Topic · AI & LLM Engineering
Best prompt engineering skills, page 3
Prompt engineering skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 97 | Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. | YYH211/ | 282 | 2 repos | ~1k | Automated safety check: Pass | MIT | 4 mo ago |
| 98 | Writes one image prompt for a 16:9 character reference sheet, with three full-body views and a face close-up, so a character stays consistent across AI video clips. | Rylaispirit/ | 146 | — | ~941 | Automated safety check: Pass | MIT | 11 days ago |
| 99 | 99.Lintlang Lint AI agent instruction files (SKILL.md, CLAUDE.md, AGENTS.md, GEMINI.md), tool definitions, system prompts, and agent configs with the deterministic LintLang CLI. | hermes-labs-ai/ | 137 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 100 | 100.Skill Creator Creates high-quality Claude Code and Cowork skills using evidence-based principles: expert vocabulary payloads for knowledge routing, dual-register descriptions for reliable triggering, named… | jdforsythe/ | 151 | — | ~4.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 101 | Writes one model-agnostic video prompt spec, then compiles it for whichever video model you can call, rewriting vague intent into results you can check in the output. | AtlasCloudAI/ | 228 | — | ~2.6k | Automated safety check: Pass | Unknown | today |
| 102 | 102.System Prompt Edit or improve the AI system prompt used in DBX Studio's AI chat. | Dbxstudio/ | 103 | 1 repo | ~773 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 103 | Build, test and autonomously improve CodeMie platform assistants. | codemie-ai/ | 294 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 104 | 104.Add Prompt Scaffold a new MCP prompt template. An agent skill from cyanheads/pubmed-mcp-server. | cyanheads/ | 155 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 105 | Tulis dan sunting teks Bahasa Indonesia agar jelas, spesifik, alami untuk audiensnya, dan sesuai suara yang diminta. | adenaufal/ | 145 | — | ~9.4k | Automated safety check: Pass | MIT | 11 days ago |
| 106 | 106.Prompt Engineer A skill your agent uses when the user asks to improve, optimize, rewrite, debug, or shorten a prompt, or asks why a prompt is producing bad output. | aakashg/ | 112 | — | ~2.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 107 | 107.Prompt Writer Methodology for writing or improving prompts and system prompts that drive any LLM. | hAcKlyc/ | 918 | — | ~2.2k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 108 | 108.Lintlang Audit Audit a named AI agent config, system prompt, tool definition, or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI in GitHub Copilot CLI. | hermes-labs-ai/ | 137 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 109 | Implements business-facing LLM calls as explicit, traceable workflows, keeping prompt versions, model policy, structured output and tracing scenarios in separate places. | lobehub/ | 83k | — | ~1.1k | Automated safety check: Pass | Unknown | today |
| 110 | Review the quality of an agent's tool descriptions, system/agent prompts, or SKILL.md files against current agent-engineering best practices. | microsoft/ | 157 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 111 | Ingest the official MITRE CWE database and generate per-domain security audit taxonomies for PromptKit. | microsoft/ | 110 | — | ~356 | Automated safety check: Pass | MIT | 20 days ago |
| 112 | 112.Prompt Optimizer Analyze draft prompts, detect intent and missing context, match ECC commands, skills, and agents, and output a ready-to-paste optimized prompt with diagnosis and rationale — advisory only, never… | affaan-m/ | 275k | 5 repos | ~3.8k | Automated safety check: Pass | MIT | 3 days ago |
| 113 | 仅在即将调用图片、视频或音乐生成模型时使用。负责把已定稿的 directorplan、剧本文字和终版参考资产编译成“本次调用”的完整生成要求并做调用前自检;不负责重新规划剧情、补发明资产、调用工具或审查生成结果。 | wangzai-double-milk/ | 163 | — | ~710 | Automated safety check: Pass | MIT | 2 mo ago |
| 114 | A skill your agent uses when building custom Kiro AI agents or when user asks for agent configurations - provides JSON structure, tool configuration, prompt patterns, and security best practices for… | pr-pm/ | 122 | 1 repo | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 115 | A skill your agent uses for translation, polishing, or de-AI-ification of academic text - provides ready-to-use prompt templates | Norman-bury/ | 3.4k | — | ~1k | Automated safety check: Pass | MIT | 4 mo ago |
| 116 | 116.Sap AI Core Guides development with SAP AI Core and SAP AI Launchpad for enterprise AI/ML workloads on SAP BTP. | secondsky/ | 462 | — | ~3.3k | Automated safety check: Pass | GPL-3.0 | 3 days ago |
| 117 | Expert guide on prompt engineering patterns, best practices, and optimization techniques. | davila7/ | 32k | 8 repos | ~1.4k | Automated safety check: Pass | MIT | today |
| 118 | 118.Prompt Library Curated collection of high-quality prompts for various use cases. | davila7/ | 32k | 8 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 119 | 119.Opik Optimize Improve a prompt with the Opik Agent Optimizer — resolve the prompt, a dataset, and a metric, pick the algorithm, run a bounded optimization, check the gain on held-out data, and save the winner as… | comet-ml/ | 219 | — | ~2.6k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 120 | Explains how to create Claude Code agents: file structure, YAML frontmatter fields, trigger descriptions with examples, model and color options, and system prompt design. | Galaxy-Dawn/ | 5.7k | 1 repo | ~2.6k | Automated safety check: Pass | MIT | 15 days ago |
| 121 | Writes fictional, non-graphic rescue scenes for MiniMax H3 with an external cinematic camera, a visible rescuer, Mandarin dialogue and shot-by-shot direction. | karuvanan/ | 131 | — | ~1.7k | Automated safety check: Pass | Unknown | 22 days ago |
| 122 | PromptKit composition engine. An agent skill from microsoft/PromptKit. | microsoft/ | 110 | — | ~420 | Automated safety check: Pass | MIT | 20 days ago |
| 123 | A skill your agent uses when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. | rrezartprebreza/ | 298 | 1 repo | ~2.1k | Automated safety check: Pass | MIT | 17 days ago |
| 124 | 124.Natural Render the provided prompt template with Jinja context and send it to the active NPC's LLM. | NPC-Worldwide/ | 1.5k | — | ~161 | Automated safety check: Pass | MIT | 2 days ago |
| 125 | 125.Module 1 This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g. | brevdev/ | 144 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 126 | Diagnose and fix retention problems using behavior design (B=MAP). | wondelai/ | 2.4k | — | ~3.8k | Automated safety check: Pass | MIT | 27 days ago |
| 127 | 127.Prompt Authoring Create or improve Agent Deck/Pi prompt templates for reusable parent-session workflows. | a-streetcoder/ | 118 | — | ~721 | Automated safety check: Pass | MIT | 2 mo ago |
| 128 | Helps write and debug prompts for ByteDance Seedance video models, with labelled multimodal references and fixes for drift, subtitles and duplicated characters. | SlavaSexton/ | 105 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 129 | Crafting examples that steer AI behavior effectively. An agent skill from Owl-Listener/ai-design-skills. | Owl-Listener/ | 181 | — | ~723 | Automated safety check: Pass | MIT | 4 mo ago |
| 130 | Prompt Engineering Patterns workflow skill. An agent skill from diegosouzapw/awesome-omni-skills. | diegosouzapw/ | 159 | — | ~3.4k | Automated safety check: Pass | MIT | 3 mo ago |
| 131 | 131.Prompt Engine Ultimate AI prompt database and builder with 2,500+ curated prompts across 19 categories and 17 AI models (Midjourney, Flux, Leonardo AI, DALL-E, Sora, Imagen, Mystic, Stable Diffusion, Ideogram… | AgriciDaniel/ | 110 | — | ~1.2k | Automated safety check: Pass | MIT | 6 mo ago |
| 132 | 132.Tool Creator 把用户的可复用需求封装成标准化的 Agent-CLI 工具,并用 myagents tool add 注册进 MyAgents 工具注册表——注册后所有未来会话(builtin / DSH / Claude Code / Codex 全 runtime)的 AI 都会在 system prompt 里自动发现它。触发场景:(1) 用户说「把 XX… | hAcKlyc/ | 918 | — | ~1.5k | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 133 | 133.Refine Prompt Refine and improve a user-supplied prompt for maximum clarity and effectiveness using prompt-engineering best practices and Penpot project context. | penpot/ | 61k | — | ~1.6k | Automated safety check: Pass | MPL-2.0 | today |
| 134 | A skill your agent uses when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. | rrezartprebreza/ | 298 | 1 repo | ~2.5k | Automated safety check: Pass | MIT | 17 days ago |
| 135 | A skill your agent uses for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization. | OmidZamani/ | 124 | 1 repo | ~1.3k | Automated safety check: Pass | MIT | 3 mo ago |
| 136 | Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. | davila7/ | 32k | 5 repos | ~1.7k | Automated safety check: Pass | MIT | today |
| 137 | 137.Module 1 This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g. | brevdev/ | 144 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 138 | 138.Prompt Patterns Practical prompt patterns and techniques for effective Claude Code usage. | cloudnative-co/ | 152 | — | ~887 | Automated safety check: Pass | MIT | today |
| 139 | Guide for customizing OhMyCode's AI personality and behavior via system prompt. | AlphaLab-USTC/ | 131 | — | ~819 | Automated safety check: Pass | MIT | 6 mo ago |
| 140 | Review the Huabu operate agent's three steering artifacts at their fixed repo locations — system prompt, tool descriptions, and skills. | microsoft/ | 157 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 141 | 141.Add Domain Manage knowledge domains (e.g., Medical, Finance). An agent skill from FabioYanezRomero/Knowledge-Graph-Builder. | FabioYanezRomero/ | 103 | — | ~3.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 142 | Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude… | AI-Builder-Club/ | 1.3k | — | ~2.2k | Automated safety check: Pass | No licence | 22 days ago |
| 143 | Prompt Engineering Patterns workflow skill. An agent skill from diegosouzapw/awesome-omni-skills. | diegosouzapw/ | 159 | — | ~4k | Automated safety check: Pass | MIT | 3 mo ago |
| 144 | 144.Benchmark Loop Fully automated self-improving loop — takes a project prompt, designs a team, runs the benchmark, analyzes results, optimizes framework code, rebuilds, and repeats until target grade is reached. | 0x0funky/ | 195 | — | ~5.3k | Automated safety check: Warn | MIT | 6 mo ago |
Explore related skills
Category
More topics in AI & LLM Engineering
- Building AI agents563
- Deep learning415
- Embeddings386
- LLM inference and serving372
- Retrieval-augmented generation358
- Fine-tuning309
- LLM evaluation308
- Speech recognition and synthesis308
- Structured output and tool calling276
- LLM cost and token optimization259
- LLM API integration255
- Model routing and gateways255
- LLM observability240
- LLM guardrails221
- Computer vision203
- Model hubs and datasets180
- GPU and accelerator computing176
- Diffusion and image models166
- Natural language processing131
- Reinforcement learning66
- AI interpretability23