Prompting skills

1,516 tagged Prompting, measured the same way as everything else here.

Browse within: prompt-engineering 176LLM 140ai-tools 113agents 99claude-code-plugin 93skills 89cursor 80agentic-ai 70agent 68ai-skills 65ai-coding 64antigravity 57cli 57ai-video 45

agenta

49

diegosouzapw/awesome-omni-skill

Skill Claude CodeCodex

LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.

not rated 57 6mo ago A 36 tokens

claude-prompt-forge

50

Bin1783/claude-prompt-forge

Skill Claude CodeCodex

Generate production-grade prompts following patterns extracted from Claude Code source. Use when writing system prompts, tool descriptions, agent instructions, compression prompts, or any structured LLM prompt. Triggers on "write a prompt", "generate prompt", "design prompt", "create instructions for".

not rated 56 5mo ago A 62 tokens

prompt-engineering

51

cmpnd-ai/skilled-proposer

Skill Claude CodeCodex

Use when optimizing or iterating on prompts for a student LLM — a prompt produces wrong-shaped output, hallucinations, refusals, poor instruction-following, or when migrating a prompt between models with different quirks. Also use when hardening a prompt against indirect prompt injection from untrusted external data.

not rated 55 26d ago C 65 tokens original MIT

zhouwei713/gpt-image-2-prompting-skill

Skill Claude CodeCodex

Write high-quality GPT-Image-2 prompts with strong structure, layout logic, and production-ready visual direction. Use this skill whenever the user asks for image prompts, wants better GPT-Image-2 prompting, wants to upgrade a weak image prompt, asks for prompt templates, wants series-style prompt systems, needs…

not rated 51 3mo ago A 145 tokens original MIT

writing-plans

53

alexey-max-fedorov/gaia-ai

Skill Claude CodeCodex

Use when you have a spec or requirements for a multi-step task, before touching code.

not rated 51 +2 3d ago A 21 tokens

AmadeusITGroup/ai-primitives-hub

Skill Claude CodeCodex

Answer questions about using AI Primitives Hub and authoring bundles. Use this skill whenever the user asks about bundles, collections, hubs, profiles, sources, scopes, marketplace, repository installation, deployment manifests, source scaffolding, collection schemas, validation errors, publishing, or any AI…

not rated 50 2d ago A 76 tokens

nai5-prompting

55

Miint-Sunny/nai5-prompting

Skill Claude CodeCodex

A guide for writing prompts for NovelAI Diffusion V5, an image-generation system. It covers describing scenes, arranging multiple characters, making comic panels, and troubleshooting results.

not rated 49 +11 8d ago A 116 tokens GPL-3.0

jatevo

56

lucacadalora/jatevo-openclaw

Skill Claude CodeCodex

Free inference-as-a-service via Jatevo.id — access Qwen 3.5 Plus, Kimi K2.5, and GLM 4.7 at zero cost. Use when you want free, high-quality LLM models for OpenClaw.

not rated 47 5mo ago A 57 tokens original MIT

prompt-polish

57

mfarzanansari/prompt-polish

Skill Claude CodeCodex

Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for…

not rated 42 1mo ago A 146 tokens original MIT

jayminwest/canopy

Skill Claude CodeCodex

Compose a canopy prompt by inheriting from a base prompt and emit the rendered result. Use when an agent needs to author, update, or render canopy prompts inside this repo.

not rated 40 1mo ago A SkillSpector: pass 42 tokens original MIT

ai-ad-prompt-guide

59

creatify-ai/ai-ad-prompt-guide

Skill Claude CodeCodex

Battle-tested prompting guide for AI video and image generation in advertising. Covers universal prompting rules, hallucination prevention, the SLCT framework for structured prompts, camera movement vocabulary, UGC formulas, product shot techniques, and the pass³ quality test. Includes model-specific guidance for Sora…

not rated 38 6mo ago A 178 tokens original MIT

prompt-pack-support

60

fastlion4376-yrjda/prompt-pack-support

Skill Claude CodeCodex

A method for creating reusable customer-support prompts for people or chatbots. The pack can include tone rules, reply templates, escalation paths, refusals, privacy guidance, and quality checks.

not rated 35 +6 1mo ago A 71 tokens original MIT

Emily2040/nano-banana-image-skill

Skill Codex

Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…

not rated 30 3mo ago A 210 tokens original Apache-2.0

genkit-ai/skills

Skill Claude CodeCodex

Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.

not rated 30 +2 changed 5d ago A Socket: passSnyk: pass 60 tokens

luozhilzh/video-prompt-reverse

Skill Claude CodeCodex

A video-prompt writing skill that examines a video or a rough idea and turns it into instructions for an AI video generator. It can describe camera movement, timing, style, consistency between shots, and platform-specific settings.

not rated 30 +3 29d ago A 130 tokens original MIT

zircote/.claude

Skill Claude CodeCodex

Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-of-thought, few-shot prompting, and progressive disclosure.

not rated 26 7mo ago A 43 tokens archived

Mr-Salticidae/knowledge-base

Skill Claude CodeCodex

A workflow for turning vague or conversational AI image and video requests into prompts suited to particular creative tools. It covers image tools such as Midjourney and DALL-E and video tools such as Sora, Runway, and Kling.

not rated 24 yesterday A 177 tokens

KathanModh259/latent-gate

Skill Claude CodeCodex

Compress images, long prompts, conversations, and RAG documents locally via Ollama before consuming LLM tokens. Reduces token usage by 80% on images and 85% on text. Use proactively when: the user uploads images, processes long context, works with multiple RAG sources, or when approaching token limits.

not rated 24 1mo ago A 73 tokens

get-zeked/ai-agent-super-skill

Skill Claude CodeCodex

Comprehensive AI agent building skill merging Perplexity Computer's skill creation, webserver, and automation capabilities with Claude Code's agent orchestration, MCP server building, RAG system construction, subagent coordination, parallel agent dispatching, prompt optimization, and execution planning. Covers…

not rated 24 +1 6mo ago A 119 tokens

prompt-optimizer

69

ckanner/agent-skills

Skill Claude CodeCodex

This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models…

not rated 23 9mo ago A 83 tokens original Apache-2.0

kling-3-prompting

70

aedev-tools/kling-3-prompting-skill

Skill Claude CodeCodex

Write better prompts for Kling 3.0 AI video generation. Use when the user wants to create, write, improve, or refine prompts — text-to-video, image-to-video, keyframes, multi-shot sequences, or dialogue scenes.

not rated 23 7mo ago A Socket: passSnyk: pass 56 tokens original MIT

Just-Agent/make-agents-cheaper

Skill Codex

Use when the user wants to make Claude Code cheaper by improving prompt-cache hit rate, especially for MiMo or other OpenAI-compatible routed models. Trigger for Claude Code cache-hit analysis, cache-friendly command construction, paired baseline vs candidate evaluation, token usage logging, or use of…

not rated 23 +1 3mo ago A 74 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: