Category
Promptsrules, skills & MCP servers
Prompts are the hand-tuned system prompts and prompt libraries that set how a model behaves before it sees a single user message. A strong prompt encodes role, constraints, format, and refusal behavior so tightly that the model is reliable across thousands of calls; a weak one drifts the moment the input gets unusual. The prompts below are quality-scored on specificity, structure, and how clearly they define the output contract — not on how clever they sound. Each is attributed to the author who wrote it, so you can see what else they've shipped and trust their judgment before you build on their work. Copy a prompt straight into your system message or your prompt-management layer, adapt the variables, and you start from a baseline that other people have already pressure-tested in production. Browse the top prompts below ranked by quality score, or open the full catalog to filter by the model, the use case, and the format each prompt is tuned for.
Top prompts right now
Ranked by quality score — freshness, schema completeness, and review signals. Refreshed daily.
Browse other categories
Rules
Context files, style guides, and coding rules for AI editors.
MCP Servers
Model Context Protocol servers that extend AI capabilities.
Skills
Packaged capabilities your assistant can invoke on demand.
Agents
Autonomous agents and subagents for Claude Code, Cursor, Codex, and frameworks like LangGraph or CrewAI.
Agent Teams
Multi-agent crews, roles, and orchestration graphs.
Workflows
End-to-end automations for n8n, Make, and similar tools.
CLIs
Command-line utilities and AI-native shells.
Datasets
Training, evaluation, and retrieval datasets.
Bundles
Curated multi-item packs priced as a single drop.