Explore the library

A system prompt that turns any AI agent into a rigorous research analyst: it searches broadly, evaluates sources by credibility, surfaces what's genuinely uncertain, and delivers a structured briefing — not a confident-sounding summary of whatever it found first.

Turn any assistant into a decisive, no-padding expert. Drop it into ChatGPT custom instructions, a Claude Project, or your API system prompt.

A system prompt for autonomous coding agents (Claude Code, Cursor agent mode, custom agents) that prevents the most common failure modes: it requires a plan before acting, checks in at decision points, and never deletes or overwrites without explicit confirmation.

A retrieval-augmented system prompt that answers only from context and returns inline citations or 'I don't know'.

Produces a complete system prompt that defines a support agent's persona, voice, knowledge boundaries, and exact escalation rules — brand-aligned and safe to ship, not a generic 'be helpful'.

Produces a system prompt and routing logic that classifies incoming tickets by intent, urgency, and language — then routes to the right queue with a priority and confidence score, so nothing critical sits in a generic inbox.

An editor that sharpens your writing without making it sound AI-generated. Works as ChatGPT custom instructions or a Claude system prompt.

A system prompt for a multi-step content agent that takes a topic brief and produces a research-backed, SEO-aware draft in stages — with checkpoints so you can redirect before the agent goes too far in the wrong direction.

Produces a guardrail layer that intercepts a support agent's draft reply, rewrites it on-brand, and blocks policy violations (refunds, promises, unsafe content) before it ever reaches the customer.

A system prompt for a support AI agent that answers confidently within its knowledge, admits what it doesn't know, never promises what it can't deliver, and hands off to a human with a complete context summary when needed.

Design strict, self-validating tool schemas with confidence calibration, discriminated unions, and chain-ready contracts — so your agent calls tools reliably instead of hallucinating arguments.

Turn a goal into a coordinated planner→worker→critic agent workflow with clear handoffs and a stop condition.

Give this agent a project goal and it builds a sequenced task list with dependencies, time estimates, and a critical path — then tracks completion, flags blockers, and adjusts the plan when things change.

Every world is anchored by a magic system designed using Brandon Sanderson's Laws — limitations that CREATE drama, costs that shape culture, and mysteries that fuel plot. Each prompt includes the magic, its societal ripple effects, and expands into a full world bible.

Scopes a 3D open-world prototype realistically — character controller + drivable vehicle + map first, bigger systems phased.

Produces a complete, local-first RAG pipeline with document loading, chunking, Ollama embeddings, a vector store, retrieval, and a grounded answer step with citations, requiring no cloud APIs.

Not random deep questions — a structured self-discovery interview that explores you through five specific lenses (values via dilemmas, energy audit, relationship patterns, money stories, and recurring choices), then writes a 'mirror summary' of who you actually are vs. who you think you are.

Produces a privacy-first local chat configuration with model and quantization choice for your hardware, a system prompt, conversation settings, and a data-leakage audit checklist so nothing leaves your machine.

Get a complete, deployable system prompt for a Custom GPT, Gemini Gem, or Claude Project — including the sections most people forget: personality guardrails, the 'don't' list, edge case handling, refusal patterns, and token budget management.

Go beyond 'animated style' with the specific visual vocabulary each animation style needs — subsurface scattering for Pixar skin, 'on twos' for anime, fingerprint texture for claymation — plus character consistency and audio pairing.

Produces a decoupled interactable system — a reusable interface, a player interaction component, and UnityEvents or a scriptable-object event channel — so doors, levers, and pickups all plug in without hard references.