| # | Mod | Type | Stars | Scan | Tokens | Rating |
|---|---|---|---|---|---|---|
| 1 | claude-apiasgeirtj/system_prompts_leaksReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude… | Skill | 71k | A | 294 | — |
| 2 | n8n-agentsczlonkowski/n8n-mcpDesign n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output… | Skill | 23k | A | 156 | — |
| 3 | AGENTSpromptfoo/promptfooCommander.js-based CLI commands registered in src/main.ts. | Command | 27k | A | 0 | — |
| 4 | prompt-masternidhinjs/prompt-masterGenerates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other… | Skill | 16k | B | 78 | — |
| 5 | gepa-optimize-anythinggepa-ai/gepaOptimize any scorable text artifact (prompts, code, configs, agent scaffolds, search solutions) with optimizeanything — one evaluator-driven API across the GEPA optimizer (reflective evolutionary search, the default), AutoResearch, and MetaHarness backends, with a best-of-N baseline for comparisons. | Plugin | 7.3k | A | — | — |
| 6 | powerapps-canvas-yaml-generatorpnp/copilot-promptsGenerates valid, importable Power Apps Source Code YAML for canvas app screens. Use when asked to create YAML, scaffold, or modify any Power Apps canvas app screen — including full screens, dialogs, forms, galleries, detail views, dashboards, or any layout container — or when asked to generate Power Fx formulas or… | Skill | 902 | A | 79 | — |
| 7 | seedance-prompt-zhdexhunter/seedance2-skillChinese-language guidance for writing prompts for Seedance 2.0, an AI video generator that can use text, images, video, and audio. | Skill | 4.4k | A | 100 | — |
| 8 | npcpy-promptingNPC-Worldwide/npcshSkill "npcpy-prompting" from NPC-Worldwide/npcsh, covering npcpy-prompting, imports, basic-call, json-mode and npc-object. | Skill | 502 | A | 16 | — |
| 9 | prompt-cache-optimizerling-kong-ran/pisperAudit and optimize Pisper system-prompt and tool-schema token overhead while preserving stable prompt-cache prefixes, permissions, and runtime behavior. Invoke only for explicit prompt or tool-context optimization work. | Skill | 308 | A | 42 | — |
| 10 | outlinesaivrar/portable-hermes-agentOutlines: structured JSON/regex/Pydantic LLM generation. | Skill | 244 | A | 17 | — |
| 11 | best-practicesMoizIbnYousaf/Ai-Agent-SkillsTransforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices. | Skill | 1.2k | A | 35 | — |
| 12 | andrej-karpathyhenryalouf/ruflowAgente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo. | Skill | 184 | A | 47 | — |
| 13 | audit-prompt-cachingsernote/audit-prompt-cachingUse whenever the user mentions cachedtokens=0,totalcachedtokens,cachereadinputtokens,cachecreationinputtokens,cachewritetokens,promptcachekey,promptcacheoptions,promptcachebreakpoint,previousinteractionid,cachecontrol/cachePoint,TTFT,KV reuse… | Skill | 133 | A | 139 | — |
| 14 | prompt-improverseverity1/claude-code-prompt-improverIntelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability… | Plugin | 2.0k | A | — | — |
| 15 | ai-shortfilm-promptsjnMetaCode/ai-shortfilm-promptsA collection of five-part methods and reusable templates for writing cinematic prompts for AI video generation. It covers 21 subject areas and lists compatibility with tools such as Seedance, Kling, Sora, Veo, Jimeng, and Runway. | Plugin | 516 | A | — | — |
| 16 | nativepromptedvardgrishin27/nativepromptA prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5. | Skill | 128 | A | 147 | — |
| 17 | prpm-blog-writerpr-pm/prpmExpert agent for creating PRPM blog posts - ensures consistent structure, tone, format, and technical depth aligned with PRPM's vision of distributable intelligence. | Agent | 124 | A | 36 | — |
| 18 | prompt-template-authoringnicobailon/pi-prompt-template-modelWrite and run custom Pi prompt templates (slash commands) for this extension. Use when creating templates with model selection, deterministic pre-steps, loops, chains, subagents, or best-of-N compare flows. | Skill | 324 | A | 47 | — |
| 19 | speckit.specjudge.recommendJoaquinRuiz/SpecJudgeRecommend the model that fits this feature's tasks, with the fragment of the spec behind every level. | Command | 59 | A | 19 | — |
| 20 | claude-promptsminipuft/claude-prompts-mcpModel Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework :: 'gate'. | Plugin | 192 | A | — | — |
| 21 | video-promptingSquare-Zero-Labs/video-prompting-skillDraft and refine prompts for video generation models (including text-to-video, image/keyframe-to-video, and reference-driven generation), and create character-sheet prompts for image models when the goal is character consistency before image-to-video. Use when a user asks for a "video prompt", a model-specific prompt… | Skill | 187 | A | 152 | — |
| 22 | llmtrimfkiene/llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost. Runs locally from the @llmtrim/cli npm package. | MCP server | 267 | A | — | — |
| 23 | video-prompt-reverseluozhilzh/video-prompt-reverseA 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. | Skill | 54 | A | 130 | — |
| 24 | nuyoah-xiezhen-promptnuyoah-ai-works/nuyoah-xiezhen-promptA Chinese-language prompt-writing guide for AI portrait photography, including recreating a photo series with a different person and breaking reference images into usable instructions. | Skill | 782 | A | 97 | — |
| 25 | general-context-and-instructionspragunbhutani/dbt-llm-agentWe are building an LLM powered AI data analyst for Data Engineering teams that work with dbt to manage their analytics code bases. To use this project, users should be able to connect with their dbt cloud projects or their dbt core github repos via an interface which is then used to build a knowlege base. We then use… | Cursor rule | 180 | A | 2,253 | — |
| 26 | prompt-refineApeironics/prompt-refine-skillImprove a prompt or reusable task specification, or enable conversation-scoped prompt-refine mode. Preserve intent and constraints while applying the target model's documented guidance. Use for prompt rewriting and explicit refinement requests, not every ordinary question or edits to a skill's implementation. | Skill | 54 | A | 56 | — |
| 27 | make-goalmajiayu000/awesome-goal-promptsCreate, tighten, or review runnable /goal contracts for coding agents such as Codex, Claude Code, Cursor, and similar agent tools. Use when the user asks to write, make, generate, improve, productize, or critique a goal prompt, rescue contract, GOAL.md-style task, done-when contract, verification prompt, stop-rule… | Skill | 52 | A | 141 | — |
| 28 | realistic-video-promptingzhouwei713/seedance-promptA skill for writing structured prompts for AI video generators such as Sora, Runway, and Veo. It focuses on videos that look like real recordings, including phone footage, home videos, documentary clips, and security-camera footage. | Skill | 335 | A | 141 | — |
| 29 | image-promptgongnyang/gongnyang-prompt-kitA Korean-language prompt-writing toolkit for turning vague image requests into detailed prompts for GPT Image. It covers posters, covers, illustrations, promotional materials, typography, presentations, and related formats. | Skill | 329 | A | 231 | — |
| 30 | prompt-senseichengzhongwei/Prompt-senseiStage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex. | Skill | 109 | A | 39 | — |
| 31 | hm-llm-guardrailsrodrigohighermind/highermind-code-skillsCatálogo de 14 patterns obrigatórios para app que integra LLM (Claude/GPT/Gemini) em produção. Use antes de shippar feature LLM pra produção, quando custo da API explode sem explicação, quando user reclama de "respostas demoram demais" ou "trava no meio", ao adicionar tool calling, agentes ou chat persistente. Cobre… | Skill | 197 | A | 149 | — |
| 32 | prompt-architectckelsoe/prompt-architect31-framework prompt engineering skill for analyzing and improving prompts across 7 intent categories. | Plugin | 328 | A | — | — |
| 33 | minimind-learningjoyehuang/minimind-notesA Chinese-language learning assistant for MiniMind, a small language-model project, that records study notes and recognizes common machine-learning terms. | Skill | 228 | A | 76 | — |
| 34 | omni-rewriterWayneJin0918/Omni-RewriterOmni-Rewriter prompt-expansion framework conventions. | Cursor rule | 89 | A | 253 | — |
| 35 | prompt-engineeringTanShilongMario/PromptSkill4imageAdvanced image prompt engineering assistant for Chinese-first users. Turns any input into high-quality image-generation prompts: reverse-engineers prompts from images, expands rough prompts into structured prompts, translates/transwrites prompts, extracts reusable variables, suggests phrase banks, supports minimal… | Skill | 141 | A | 63 | — |
| 36 | directional-promptingkingbootoshi/directional-promptingWrite prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition) plus directional language (every sentence names the path with positive verbs). Triggers when writing or reviewing any… | Skill | 144 | A | 151 | — |
| 37 | meta-harness001TMF/harness-forgeRun a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto… | Skill | 80 | A | 217 | — |
| 38 | prompt-mastermackswendhell/prompt-mestreGera prompts otimizados para qualquer ferramenta de IA. Use quando for escrever, corrigir, melhorar ou adaptar um prompt para LLM, Cursor, Midjourney, IA de imagem, IA de vídeo, agentes de código ou qualquer outra ferramenta de IA. | Skill | 61 | A | 56 | — |
| 39 | gpt-image-2-promptingzhouwei713/gpt-image-2-prompting-skillWrite 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… | Skill | 56 | A | 145 | — |
| 40 | convexwaynesutton/promptstackCursor rule "convex" from waynesutton/promptstack, covering convex guidelines, function guidelines, new function syntax, http endpoint syntax and function registration. | Cursor rule | 78 | A | 0 | — |
Want everything, not just what passes the gates? Browse the full category from any type hub, or search it. This shelf recomputes nightly from the measurements.