1328 hand-tested AI prompts across image, video, and music — each with full context, variables, and a sample output. Content is authored in Traditional Chinese; the UI here is English.
Has the agent automatically inventory your Cursor project (.cursorrules, .cursor/rules, .cursor/mcp.json), produce a step-by-step migration plan, and generate the corresponding CLAUDE.md or AGENTS.md, slash commands, and MCP config — so you're not stuck 'dumber than Cursor' on day one.
A Definition of Done template you can paste into any coding agent, turning 'what counts as done' into a checklist the agent must self-verify item by item: behavior meets acceptance criteria, tests/lint/typecheck/build all pass (or it states why they didn't run), risky changes come with a rollback plan, and a final 'verification story' is delivered. Puts an end to agents claiming 'done' while everything is actually broken.
Converts plain-language requests like 'find customers who bought more than 3 times last month' into an executable SQL query plus an explanation — give it your table schema for even more accurate results.
Hand the AI the options you're torn between; it lists the key considerations, gives weighted scores, points out risks you might have missed, and gives a reasoned recommendation.
For emailing strangers: one line of relevant opening, one line naming their pain point, one line of concrete value, and one low-friction CTA — avoiding the 'our company was founded in...' dead-on-arrival opener.
Generate a full sales-page copy skeleton in one shot: an attention-grabbing headline, amplified pain points, stacked benefits, objection handling, and a strong CTA — ready to drop your product straight in.
Generates 5 title-plus-thumbnail-text combinations for a single video — the title creates curiosity, the thumbnail adds non-redundant information, and together they drive more clicks than either alone.
Gives you a response script for each of the most common customer objections — not a hard pitch, but 'acknowledge first, then reframe' — phrased naturally so it doesn't sound rehearsed.
Have AI review your code like a senior engineer: it flags concrete issues and fixes across four dimensions — correctness, security, performance, and readability — instead of vague praise.
Uses Gemini 2.5 Pro's multimodal ability to turn any screenshot — an error message, an admin dashboard, a report, a conversation — into a concrete, actionable next-step checklist.
Has the AI produce a first draft, then switch into a strict editor role to pick apart its own flaws, and finally rewrite based on that critique — effectively running three rounds of polish inside a single prompt.
Write out the grading rubric in your head and give it to the AI first — it will use that yardstick to self-align, self-evaluate, and fix whatever falls short, getting you much closer to the quality you actually want.
Explicitly naming "the most common failure mode AI makes on this type of task" in the prompt and telling it to proactively avoid that mode — 2026 field tests show roughly a 28-30% reduction in errors.
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.
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.
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).
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.
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.
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.
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.
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.
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.
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).
An Oxford study in Nature: the "warmer" an AI is trained to be, the more its accuracy drops, by 10-30 percentage points. This prompt reviews an AI response and flags every place warmth overrides accuracy.