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.
Lock in a design system (primary color, font weight, grid) as text, then generate 16:9 slide visuals page by page in a consistent style. Great for pitch decks, proposal presentations, and internal training materials — avoids the disaster of every slide drifting into a different style.
Lock the shop name in quotes first, then generate a realistic storefront sign mockup with crisp, undistorted Traditional Chinese strokes. Good for pre-launch brand visual pitches; to be honest, a commercial vector file still needs a designer's redraw — this prompt is only meant to get you a directional preview.
Nail down the main copy, discount numbers, and CTA button placement for a promo banner one by one, then lock the wording with quotes to produce a banner ready to publish. Great for e-commerce sales events and social ads — swap three variables to reuse it repeatedly.
Write your Instagram account's visual rules out as a text-based design system, then generate images continuously in the same conversation so every post looks like it came from the same account. Great for personal branding and social scheduling; if the style starts drifting, just repaste the design-system paragraph to pull it back in line.
Upload a person photo, a product photo, and a scene photo separately, and clearly specify in the prompt who is the subject, what object is being placed, and what serves as the environment, compositing them into a commercial-looking shot that reads as if it were actually photographed. The key is a declaration for unified lighting and undistorted product labels — great for small e-commerce sellers who can't afford a real model shoot.
The biggest fear when making brand character posts, picture-book pages, or a social series is the character changing by the second image. This prompt separates 'locked' elements from 'variable' ones: the face, fixed features, and style stay locked while only the pose and setting change per image. Generate one image at a time, reusing the same opening instructions, to keep the whole series stable.
When a brand or club needs a mascot IP, what's actually needed isn't a single cute image but a character reference sheet with front, side, and back views laid out together. This prompt locks down the layout requirements for cross-angle consistency, standing pose, and an expression-variation zone, producing a sheet you can use as the reference for every generation that follows.
Turn a phone selfie into a formal headshot: swap in a solid-color background, formal attire, a front-facing pose, and even lighting, while a preservation clause locks down the facial features so you don't get beautified into someone else. Good for resumes, employee badges, and LinkedIn avatars; most official ID documents require an unretouched real photo, so weigh the risk of rejection honestly before using this for that purpose.
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.
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.
The worst part of writing a year-end self-review is not being able to remember what you did all year, and then having it come out reading like a diary log anyway. This prompt lets you dump in a whole batch of weekly reports, calendar events, or scattered notes, and the AI organizes them into 3-5 achievement themes, fills in quantified phrasing, and aligns everything with company goals to produce a formal self-review. It also includes a "raise negotiation" version you can use directly when discussing salary.
Pulling a report but not knowing how to write the 'so what' is the most common sticking point in data work. This prompt has the AI act as a senior data analyst, interpreting the data you paste in through a three-layer structure—observation, hypothesized cause, recommended action—while forcing a hard distinction between 'conclusions directly supported by the data' and 'speculation that still needs verification,' so you don't get called out in a meeting for over-interpreting.
When you're assigned to run training or onboard new hires, the time-consuming part isn't knowing the content — it's arranging it into an order you can actually teach. This prompt uses the basic instructional-design framework (objectives, motivation hook, explanation, practice, assessment) to produce a complete lesson plan, including time allocation, interaction design, and points where learners tend to get stuck. Works for corporate training, new-hire onboarding, and club/community teaching.
The biggest problem with handover documents is that everything you consider obvious never gets written down. This prompt has the AI act as a handover reviewer, first using structured questions to draw out the tacit knowledge in your head (who to contact, where passwords live, what has to happen every month, where the landmines are), then organizing it into a handover manual the successor can actually follow. Useful before resigning, transferring roles, or taking extended leave.
A full Suno support thread from one user: wrote their own lyrics, generated with Suno, distributed via Amuse, published through Musixmatch — then tried to make an acoustic version, and Suno blocked it entirely with a copyright error. Suno officially confirmed this is a platform-level limitation.
The RefineAnything LoRA + ComfyUI-RefineNode plugin automate the painful "fix one area, leave the rest untouched" task. A lifesaver for product-image flaws, logos, text, and label repair.
Installs a focused 'security auditor' subagent into Claude Code that reviews code and architecture file-by-file through an OWASP Top 10 lens as you develop features, classifying vulnerabilities by severity with directly-applicable remediation suggestions.
Installs a dedicated 'performance engineer' subagent into Claude Code that profiles code you've just written, finds bottlenecks like N+1 queries, memory leaks, and slow APIs, classifies them by impact, and provides before/after optimization recommendations with benchmark estimates.
A PostToolUse hook that makes Claude Code automatically run a formatter (Prettier/Black/gofmt) plus a linter every time it edits or writes a file—permanently removing 'inconsistent formatting' as a code review chore.
A PreToolUse Bash hook that intercepts destructive commands like rm -rf, fork bombs, and curl|sh before the AI executes them—a last line of defense that holds even against --dangerously-skip-permissions.
A single npx command generates an information-rich terminal statusline for Claude Code, showing the current directory, Git branch, model, a context-usage progress bar, real-time spend burn rate, and a countdown to usage reset—hooked into live ccusage stats.
Borrowing the three-layer architecture from buildermethods/agent-os (Standards / Product / Specs): have AI first scan your codebase to extract existing conventions into documented standards, then auto-inject them every time it writes code — so you never have to re-explain the rules.
Rewrites awesome-cursorrules' Go backend scalability standard into an AGENTS.md/CLAUDE.md covering idiomatic error handling, context propagation, interface abstraction, concurrency, and observability — so AI follows standard conventions and trade-off analysis when writing Go services.
A ready-to-paste ~/.codex/config.toml template that sets up OpenAI Codex CLI's approval policy, sandbox isolation, reasoning effort, and multiple profiles in one go — balancing automation efficiency with safety boundaries.