Kimi K3 is now availableExplore Kimi K3
Claude Fable 5 prompt gallery hero background

Claude Fable 5 Prompts

Reusable prompt patterns drawn from real Claude Fable 5 use cases — coding, agentic automation, interactive builds, frontend design, and long-context research. Copy and run.

Browse prompt templates built from real-world Claude Fable 5 use cases, then continue to the model page to run them on EvoLink.

Featured Claude Fable 5 Prompt Examples

A curated set of reusable prompts, expanded over time. For more real-world use cases, open the GitHub guide.

Coding & Refactoringcoldopn on X
AgenticAdvanced

Rebuild An App UI From A Screenshot

Turns a single screenshot of an existing product into a working, functional clone of its interface.

Here is a screenshot of [PRODUCT NAME]'s interface: [ATTACH SCREENSHOT]. Recreate this UI as a working [FRAMEWORK / SINGLE HTML FILE] app with REAL functionality, not a static mockup. - Match the layout, spacing, and visual hierarchy in the screenshot as closely as you can. - Implement the core interactions I would actually use: [LIST KEY FEATURES, e.g. navigation, search, create/edit items]. - Wire up local state so buttons, forms, and lists genuinely respond. Work autonomously until it runs, then tell me what you approximated and what still needs real backend wiring.

reverse-engineeringui-clone
Coding & Refactoringmeta_alchemist on X
Long contextAdvanced

Repo Audit And Improvement Plan

Runs a principal-engineer-level audit of a repository and returns a prioritized, evidence-cited improvement plan.

You are a principal-level software engineer and technical auditor. Deeply analyze this repository and deliver an honest audit plus a prioritized, actionable improvement plan. Ground every claim in actual files: cite file paths and line numbers. If you cannot verify something, say so. Work through these phases in order, do not skip ahead: 1. Map the architecture, key modules, and how data flows through [PROJECT NAME]. 2. Find correctness bugs, security issues, and [SPECIFIC CONCERN, e.g. performance hot paths]. 3. Flag dead code, duplication, and risky patterns worth refactoring. 4. Produce a ranked improvement plan (impact vs effort) with concrete next steps.

auditrefactoring
Coding & RefactoringPilgrim6938 on X
Long contextExpert

Diagnose And Fix A Bug In A Large Codebase

Traces a hard bug across a large repository, pinpoints the root cause, and returns a review-ready fix.

This repository has roughly [LINE COUNT] lines. There is a bug: [DESCRIBE THE SYMPTOM, e.g. cache never invalidates after an update]. Do a full investigation before proposing anything: - Trace the relevant call chains end to end, including hidden or indirect calls. - Identify the true root cause, not just the surface symptom, and cite the files and lines involved. - Propose a complete fix that a reviewer could merge, covering edge cases and any affected callers. Explain your reasoning and list anything you were unsure about so I can verify before merging.

debugginglarge-codebase
Agents & Automationayushagarwal on X
AgenticExpert

Diagnose A Production Outage And Open A Fix PR

Investigates a live infrastructure outage across logs and services, finds the cause, and opens a fix PR.

Something is broken in [ENVIRONMENT, e.g. my self-hosted k8s cluster] and I cannot describe it precisely. Investigate and fix it. You have access to [AVAILABLE TOOLS, e.g. kubectl, database query access, container registry]. Work autonomously: - Read pod/service logs and error logs from [DATA SOURCES] to find what actually changed. - Compare deployed versions, image digests, config, and migrations to spot mismatches. - Form a hypothesis, verify it against evidence, then open a PR with the fix and a clear write-up. Do not ask me to hand-hold each step; report your findings and the PR when done.

incident-responsedevops
Agents & Automationoutsource_ on X
AgenticExpert

Autonomous Build-Test-Play Loop

Sets up a hands-free loop where the agent keeps building, testing, and smoke-testing a project until it is done.

Build [PROJECT NAME] to completion by running an autonomous loop, hands-free, until every item in the spec is met. The spec / definition of done is: [SPEC OR CHECKLIST]. On each iteration: - Implement the next unfinished piece. - Build it, run the tests, and smoke-test the actual behavior (launch it, exercise it, [e.g. play the level]). - If something fails, diagnose and fix it, then re-verify before moving on. Keep a running log of what is done, what changed, and what remains. Continue on autopilot until the checklist is fully satisfied.

autonomouslong-horizon
Agents & Automationoikon48 on X
AgenticAdvanced

Goal-Driven Workflow With Self-Verification

Frames a task as a goal the model pursues until done, then verifies each part and reports what differed.

Set a goal to fully implement this spec, then keep working until it is genuinely complete: [SPEC]. Context you should know: [BACKGROUND AND CONSTRAINTS, e.g. this is experimental and may be removed in a month, so keep it easy to delete]. Then run a workflow that verifies each part of the plan independently: - For every requirement, check the real behavior against what was asked. - Note anything that differs from the spec or that you had to interpret. Prepare a short report of what was implemented, how you verified it, and where reality diverged from the plan.

goalworkflow
Games & Interactiveai_for_success on X
Single promptIntermediate

Gesture-Controlled Runner Game

Builds a browser endless-runner controlled by hand or finger tracking through the webcam, in one file.

Build a browser-based endless-runner game controlled by [INPUT, e.g. finger/hand tracking via the webcam]. Requirements: - Use [LIBRARY OR APPROACH, e.g. a hand-tracking library] to map [GESTURE, e.g. raising a finger] to the jump action. - Add obstacles, increasing speed, a score counter, and a game-over/restart flow. - Keep it self-contained and runnable as a single [HTML file / small project] with no build step. Handle camera permission gracefully and keep it at a smooth frame rate.

gamewebcam
Games & Interactivekieradev on X
Single promptAdvanced

One-Shot Kart Racing Game

Generates a complete arcade kart racer with tracks, characters, modes, music, and UI from a short prompt.

Build a complete arcade kart-racing game in the style of [REFERENCE, e.g. Mario Kart 64]. Include, generated by you, no external assets: - At least [N] tracks with distinct themes and decoration. - Driveable characters/karts with simple models and handling. - [GAME MODES, e.g. grand prix, time trial, versus], plus background music and sound. - A full UI: menus, HUD, lap and position tracking, and results screen. Keep controls responsive and ship it as a runnable project I can start immediately.

game3d
Games & Interactiveydamitcodes on X
AgenticAdvanced

Voxel Sandbox Game Clone

Builds a playable voxel sandbox with terrain, mining, day/night, and mobs from a single prompt.

Build a playable voxel sandbox game in the style of [REFERENCE, e.g. Minecraft]. Include: - Procedurally generated terrain with [FEATURES, e.g. biomes, caves, ores]. - Block placing and mining with a simple inventory. - A day/night cycle and basic [MOBS/ENTITIES] with simple AI. - First-person movement, collision, and mouse-look controls. Target [TECH, e.g. a single HTML file with WebGL / a Rust project] and keep a steady frame rate. Build it end to end, testing as you go.

gamevoxel
Frontend & Designintheworldofai on X
Single promptAdvanced

Desktop OS In A Single HTML File

Generates a full desktop-OS web experience with windows, a dock, and working apps in one HTML file.

Build a full [STYLE, e.g. macOS-style] desktop operating system as a single self-contained HTML file with embedded CSS and JS. Include: - A menu bar and dock, plus draggable and resizable app windows. - Working built-in apps: [APPS, e.g. file explorer, terminal, settings, browser mockup]. - Desktop icons, notifications, themes, and a boot screen. - [BONUS, e.g. a small working sound player using real synthesis, or a mini game inside the desktop]. Make it feel real and responsive, generated in one pass with no external files.

uisingle-file
Frontend & Designecomchasedimond on X
Single promptIntermediate

Premium Ecommerce Email Mockup

Designs a realistic, full-length vertical ecommerce email mockup for a brand in a single pass.

Create a full-length, tall vertical ecommerce email mockup for [BRAND], a [CATEGORY] brand for [AUDIENCE]. Design a highly realistic premium DTC email that feels sleek, polished, and editorial, like a real designer-made email screenshot, not a poster, landing page, or generic template. Brand vibe: [ADJECTIVES, e.g. modern, confident, clean, aspirational]. Feature these products prominently: [PRODUCT LIST]. Include a hero, product sections with real-feeling copy, and a clear call to action. Use realistic typography, spacing, and imagery placement.

designemail
Frontend & Designscottstts on X
Single promptAdvanced

Navigable 3D Scene From A Floor Plan

Builds a first-person walkable 3D room in Three.js that faithfully follows a supplied floor plan.

In Three.js, create a first-person, navigable 3D scene of [PLACE, e.g. the iconic apartment from a TV show] based on this floor plan: [ATTACH FLOOR PLAN]. - Stay true to the original look and feel: layout, furniture placement, colors, and materials. - Use [LIGHTING STYLE, e.g. warm interior lighting] and sensible shadows. - Let me walk around with WASD and mouse-look, with collision so I cannot pass through walls. Deliver it as a single HTML file. Verify your result visually against the floor plan and iterate until the geometry matches.

3dthreejs
Docs & Researchmanaltdan on X
Long contextIntermediate

Track-Changes Review Of A Long Document

Does a full read-through of a long document and returns track-changes edits, challenges, and sources.

Do a full, careful read-through of this [DOCUMENT TYPE, e.g. policy memo]: [PASTE OR ATTACH DOCUMENT]. Return your review in three layers: - Fluency edits: tighten wording and flow, shown as clearly marked track changes. - Comments: flag shaky or unsupported claims and ask the questions a sharp reviewer would. - Sources: suggest specific references or data that would strengthen or verify the weak points. Preserve my voice and argument; do not rewrite it into your own style. Keep the changes suggestion-style so I can accept or reject each one.

editingreview
Docs & Researchnaoyafujiwara on X
Long contextIntermediate

Structured Deep-Research Brief

Answers a big open question with a deep yet cleanly structured analytical brief.

Research and answer this question in depth: [QUESTION]. Frame it around a specific premise: [PREMISE OR ANGLE, e.g. treat the timeline as starting from a particular year rather than the conventional one]. Structure the answer as: - What actually happened: the concrete events, decisions, and turning points. - Why it happened: the underlying causes and how they compounded. - What it means going forward: implications for [TIME HORIZON / DOMAIN]. Go deep on substance but keep the surface clean and readable. Cite specific figures, dates, and facts, and flag where the evidence is contested.

researchanalysis
Docs & Researchgabepereyra on X
Long contextAdvanced

Draft An S-1 Registration Statement

Drafts a properly structured, long-form S-1 registration statement for a given company.

Draft an S-1 registration statement for [COMPANY], a [DESCRIPTION] company. Follow the standard S-1 structure and produce genuinely long-form content, not an outline: - Prospectus summary, risk factors, use of proceeds, and MD&A. - Business description, competition, and market opportunity. - Selected financial data and management/ownership sections. Match the tone, formatting, and structure of a real filing. Where you would need actual numbers, use clearly labeled placeholders such as [FY2025 REVENUE] rather than inventing figures.

legalfinance

How To Write Better Claude Fable 5 Prompts

State the goal, then the constraints — what to keep, what not to touch, which libraries are allowed.
Ask for a plan before code on anything non-trivial, so you can catch a wrong approach cheaply.
Require verification: tests, typecheck, or a run — "looks done" is not done.
Tell it to flag assumptions and ambiguities instead of silently guessing.

Claude Fable 5 Prompt FAQ

What is Claude Fable 5 best at?

Fable 5 is Anthropic's most capable model, a tier above Opus, with state-of-the-art coding, reasoning, and agentic ability plus a 1M-token context window. It is strong at multi-file coding, long agentic runs, refactoring, and synthesizing very large documents.

How is this different from an image or video prompt page?

Fable 5 is a text, coding, and agent model, so these prompts are reusable instructions you paste into a chat, a coding agent, or the API — not media generation prompts. Each card shows the full prompt with notes on why it works.

How do I write a good Fable 5 prompt?

Separate the goal from the constraints, ask for a plan before code on complex tasks, require explicit verification, and tell the model to flag assumptions rather than guess. The framework section on this page breaks this down.

Can I use these prompts inside Claude Code or my own tools?

Yes. These are model-agnostic prompt patterns. With EvoLink you can point Claude Code or any OpenAI-compatible client at our endpoint and run Fable 5 with the same prompts.

How do I use these prompts with EvoLink?

Click Copy on a prompt card, replace the [PLACEHOLDERS] with your own details, then run it against Fable 5 through EvoLink — in the API, in Claude Code, or in any OpenAI-compatible client pointed at our endpoint. The model page has pricing and connection details.