PROMPTS
1346 original and curated AI prompts across image, video, music, and tutorials. Browse by tool, use case, and difficulty; each entry shows its available notes and examples.
FiltersExpandCollapse
Contrastive Example Calibration: Show It What You Want AND What You Don't — One Negative Example Beats Three Positive Ones
Demonstrate both the 'desired output' and the 'output that shouldn't appear' at the same time, so the AI calibrates between the two poles; for tasks about tone and precision, a single negative example often outperforms three positive ones.
Chain-of-Thought Scaffold: A Fixed 5-Step "Think Before You Answer" Process
Forces the AI to think through 5 fixed steps before answering — restate → list assumptions → reason step by step → self-check → conclude. Field tests show roughly a 30% reduction in confidently wrong answers on complex reasoning tasks.
5 Claude Repeat-Task Templates That Lasted 6+ Months — and the 3 Retention Rules
After 18 months of testing 60 Claude workflows, the retention pattern: annoying but not painful, output has a destination, input under 30 seconds. The 5 templates that survived 6+ months (Friday review / meeting follow-up / client weekly report / Monday briefing / pipeline update).
5 Prompt Engineering Techniques That Actually Move the Needle (XML Beats Markdown by 28%)
Five quantifiable techniques from an AI engineer's hundreds of hours testing across GPT-4, Claude, and Gemini: CoT scaffolding, persona + goal + anti-goal, XML being 28% more accurate than markdown, negative examples outperforming positive ones, and prompt chaining beating the mega-prompt.
Turn Off ChatGPT's Polite Lying — 3 Anti-Sycophancy Instructions
By default, helpful = agreeable = burying the real problem in paragraph four. Three one-line instructions reverse it: problem first, force a recommendation, explicitly forbid softening. The difference between reading and fixing.
A Red Teamer's View: 3 High-Capability Prompt Patterns That Work Across Models
Three patterns shared by the HackAPrompt 2.0 champion: frame the task as an audit, make the abstraction level explicit, and stage the context like production. They work on Claude, GPT, and Gemini alike.
AI Agent Harness Engineering: Separating the LLM from the Deterministic Orchestration Layer
Mitchell Hashimoto's "Agent = Model + Harness" framework. The reason 88% of enterprise AI agents never reach prod isn't the prompt — it's the missing deterministic orchestration layer. Four CS primitives you can't skip: state machine, idempotency, DAG, DLQ.
COMMAND PLANNING MODE: A 9-Section Structured Planning Prompt
No conversation, no suggestions, no attempts — it just turns any situation into a structured execution plan. Fixed 9-block output: Reality / Objective / 4-phase Timeline / Tactics / Threats / Defenses / Contingency / Leverage / Confidence. Same input always yields the same output.
System vuln scanner: analyze your architecture, find attack chains, estimate time-to-compromise
More than "list the CVEs." It finds how individual weaknesses chain into an attack and estimates how long an AI-augmented attacker would need to break in. A take on the OpenAI Daybreak concept, built for small teams. Feed in a stack description (Next.js + Supabase + Clerk, etc.) and get back critical paths plus a patch-priority order.
ChatGPT Custom Instructions: describe the relationship, not your resume
Most people fill Custom Instructions with a LinkedIn resume, "I'm a software engineer, I like bullet points," and it does nothing. Swap in a description of the conversational relationship you want, and three sentences will completely change how the model behaves.
reClaim: Turn a Frontier Model Into a Research Agent With Confidence Scores
Scores every claim on three axes (A: sources / B: counterevidence / C: completeness), plus a 4-tier source hierarchy, adversarial self-poking, and 4 output modes.
AI attack-surface audit: see yourself the way an AI-augmented attacker does
Written after Google's threat-intelligence report in May 2026. AI hacking has gone from nascent to industrial scale, with commercial AI models digging up zero-days humans had missed for decades. This prompt lays out every place you can be attacked.
Suno Live Concert Mode: Injecting Ambience with Asterisk Syntax + 35 Sound Cues
This isn't "adding sound effects" — it's changing the performance context. When Suno sees [Live Crowd] or *crowd cheering*, it dials back vocal processing, loosens the timing, and adds spatial depth. It genuinely sounds like a live concert recording.
Job-search strategy: turn ChatGPT into a 4-in-1 (auditor + analyst + advisor)
Combines a resume auditor, market analyst, system auditor, and strategist. It won't flatter you, won't over-reassure you, and won't push you toward roles that don't fit. Includes a 10-step process and ghost-job detection.
English copy editor: 4 priorities, emotional resonance, and structural flow
More than a grammar fix. Purpose-built for persuasive and narrative writing: four priorities (clarity → tone → emotional resonance → structure), an explanation for every change, plus extra suggestions.
Suno Advanced: Pin Down Your Sound with Synth Models + Recording Details
Why does Suno always sound generic? Because you only describe "genre + vibe." Swap in "Jupiter-8 saw wave bass with reverb tail" and Suno gives you the exact sound you're after.
A Universal Decision Prompt: Use "What Will You Regret in a Year" to Force a Verdict
Stop picking a role for every decision (financial planner / career coach / relationship coach) — one universal prompt, four steps. The regret line is the core — it forces the model from "it depends" to "actually do this."
CV Writer Ruleset: It Interviews You STAR-Style and Bans "Dynamic Team Player"
The pain of writing a CV isn't the layout — it's listing duties instead of achievements, then having AI pile on and turn you into a "dynamic team player." This ruleset forbids AI from drafting anything until it has your evidence and positioning, and walks you through one question at a time.
Voice Memo → Tomorrow's Priorities (With a Confirmation Round)
Before you log off, ramble into your phone mic for 2 minutes, hand it to Claude, and get back a sorted list: first thing tomorrow morning + ranked to-dos + waiting-on + can-defer. Auto-detects daily vs. weekly mode.
The 60-Second Pre-Send Check: Catch the Message You'll Regret Tomorrow Morning
The author wrote this after 30% of their heated replies made them wince the next day — costing a few deals and a friendship. The trick: don't let AI rewrite it, let it show you what the calm version would look like. Once you see it, you usually can't go back to the original.
Grading essays as a teacher: a 3-step chain (lens → diagnose → tone)
A method dreamed up by a teacher 19 essays into a 30-essay all-nighter. Where typical AI prompts "act as an English teacher" and devolve into a wall of rubric noise, this chain solves the real grading workflow: don't comment on everything.
AI displacement self-assessment: break your job into tasks and score each 1-10
Written after Cloudflare cut 20%, BILL cut 30%, and Upwork cut 24% in 2026. Your job title tells you nothing; breaking the work into tasks tells you everything. Get an AI vulnerability score (1-10) and timeline for each task, plus an overall risk rating.
Flip Your AI Dev Workflow: Generate the Prompt First, Then the Code (4 Phases)
Instead of telling AI to write code directly, have it translate a vague goal into an executable prompt structure first, then use that structure to drive code generation. Phase 1 Intent → Phase 2 Structuring → Phase 3 Tool-Level → Phase 4 Implementation.
Custom GPT governance: the 7-block Agent Identity Card
Run this before you build a custom GPT or n8n agent. It forces you to define boundaries up front and prevents agent scope creep ("just handle my work for me" = disaster).