프롬프트 라이브러리

API Rate Limiting taste of a backend platform engineer

• Rate limit every public endpoint from day one, including authenticated ones; abuse rarely announces itself in advance. Confidence: 0.90
• Key limits on the authenticated identity (API key, user or tenant) first and fall back to client IP only for anonymous traffic. Confidence: 0.90
• Use a token bucket or sliding-window counter instead of a fixed window, so clients cannot burst twice the limit at window edges. Confidence: 0.85
• Keep limiter state in a shared store like Redis with atomic operations (Lua script or INCR plus EXPIRE), never in per-instance memory behind a load balancer. Confidence: 0.90
• Return HTTP 429 with a Retry-After header and a machine-readable error code in the body. Confidence: 0.95
• Send RateLimit-Limit, RateLimit-Remaining and RateLimit-Reset headers on every response so clients can pace themselves. Confidence: 0.80
• Set separate, tighter limits for expensive operations (search, exports, login, password reset) than for cheap reads. Confidence: 0.90
• Weight requests by cost when endpoints differ a lot, for example a bulk call spending 10 tokens instead of 1. Confidence: 0.70
• Fail open on limiter outages for ordinary traffic, but fail closed on authentication and payment endpoints. Confidence: 0.75
• Apply a coarse global limit at the edge (CDN or gateway) and finer per-tenant li

Python Type Hints taste of a typed-Python maintainer

• Run a type checker (pyright or mypy) in CI on every pull request and treat new errors as build failures. Confidence: 0.95
• Start strict on new code with strict = true and loosen per module only with a written reason, instead of starting loose and tightening never. Confidence: 0.80
• Use modern built-in generics like list[str] and dict[str, int] and X | None instead of importing List, Dict and Optional from typing. Confidence: 0.90
• Annotate every public function signature, including the return type; let local variables be inferred unless inference is wrong. Confidence: 0.90
• Accept abstract types in parameters (Iterable, Mapping, Sequence) and return concrete types (list, dict). Confidence: 0.85
• Prefer Protocol for structural interfaces over abstract base classes when callers should not have to inherit anything. Confidence: 0.75
• Model fixed-shape records with dataclass (or pydantic at I/O boundaries) instead of passing raw dicts around. Confidence: 0.90
• Use TypedDict only for dict-shaped data you do not control, such as JSON payloads and legacy APIs. Confidence: 0.75
• Represent a closed set of string options with Literal or an Enum, never a bare str. Confidence: 0.85
• Treat Any as a bug report: confine it to the boundary where untyped data enters and narrow it immediate

You are a careful household product safety assistant. Help me build and maintain a recall check and product registration tracker for the products in my home, then return the result as JSON only, matching the schema below exactly.

My inputs (fill in what you know; leave blank if unknown):

• Country or region: [e.g., United States, United Kingdom, EU country, Canada, Australia]
• Household notes: [e.g., baby or toddler at home, older adults, pets, renter or owner]
• Product list, one per line: [category | brand | model name or number | approximate purchase date | where bought | serial or batch number if known | registered with maker? yes/no]

Example: Car seat | BrandX | Model 300 | 2025-03 | online store | SN unknown | no

Instructions:

1. Normalize each product: category, brand, model, purchase date, retailer, and which identifiers I still need to find (model number, serial, batch or lot code, date code). Tell me exactly where such labels usually are for that kind of product (base, back panel, inside the door, under the seat, on the battery, on the packaging).
2. Rank each product's recall-check priority as high, medium or low. Treat as high: child car seats, cribs and other sleep products, strollers, high chairs, heaters, dehumidifiers, pressure cookers, power banks and e-bike or scooter batteries, smoke and carbon monoxide alarms, gas appliances, extension cords and vehicle

name: fashion-showcase
description: create humanize movement for fashion outfit showcase
---

My Skill

Describe what this skill does and how the agent should use it.

Instructions

• Step 1: ...
• Step 2: ...

Step 1 — Image (Nano Banana 2.1): generate the product poster

An epic minimalist poster for a walkman product called Explo, all in matte white style colors, thin font, the product has a slight neon glow around it, dark blank background.

Step 2 — Video (Gemini Omni 1.2 Flash): use the Step 1 image as the reference

Using the attached reference photo, create a sequential layer style animation where each section of the product pieces together smoothly with an Exploded View. The camera crash zooms and moves to focus on each sequential element as it is added. The final shot reveals the full product.

Tokio Async Rust taste of a production service engineer

• Use #[tokio::main] only in the binary and keep library crates runtime-agnostic where practical, taking futures and handles as inputs. Confidence: 0.80
• Never block the async runtime; move CPU-heavy or blocking I/O work to spawn_blocking or a dedicated thread pool. Confidence: 0.95
• Use tokio::sync::Mutex only when a lock must be held across an .await; otherwise use std::sync::Mutex or parking_lot for short critical sections. Confidence: 0.90
• Prefer message passing with bounded mpsc channels over shared mutable state, and size every channel deliberately for backpressure. Confidence: 0.85
• Never use unbounded channels in request paths, because a slow consumer turns into unbounded memory growth. Confidence: 0.85
• Put a timeout on every network call with tokio::time::timeout or a client-level setting; no await on the network should be able to hang forever. Confidence: 0.95
• Use JoinSet or TaskTracker to own spawned tasks so they are awaited, cancelled and their errors are observed. Confidence: 0.85
• Treat every .await as a possible cancellation point and keep state consistent if the future is dropped there. Confidence: 0.85
• Use select! carefully and only with cancel-safe branches; document why each branch is safe to drop. Confidence: 0.80
• Implement graceful shutdown with a `CancellationT

name: quoter
description: Searches quote databases (AZQuotes, BrainyQuote, Quotes.net) by author or media (books, movies, TV shows, interviews, articles). Returns candidate quotes in sets of 5, handles accurate attribution correction for book characters, and formats user-selected quotes in a standard citation template.
---

Quoter

Search, retrieve, and standardize quote attributions from web quote databases.

When to Use

Use this skill whenever the user asks to:

• Find quotes by a specific author, book, movie, TV show, interview, article, or newspaper.
• Retrieve quotes from AZQuotes (https://www.azquotes.com/), BrainyQuote (https://www.brainyquote.com/), or Quotes.net (https://www.quotes.net/).
• Attribute character quotes from books/media accurately to both the character and the actual author/creator.

Core Workflow

Step 1: Query & Search Strategy

When searching for quotes:

1. Target external databases (AZQuotes, BrainyQuote, Quotes.net) or perform targeted web searches filtered by the requested topic, author, or media source.
2. Group and present candidates in batches/sets of 5 quotes at a time.
3. Number candidates 1 through 5 in each batch so the user can easily select their choices.

Step 2: Fix Misattributed Book & Media Character Quotes

Many quote aggregator databases (notably AZQuotes) attribute quotes spoken by fictional characters directly

Tailwind CSS taste of a utility-first UI engineer

• Configure design tokens (colors, spacing, radii, fonts) once in the Tailwind theme and never hardcode hex values or arbitrary pixel sizes in markup. Confidence: 0.90
• Prefer theme-scale utilities over arbitrary values like w-[437px]; treat each arbitrary value as a missing token to add or a design to question. Confidence: 0.85
• Extract repeated utility groups into components (React, Vue, Svelte) rather than @apply classes in CSS files. Confidence: 0.85
• Reserve @apply for styling third-party markup or CMS content you cannot add classes to. Confidence: 0.75
• Use prettier-plugin-tailwindcss so class order is automatic and never argued about in review. Confidence: 0.95
• Build class names from complete static strings; never concatenate fragments like text-${color}-500, because the scanner cannot see them. Confidence: 0.95
• Use clsx plus tailwind-merge (or a cn() helper) so component props can override default classes without conflicts. Confidence: 0.85
• Model component variants with a typed variant helper such as cva instead of long ternary chains in className. Confidence: 0.80
• Write mobile-first: unprefixed utilities are the base and sm:, md:, lg: only add changes for wider screens. Confidence: 0.90
• Use container queries (@container, @md:) for reusable components whose layout depends on

Start from the previous step image "Whitewashed Santorini Cliffside Village with Blue Domes at Golden Hour" as the exact first frame, and animate it into a calm ${duration:6}-second cinematic shot. Keep the sea on the left with the sun and gold path, the whitewashed village on the right, the two blue domes (larger center-right, one slightly lower), volcanic cliff rock, warm golden-hour light, haze, and style exactly as in the image. The camera makes a slow gentle push-in toward the larger blue dome. Subtle sun glitter shimmers on the sea; very light atmospheric haze drifts softly. Architecture stays locked. Natural, realistic motion, no large crowds, no close faces, no cuts, no text, no logos. Soft evening ambience, distant quiet air.

Act as an expert technical recruiter, career coach, and professional CV writer.

Create a job-winning, ATS-friendly CV tailored to a specific job advert. Use only the information I provide. Do not invent employers, job titles, dates, qualifications, skills, projects, or achievements. If important information is missing, ask me up to 5 targeted questions before writing the CV.

MY INFORMATION

• Full name: ${full_name}
• Location: ${location}
• Phone: ${phone}
• Email: ${email}
• LinkedIn / GitHub / portfolio: ${links}
• Current or most recent job title: ${current_title}
• Years of experience: ${years_experience}
• Target job title: ${target_job_title}
• Job advert: ${job_advert}
• Work experience: ${work_experience}
• Education and certifications: ${education_certifications}
• Technical skills, tools, and programming languages: ${skills}
• Projects, achievements, awards, or volunteering: ${projects_achievements}
• Preferred CV length: one page / two pages

TASK

1. Analyze the job advert and identify the most important requirements, responsibilities, keywords, and seniority signals.
2. Identify which of my skills and experience should be emphasized for this specific role.
3. Create a clean, professional CV with these sections:
4. Name and contact details
5. Professional summary
6. Core skills
7. Professional experience
8. Selected projects or portfolio, if relevant

-

Create an ultra-realistic 15-second cinematic historical documentary of the Acropolis of Athens, Greece, during a spectacular golden sunrise. Exactly 15 rapid shots, 1 second each, with clean hard cuts and smooth visual continuity.

Shot sequence:

1. Aerial establishing shot revealing the entire Acropolis above Athens.
2. Smooth drone glide toward the ancient Parthenon.
3. Wide symmetrical view of the Parthenon glowing in sunrise light.
4. Close-up of massive ancient Greek marble columns.
5. Slow tilt-up revealing the magnificent temple architecture.
6. Cinematic orbit around the Parthenon.
7. Close-up of intricate ancient stone carvings and sculptures.
8. Side-angle tracking shot along the majestic columns.
9. Tracking shot across ancient marble pathways.
10. Low-angle hero shot emphasizing the towering columns.
11. Pan across the Erechtheion and its famous Caryatid statues.
12. Golden sunlight illuminating weathered marble textures.
13. Elevated aerial view showing Athens stretching toward the horizon.
14. Close-up revealing ancient architectural details and stone textures.
15. Spectacular aerial pull-back revealing the entire Acropolis beneath the glowing sunrise sky.

Visual style: Photorealistic 4K HDR, premium historical documentary cinematography, authentic ancient Greek architecture, warm golden-pink sunrise, soft atmospheric haze, realistic marble textures, cinematic

Vite Frontend Tooling taste of a fast-feedback web developer

• Start new single-page apps and component playgrounds on Vite with the official framework plugin instead of a custom webpack setup. Confidence: 0.85
• Keep vite.config.ts in TypeScript with defineConfig, and keep it short enough to read in one screen. Confidence: 0.80
• Run type checking separately with tsc --noEmit in CI and in a watcher, since Vite only strips types and never checks them. Confidence: 0.95
• Use path aliases sparingly, define them once in tsconfig.json, and mirror them in Vite with a plugin such as vite-tsconfig-paths. Confidence: 0.75
• Expose only VITE_-prefixed environment variables to client code and never put secrets in them. Confidence: 0.95
• Type import.meta.env in a vite-env.d.ts file so missing or misspelled variables fail at compile time. Confidence: 0.80
• Configure the dev server proxy for backend APIs instead of enabling permissive CORS on the backend just for local development. Confidence: 0.85
• Use Vitest for unit and component tests so tests share the same config, transforms and aliases as the app. Confidence: 0.90
• Lazy-load routes and heavy widgets with dynamic import() and let Rollup split chunks, rather than hand-tuning manualChunks early. Confidence: 0.80
• Inspect bundle size with rollup-plugin-visualizer before releases and treat a large new dependen

Linux Server Hardening taste of a careful operations engineer

• Build servers from a minimal base image and install only the packages a role needs, removing compilers and debugging tools from production hosts. Confidence: 0.85
• Manage every server with configuration as code (Ansible, cloud-init or an image pipeline) and never rely on manual changes that drift. Confidence: 0.90
• Disable SSH password authentication and root login, and allow only key-based or certificate-based logins. Confidence: 0.95
• Prefer short-lived SSH certificates or an identity-aware access proxy over long-lived authorized_keys files copied around. Confidence: 0.75
• Give each engineer a named account with sudo through groups, and never share a common admin user. Confidence: 0.90
• Default the host firewall to deny inbound traffic and open only the ports the service actually listens on. Confidence: 0.90
• Keep SSH and admin interfaces off the public internet, reachable only through a VPN, bastion or private network. Confidence: 0.85
• Enable unattended security updates for the base OS, and schedule reboots so kernel patches actually take effect. Confidence: 0.85
• Run each service as its own unprivileged system user with no login shell. Confidence: 0.90
• Use systemd sandboxing options such as ProtectSystem=strict, NoNewPrivileges=yes and PrivateTmp=yes for every long-running service. Confidence

name: language-editor
description: A professional multilingual language editor that corrects and refines text in any language, improving grammar, spelling, clarity, fluency, and natural expression while preserving the original meaning, intent, and appropriate tone. Ensures polished, authentic, native-level writing with concise, professional results.
---

My Skill

Describe what this skill does and how the agent should use it.

Instructions

• Step 1: ...
• Step 2: ...

name: theme-and-colors
description: study the theme and colors. and then change the whole process for the theme to be better, and change the colors to be better and modern.
---

theme and colors

Describe what this skill does and how the agent should use it.

Instructions

• Step 1: ...
• Step 2: ...