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.
Filters3 activeExpandCollapse
AI Self-Fact-Check: Source Tags, Self-Attack, Confidence Grading
Doesn't let the AI just hand in its answer as-is: it first tags the source type of every key sentence, then hunts for counterexamples to attack its own claims, and finally grades confidence level item by item with suggested directions for verification. Good homework before researching, writing a report, or making a decision. Honest note: this isn't the same as actual fact-checking (the model may not be able to search the web) — but it forces uncertainty out into the open and noticeably reduces confident-sounding nonsense.
Bug Report Format for AI Fixes: Symptom, Repro, Behavior, Environment
Report a bug in this format and the AI's fix hit rate jumps noticeably: give all four parts at once — the raw symptom, a minimal repro, expected behavior, and environment — and force the AI to diagnose first, ask for more information when it's insufficient, and never guess-and-change blindly. Suited to any scenario where you're asking ChatGPT or Claude to fix code. Note: the AI's diagnosis is reasoning, not an actual test run — after the fix, be sure to actually run through the included verification checklist.
Contract Red-Flag Scan: Risky Clauses in Leases, Jobs, and Outsourcing
Feed in a lease, employment, or outsourcing contract, and it scans clause by clause from your side of the deal: a plain-language translation, worst-case scenario, risk grading, and negotiation angle for each, plus three questions to bring to a professional at the end. Note: this is a prep tool for understanding a contract, not legal advice — for high-value contracts or ones involving major rights, consult a lawyer, and it's safest to treat the scan results as homework to do before meeting one.
Taiwan Official Document Drafter: Subject/Explanation/Action Format
Feed the AI the background of a matter and it produces a draft following Taiwan's official document format — Subject, Explanation, Action — automatically applying standard bureaucratic phrasing and adjusting tone for upward, lateral, or downward correspondence. The final section forcibly flags regulations and figures that "need human verification"; this is positioned as a draft, not a final document.
Localization Translation: Literal + Taiwan-Flavored Polished Versions
Bilingual Chinese-English localization with one more layer than Google Translate. Specifies Traditional Chinese as used in Taiwan plus Taiwan-specific idioms, keeps names, brand names, and technical terms from being mistranslated, and delivers both a literal version and a localized, polished version in one pass so you can compare and pick. You can also feed it style samples so it learns your company's tone. Suited to marketing copy and product descriptions for foreign firms, freelancers, and cross-border e-commerce in Taiwan.
Stop Writing 'Think Step by Step': How to Rewrite Prompts for Reasoning Models
The 2026 cognitive gap: reasoning models like Opus, GPT-5, and Gemini Deep Think already think internally, so 2023-era incantations like 'you are a top expert,' 'take a deep breath,' and 'let's think step by step' are ineffective on them — or even counterproductive. This prompt has the AI rewrite your old prompts into a reasoning-model version, with a before/after comparison table, and explains which models count as reasoning models and whether free tiers support them.
Self-Consistency Voting: Have AI Solve the Same Problem Three Times and Take the Consensus
A no-code way to run Self-Consistency: have the AI solve the same problem via three different lines of reasoning, then compare the results and take the majority consensus. Especially useful for scenarios where a mistake is costly — tax estimates, loan interest comparisons, recipe scaling. Worth noting upfront: this uses more tokens, so it burns through free quotas faster.
Prompt Chaining: A 4-Step Template for Breaking Up a Big Task
A workflow mindset office workers can copy directly. Complex tasks (writing a proposal, building a report) done in one giant prompt come out poorly; this teaches you to split it into four steps — outline → expand each section → proofread and polish → convert to bullet points — with the output of each step feeding the next, plus four ready-to-use Traditional Chinese prompts. You can even change direction mid-task by rerunning just one step instead of starting over.
Meta-Prompt: Use AI to Turn Your Bad Prompt Into a Good One
A reusable Traditional Chinese 'prompt optimizer' incantation — paste in a rough prompt and it first asks for the key missing details, then produces a well-structured version along with notes on what changed and why. Honestly flags its limits: a meta-prompt can fix structure and phrasing, but not factual errors in the content itself.
Mock Interviewer: Industry Persona, One Question at a Time, Bilingual
A turn-based mock interview: the interviewer asks scenario-based questions tailored to your industry, one at a time, follows up on your answer before giving feedback, and provides a speakable English version of the answer for each question. After eight questions, you get an overall hiring-likelihood assessment. Closer to a real interview than just reading past questions.
Boss Message Reply Generator: Handle Pressure, Pushback, and Extra Asks
For a boss's urgent demands, pushback, or last-minute extra work, this first diagnoses what they actually need (reassurance? a scapegoat? just an update?), then gives short, full, and escalation-ready reply options with risk notes for each. Built-in red-line check: it refuses goals that would require lying and offers an honest alternative instead.
Plain English to SQL: Describe What You Want, Get the Query
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.
Decision Matrix: Get Unstuck Between Two or Three Options
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.
Cold Outreach Emails That Get Replies: A 4-Line Template That Doesn't Read Like a Sales Pitch
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.
Sales Objection Handler: What to Say to 'Too Expensive / Let Me Think / No Time'
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.
Gemini 2.5 Pro: Drop a Screenshot, Get Your Next Steps
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.
Self-Critique Revision Loop: Draft, Self-Criticize, Revise — Three Rounds of Polish in One Prompt
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.
Rubric-Driven Output: Tell AI What a Perfect Score Looks Like First
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.
The Anti-Goal Sandwich: One Line to Stop AI's Most Common Mistake
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.
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 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.
Onboard New Hires to a Codebase with Gemini
Upload the whole repo or its key files, and Gemini gives new hires a reading order to understand the codebase within an hour
Reverse-Engineer a UI Bug from a Screenshot with Gemini
Paste 1-3 screenshots (browser / Figma / app) and Gemini pinpoints the visual problem + the fix