Prompt Engineering skills for Claude Code and Codex
Skills that write, refine, test and manage prompts: system prompt creators, prompt optimizers, prompt engineering guides for agents and subagents, trace-driven optimization on Arize, managed prompts on Google's Agent Platform, and model-specific prompt craft for image and video models on fal.ai and Replicate. They give an agent a repeatable method for turning a rough request into a prompt that holds up.
Highest-scoring prompt engineering skills in the October 22, 2026 snapshot: emblem-ai-prompt-examples from EmblemCompany/Agent-skills (81/100), prompt-optimizer from getsentry/skills (81/100) and optimize-agent-prompt from browserbase/skills (81/100). Scores come from the Suede Skill Check.
- 28 listed skills
- 19 repositories
- 7 with full pages
18 from official publishers. 3 bundle scripts. 1 connect to an outside service. Listed in AI Agents and LLM Engineering (20), Video, Image, Audio and Creative (4), Security (2), Business, Sales and Finance (1), Frontend and Design (1).
All 28 prompt engineering skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| emblem-ai-prompt-examples 81/100 · B | EmblemCompany/Agent-skills | Provides example prompts for EmblemAI tasks such as research, portfolio review, quote requests, NFT discovery, and prediction-market analysis, with explicit confirmation before value-moving actions. |
| optimize-agent-prompt 81/100 · B | browserbase/skills | Builds and improves Browserbase Agent API demos by running a fixed task, collecting logs, scoring results, revising one system-prompt heuristic, and confirming convergence. |
| prompt-images 72/100 · C | replicate/skills | Teaches prompting techniques for AI image generation and editing models on Replicate, for writing prompts or building image generation features. |
| prompt-optimizer 81/100 · B | getsentry/skills | Creates and refines agent, system, and developer prompts and reusable prompt templates, including porting prompts between OpenAI, Claude, and Gemini and building prompt evals. |
| prompt-videos 70/100 · C | replicate/skills | Teaches prompting techniques for AI video generation models on Replicate, for writing prompts or building video generation features. |
| suno-engineer 79/100 · C | bitwize-music-studio/claude-ai-music-skills | Constructs technical Suno style prompts for the current model family, selects models and generation settings, and optimizes prompts for track generation. |
| vibe-creating-prompt 80/100 · B | Alisa0808/vibe-creating-skill | Rewrites ideas or rough prompts into clearer text-to-video prompts in the Vibe Creating style, preserving user-specified dialogue, voiceover, music, and sound effects. |
| agent-development 86/100 · B | anthropics/claude-plugins-official | This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use… |
| agent-platform-prompt-management 87/100 · B | google/skills | Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent… |
| ai-prompt-engineering-safety-review 69/100 · D | github/awesome-copilot | Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and… |
| arize-prompt-optimization 82/100 · B | github/awesome-copilot | Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers… |
| boost-prompt 63/100 · D | github/awesome-copilot | Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code… |
| create-agent 70/100 · C | NeoLabHQ/context-engineering-kit | Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official… |
| diagnose 69/100 · D | github/awesome-copilot | Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture… |
| enhance-prompt 72/100 · C | google-labs-code/stitch-skills | Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and… |
| fal-prompting 76/100 · C | fal-ai-community/skills | Model-family-specific prompt craft for fal.ai endpoints. Trigger when the user mentions a specific model family by name and asks how to prompt it… |
| finalize-agent-prompt 59/100 · D | github/awesome-copilot | Finalize prompt file using the role of an AI agent to polish the prompt for the end user. |
| goal-prompt 88/100 · B | trailofbits/skills | Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress… |
| gws-modelarmor-sanitize-prompt 54/100 · D | googleworkspace/cli | Google Model Armor: Sanitize a user prompt through a Model Armor template. |
| long-horizon-prompting 76/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent… |
| prompt-engineer 84/100 · B | jeffallan/claude-skills | Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test… |
| prompt-engineering 70/100 · C | NeoLabHQ/context-engineering-kit | Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing… |
| prompt-guard 66/100 · D | Orchestra-Research/AI-Research-SKILLs | Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU)… |
| prompt-optimizer 75/100 · C | github/awesome-copilot | Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat… |
| system-prompt-creator 84/100 · B | tronghieu/agent-skills | Create high-quality, model-aware system prompts for any LLM (Claude, GPT, Gemini, open-source, etc.). Use this skill whenever the user wants to… |
| test-prompt 70/100 · C | NeoLabHQ/context-engineering-kit | Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies… |
| tldr-prompt 67/100 · D | github/awesome-copilot | Create tldr summaries for GitHub Copilot files (prompts, agents, instructions, collections), MCP servers, or documentation from URLs and queries. |
| venice-characters 70/100 · C | veniceai/skills | Discover and use Venice public characters (persona-driven system prompts with a suggested model). Covers GET /characters… |
How to choose prompt engineering skills
Match the skill to the prompt's target. General optimizers (prompt-optimizer, system-prompt-creator, prompt-engineer) work across models; fal-prompting and Replicate's prompt-images and prompt-videos encode the conventions of specific media models.
For prompts already in production, pick a skill that works from evidence. arize-prompt-optimization uses traces and evaluations, and test-prompt runs the prompt against cases before you commit a change.
Most prompt skills are plain Markdown with no scripts, so you can read the whole method in SKILL.md before installing. The platform skills (Arize, Agent Platform) read service credentials, shown under Before you install.
Ranked prompt engineering shortlists
Related topics
Prompt Generators 19Evals and Benchmarks 27Agent Safety and Guardrails 27AI Agent Builders 56AI Video Generation 18Security Auditing and Review 108Subagents and Multi-Agent Orchestration 40Agent Tracing and Observability 41
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills