | ★ 712 | See repo | 7 Oct 2026 |
| #15 | gateway | The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs. | 52/100 | ★ 607 | MIT | 29 Jul 2026 |
| #16 | agnosticui | AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, an… | 46/100 | ★ 828 | Apache-2.0 | 11 Oct 2026 |
| #17 | harmonist | Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies. | 44/100 | ★ 2.3k | MIT | 9 Jun 2026 |
| #18 | OpenAgentsControl | AI agent framework for plan-first development workflows with approval-based execution. Multi-language support (TypeScript, Python, Go, Rust) with auto… | 43/100 | ★ 4.9k | MIT | 13 Sept 2026 |
| #19 | agents-best-practices | Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design. | 41/100 | ★ 2.4k | MIT | 13 Oct 2026 |
| #20 | three-man-team | A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, … | 41/100 | ★ 953 | MIT | 9 Jun 2026 |
| #21 | unlazy | Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the who… | 39/100 | ★ 3.9k | MIT | 3 Sept 2026 |
| #22 | loopy | A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows. | 39/100 | ★ 3.2k | MIT | 11 Sept 2026 |
| #23 | nano-banana-pro-prompts-recommend-skill | AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample im… | 39/100 | ★ 1.9k | See repo | 14 Oct 2026 |
| #24 | designer-skills | Designer Skills Collection: agentic skills, commands, and plugins for design — from research to systems, UI, interaction, and delivery. | 36/100 | ★ 2.9k | MIT | 5 Sept 2026 |
| #25 | maestro | Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Cod… | 32/100 | ★ 591 | MIT | 29 Apr 2026 |
| #26 | agents-from-scratch | Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning. | 31/100 | ★ 1k | MIT | 25 Jul 2026 |
| #27 | harness-books | Harness engineering in two books: constraints, query loops, context governance and multi-agent verification in Claude Code and Codex. harness-books.ag… | 29/100 | ★ 3.2k | See repo | 19 Apr 2026 |
| #28 | ELI5 | ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the a… | 26/100 | ★ 1.7k | MIT | 18 Mar 2026 |
| #29 | claude-code-prompts | Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coor… | 26/100 | ★ 1.2k | MIT | 11 May 2026 |
| #30 | agentic-ai-prompt-research | Research into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classification | 19/100 | ★ 2.6k | See repo | 31 Mar 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Check which models and providers it supports.
- Prefer tools that show diffs and ask before running commands.
- Look for recent commits: coding agents change fast.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for agent skills →
Coding agents & IDE assistants
AI agent tools for developer tools →
Coding agents & IDE assistants
AI agent tools for the terminal →
Coding agents & IDE assistants
AI agent tools for macOS →
Coding agents & IDE assistants
AI agent tools for agent harnesses →
Coding agents & IDE assistants
AI agent tools for agent orchestration →
Coding agents & IDE assistants
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.