Topic · AI & LLM Engineering
Best prompt engineering skills for Claude Code, Codex and other agents.
- skills
- 350
- official
- 19
Prompt engineering skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design. | anthropics/ | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Turns a rough idea into one ready-to-paste prompt tuned for a specific AI tool such as an LLM, Cursor, Midjourney or a video model. | nidhinjs/ | 14k | 1 repo | ~8k | Automated safety check: Pass | MIT | 1 mo ago |
| 3 | Reference of Claude API examples and guides covering tool use, vision, RAG, classification, summarization, text-to-SQL, prompt caching and agent patterns. | 2025Emma/ | 23k | 1 repo | ~2.2k | Automated safety check: Pass | MIT | 9 mo ago |
| 4 | This skill enriches vague prompts with targeted research and clarification before execution. | severity1/ | 1.9k | 2 repos | ~1.7k | Automated safety check: Pass | MIT | 6 days ago |
| 5 | A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and… | danyuchn/ | 3.9k | — | ~4.1k | Automated safety check: Pass | MIT | 3 days ago |
| 6 | Routes Seedance 2.0 video work across Dreamina, API and router surfaces, covering prompts, reference handling, audio and lip-sync, pricing and model-ID questions. | Emily2040/ | 7.5k | 1 repo | ~7.4k | Automated safety check: Pass | MIT | 4 days ago |
| 7 | Rewrites Seedance 2.0 video prompts that name characters, brands, celebrities, songs or real people into original, rights-safe versions that keep the creative intent. | Emily2040/ | 7.5k | 1 repo | ~930 | Automated safety check: Pass | MIT | 4 days ago |
| 8 | A skill your agent uses when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. | DenisSergeevitch/ | 2.4k | — | ~7.4k | Automated safety check: Pass | MIT | 2 days ago |
| 9 | Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. | ynulihao/ | 617 | 14 repos | ~1.7k | Automated safety check: Pass | No licence | 7 mo ago |
| 10 | Create and register new patches for tweakcc. An agent skill from Piebald-AI/tweakcc. | Piebald-AI/ | 2.5k | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 11 | Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop. | aiming-lab/ | 15k | — | ~1.8k | Automated safety check: Pass | MIT | 1 mo ago |
| 12 | Analyzes a reference image and writes a prompt that could recreate it in an AI image generator, focusing on the visual traits that most affect similarity. | wuyoscar/ | 5.6k | — | ~1.8k | Automated safety check: Pass | MIT | 7 days ago |
| 13 | Provides Japanese prompt patterns and safe example rewrites for Seedance 2.0 video generation, with reference tags kept intact and each example labeled by risk. | Emily2040/ | 7.5k | 1 repo | ~898 | Automated safety check: Pass | MIT | 4 days ago |
| 14 | Analyzes and improves prompts using 31 frameworks across 7 intent categories. | ckelsoe/ | 310 | 1 repo | ~6.9k | Automated safety check: Pass | MIT | 2 mo ago |
| 15 | Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. | MoizIbnYousaf/ | 1.1k | 2 repos | ~1.3k | Automated safety check: Pass | MIT | 16 days ago |
| 16 | Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems. | maslennikov-ig/ | 259 | 4 repos | ~1.4k | Automated safety check: Pass | Unknown | 7 mo ago |
| 17 | Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template. | krusemediallc/ | 1.6k | — | ~4.2k | Automated safety check: Pass | MIT | 15 days ago |
| 18 | Korean-language prompt patterns for Seedance 2.0 video generation, each labeled as safe, needing an owned reference, or requiring a rewrite. | Emily2040/ | 7.5k | 1 repo | ~942 | Automated safety check: Pass | MIT | 4 days ago |
| 19 | Model-agnostic workflow for AI image and video projects: prompt writing, tracking of assets and shots, continuity checks and diagnosis of failed generations. | renmu2017/ | 224 | — | ~1.8k | Automated safety check: Pass | MIT | 13 days ago |
| 20 | Adding a Community Agent Skill: a Markdown attack-workflow file that users import from the catalog, which then competes in the Intent Router and is injected into the agent's system prompt. | samugit83/ | 2.9k | — | ~775 | Automated safety check: Pass | MIT | 2 days ago |
| 21 | Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research. | lingbol088-spec/ | 222 | — | ~1.8k | Automated safety check: Pass | MIT | 2 mo ago |
| 22 | 22.Codex Fable5 Apply a Claude Fable 5 inspired operating style inside Codex. | baskduf/ | 437 | — | ~1.6k | Automated safety check: Pass | AGPL-3.0 | 2 mo ago |
| 23 | 23.Talk Normal Installs an always-on set of rules into your agent's workspace config that cuts filler, hedging and padded closings from its replies. | hexiecs/ | 1.9k | — | ~784 | Automated safety check: Pass | MIT | 5 mo ago |
| 24 | Supplies Chinese example prompts for Seedance 2.0 video generation, labeled by safety, with notes on rewriting prompts that name protected people or brands. | Emily2040/ | 7.5k | 1 repo | ~862 | Automated safety check: Pass | MIT | 4 days ago |
| 25 | Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts. | wshobson/ | 40k | — | ~1.3k | Automated safety check: Pass | MIT | 2 days ago |
| 26 | This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to… | pnp/ | 891 | — | ~2.6k | Automated safety check: Pass | MIT | yesterday |
| 27 | Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation. | breaking-brake/ | 5.4k | — | ~1.3k | Automated safety check: Pass | Unknown | today |
| 28 | Universal quality bar and final audit rubric for any agent system prompt. | mastra-ai/ | 29k | — | ~2k | Automated safety check: Pass | Unknown | today |
| 29 | 29.Talk Normal Installs a set of rules into AGENTS.md that strips filler, hedging and padded closings from your agent's replies, in English and Chinese. | hexiecs/ | 1.9k | — | ~931 | Automated safety check: Pass | MIT | 5 mo ago |
| 30 | Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. | SalesforceAIResearch/ | 112 | 1 repo | ~7.4k | Automated safety check: Pass | Unknown | 24 days ago |
| 31 | Write and run custom Pi prompt templates (slash commands) for this extension. | nicobailon/ | 321 | — | ~1.3k | Automated safety check: Pass | MIT | 16 days ago |
| 32 | Lays out a minimal, iteration-first approach to writing system prompts for LLM agents, with model-specific notes for Claude, GPT, Gemini, and Codex. | cashew-labs/ | 904 | — | ~570 | Automated safety check: Pass | MIT | 1 mo ago |
| 33 | Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. | kayba-ai/ | 2.6k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 34 | 34.Lintlang A skill your agent uses when writing or reviewing AI agent configs, system prompts, or tool definitions (JSON/YAML/Python) and you need to catch ambiguous tool descriptions, missing stop conditions… | hermes-labs-ai/ | 137 | 1 repo | ~719 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 35 | Turns a vague video idea into a seven-section prompt that reads like real home-video, phone, DV or surveillance footage, with checks against an AI-look checklist. | zhouwei713/ | 326 | — | ~749 | Automated safety check: Pass | MIT | 2 mo ago |
| 36 | Inspect or modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, agent secrets, and local runtime settings. | letta-ai/ | 3.5k | — | ~7k | Automated safety check: Pass | MIT | today |
| 37 | Writes, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes. | gnipbao/ | 142 | — | ~662 | Automated safety check: Pass | MIT | 24 days ago |
| 38 | Defines practical standards for implementation-focused coding agents. | repowise-dev/ | 1.2k | — | ~296 | Automated safety check: Pass | MIT | 4 mo ago |
| 39 | Audit an agent's context layout against the four places: system prompt, tools, history, tail. | undefined-ui/ | 999 | — | ~810 | Automated safety check: Pass | MIT | 8 days ago |
| 40 | Build complete, working voice agent applications using the gradbot framework. | gradium-ai/ | 126 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | 18 days ago |
| 41 | 41.Create Task Create an end-to-end Continual Learning Bench task. An agent skill from melandlabs/openloomi. | melandlabs/ | 1k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 42 | Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition)… | kingbootoshi/ | 143 | — | ~2.3k | Automated safety check: Pass | MIT | 4 mo ago |
| 43 | Generates or edits images with GPT Image 2 through an OpenAI-compatible API, or falls back to writing finished prompts from a library of structured templates. | ConardLi/ | 13k | — | ~4k | Automated safety check: Notes | MIT | 2 mo ago |
| 44 | Plans, writes prompts for, renders and audits academic figures from repos, papers or notes, with an option to turn rendered text into editable PowerPoint. | Azhi-ss/ | 145 | — | ~5k | Automated safety check: Pass | MIT | yesterday |
| 45 | This skill should be used when the user asks to "create an agent instruction", "add agent instructions", "scaffold an agent sample", "create a system prompt sample", "add a system prompt", "create a… | pnp/ | 891 | — | ~3.1k | Automated safety check: Pass | MIT | yesterday |
| 46 | Rewrites Seedance 2.0 video prompts to replace filler, hollow superlatives and vague cinematic wording with production-specific detail while keeping the user's style. | Emily2040/ | 7.5k | 1 repo | ~1.1k | Automated safety check: Pass | MIT | 4 days ago |
| 47 | Audit a named AI agent config, system prompt, tool-definition or instruction file (YAML, JSON, Markdown, text, or Python) with the released LintLang CLI, on request. | hermes-labs-ai/ | 137 | 1 repo | ~1.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 48 | 48.Qwen Edit AI image editing prompting patterns for Qwen-Image-Edit. An agent skill from digitalsamba/claude-code-video-toolkit. | digitalsamba/ | 2.2k | 1 repo | ~711 | Automated safety check: Pass | MIT | 2 days ago |
Questions, answered from the data.
What is the best prompt engineering skill?
Claude Code Agent Development (official) from anthropics/claude-plugins-official ranks first of the 350 prompt engineering skills listed here, with the highest score: its repository has 37k GitHub stars, 8 other GitHub owners carry a copy, its SKILL.md loads about 2.8k tokens and it passes the automated safety check with no findings. Next come Prompt Master and Claude Cookbooks Reference.
Which prompt engineering skills are official?
19 of the 350 prompt engineering skills are official, published by the vendor's own GitHub organization: Claude Code Agent Development, Microsoft Foundry, Canvas Templates, Respond To PR Comments, Hcls Build Agent and 14 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.
Explore related skills
Category
More topics in AI & LLM Engineering
- Building AI agents525
- Deep learning408
- Embeddings381
- LLM inference and serving364
- Retrieval-augmented generation360
- Fine-tuning313
- LLM evaluation303
- Speech recognition and synthesis272
- Structured output and tool calling271
- LLM cost and token optimization256
- LLM API integration218
- LLM observability217
- Model routing and gateways217
- LLM guardrails208
- Computer vision206
- Model hubs and datasets180
- GPU and accelerator computing171
- Diffusion and image models167
- Natural language processing141
- Reinforcement learning67
- AI interpretability23