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.
Have the agent interview you about your project, then produce a structured, no-fluff AGENTS.md that spells out build/test commands, code style, commit conventions, and off-limits areas in one shot — auto-loaded every time work starts.
Turns a vague requirement into a full Codex workflow: first force it to nail down a 'definition of done,' use plan mode to produce a plan for your approval, then implement in small steps, run its own tests, and finally produce a reviewable diff with verification evidence.
Once your code changes are done, have Codex read the staged diff, produce a Conventional Commits message, and write a PR description covering background, what changed, why, how it was verified, and risks — without bundling in unrelated changes, exaggerating, or fabricating tests.
Has Codex do a disciplined code review of your git diff across three tracks (correctness bugs / simplification-and-reuse / security), listing each finding with a confidence level and a pastable fix, and explicitly instructed to say so when nothing's wrong instead of manufacturing complaints.
Forces Codex through a closed loop — write a failing test that reproduces the bug, find the root cause, make the minimal fix, watch that same test go from red to green, then run the full test suite to confirm no regressions — eliminating both 'fixed it without verifying' and 'changed a bunch of unrelated stuff along the way.'
Has Codex write characterization tests for untested legacy code: it first reads and documents what the code 'actually does right now' (bugs included), systematically covers the happy path plus edge cases and error paths, and is strictly forbidden from modifying the code under test.
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.
A large-refactor playbook for agents: first do a read-only survey of the 'blast radius' — which files, call sites, and tests are affected — then split the change into small batches, each preserving behavior, each run through its own tests, each its own atomic commit. Puts an end to 'change 40 files at once, then the build breaks and no one knows where to start fixing it.'
An indie slow ballad with local Taiwanese Hokkien storytelling, complete with style tags and lyric structure — ready to drop into Suno.
An '80s-styled Mandarin City Pop love song with synths and funky bass — retro yet catchy.
A custom Mandarin wedding entrance song for the couple — warm, grand, and emotionally on point, with a well-paced section structure.
An 8-second product reveal shot list with professional camera-movement language, ready to feed directly into Veo.
Generates a UGC-style spoken-word ad that looks like it was shot by an ordinary person — natural, unpolished, and well suited to short-form product-selling content.
An advanced workflow: generate two keyframes with Nano Banana first, then hand them to Veo to interpolate into a fully realized camera move.
A soothing macro slow-motion product close-up clip, well suited to beauty, food, and texture-driven products.
Turns a selfie into a realistic product photo of a boxed collectible figure — one of Nano Banana's most viral tricks, built on its strongest asset: consistency.
Turns a single cutout product image into a lifestyle-style e-commerce hero shot of a model holding the product — no reshoot needed.
Restores a yellowed, scratched, or blurry old photo to clarity and colorizes it naturally, while preserving the subject's original appearance.
Convert a portrait into a watercolor, 3D, anime, or other style while keeping the face consistent and unwarped.
No need to memorize regex syntax — describe in plain language what you want to match, and the AI gives you the regex, an explanation of what each part does, and test cases.
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.
Use the Feynman Technique to have AI teach you: first explain it clearly in plain language with an analogy, then flag the point you're most likely to misunderstand, and finish with a self-check.
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.