Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
★not rated 173k▲
+664 yesterdayA
tokens not measured
Optimize 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.
★not rated 7.0k▲
+80 5d agoA
tokens not measured
originalMIT
User-level skills that recommend TanStack AI, map a task to the package that covers it, install it, then load that package's own SKILL.md through TanStack Intent.
Intelligent 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…
A 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.
★not rated 475▲
+9 7d agoA
tokens not measured
originalMIT
A prompt-engineering toolkit that turns ideas into executable prompts. It includes a prompt-generation command, model-specific guides for Claude, GPT, Gemini, and image models, and a prompt kit.
★not rated 187▲
+3
changed 22d agoA
tokens not measured
AI / LLM application engineering expertise. Ships the ai-engineer agent plus the in-house ai-app-templates skill and 1 vendored skill (senior-prompt-engineer) for production LLM systems, RAG, agents, and prompt design.
★not rated 154▲
+2 6d agoA
tokens not measured
originalMIT
AI prompt database and builder skill for Claude Code. 2,500+ curated prompts across 19 categories and 17 AI models. Search, build, enhance, and adapt prompts.
★not rated 113▲
+2 6mo agoA
tokens not measured
originalMIT
Clarity gate for prompts: intercepts unclear requests and forces AI to restate intent to align with the user, then diagnose the root cause and reuse the domain's mature, established practices before proceeding.
★not rated 38 3mo agoA
tokens not measured
originalMIT
Extract invoices and documents from text, Markdown or Mistral OCR into typed JSON. Six core MCP tools, chat, vision, transcription and 11 Claude Code skills.
★not rated 15
changed 20d agoA
tokens not measured
originalMIT
Adapt any prompt to fit Claude Fable 5 (claude-fable-5) without losing its meaning: optimize structure per Fable's prompting guidance, clarify legitimate intent to avoid false-positive refusals, and flag mechanical API incompatibilities.
★not rated 14 3mo agoA
tokens not measured
originalMIT
Audit and optimize agentic systems — review agents, tool loops, and inference requests across prompt engineering, tools, context, cache, evaluation, and guardrails; rewrite prompts using Anthropic best practices.
★not rated 12 10d agoA
tokens not measured
originalMIT
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: