Software Engineering
React Component Refactor
Refactor legacy Class components to modern Hooks, ensuring all tests pass
Open in generator53 ready-to-paste prompts for working with Claude Fable5 — across creative writing, research, coding, marketing, learning, productivity, and review. Fill in the [brackets], copy, and paste into your Claude app.
Eleven real-world agent configurations — each opens in the prompt generator with task type, autonomy, and advanced modules pre-filled. Tweak and copy the full system prompt from there.
Software Engineering
Refactor legacy Class components to modern Hooks, ensuring all tests pass
Open in generatorSoftware Engineering
Systematically diagnose and fix REST API performance bottlenecks and error handling
Open in generatorSoftware Engineering
Implement complete user authentication from scratch: frontend, backend, and database
Open in generatorResearch & Analysis
Comprehensive analysis of competitor features, pricing, and market positioning
Open in generatorResearch & Analysis
Evaluate and compare multiple technology options with evidence-based recommendations
Open in generatorData Processing
Build an automated data cleaning and transformation pipeline with standardized output
Open in generatorData Processing
Analyze server logs to identify anomaly patterns and generate visual reports
Open in generatorContent Creation
Write complete, clear developer documentation for APIs or open-source projects
Open in generatorContent Creation
Write landing page copy for SaaS products emphasizing core value propositions
Open in generatorAgentic Workflow
Act as a CI/CD agent to automatically review PRs with structured suggestions
Open in generatorAgentic Workflow
Automatically execute a complete research workflow: collection, analysis, writing
Open in generator42 single-message prompts across 7 categories. Pick a category, fill in the [brackets], and copy.
Write a [genre] short story set in [setting], told from the perspective of [character]. Keep it under [400] words, with a clear beginning, turn, and ending. Tone: [folktale / noir / hopeful].
Create a world-building brief for [world name]: geography, political tension, one daily-life detail, and one unresolved mystery. Format as four short sections with headers.
Write the same 120-word monologue three times, in three distinct voices: [a weary mentor], [an overconfident rookie], [a quiet observer]. Label each version.
Write a dialogue-only scene between [character A] and [character B] who disagree about [topic]. No narration. End on an unspoken compromise.
Write a [12]-line poem about [subject] that never names it directly. Use concrete imagery only — no abstract nouns.
Critique the following opening paragraph for pacing, voice, and hook strength. Quote specific phrases, then suggest one rewrite. Text: [paste].
Compare [option A] and [option B] for [use case]. Return a table with criteria rows: cost, learning curve, ecosystem, risks. End with a 2-sentence verdict and a confidence level.
List every assumption hidden in this claim: "[claim]". Mark each as testable or untestable, and suggest how to verify the top three.
Summarize the key arguments for and against [topic] in under 250 words. Attribute each argument to its typical proponents and note where the evidence is weakest.
Give pros, cons, and a final verdict on [decision]. Limit to 5 bullets each, ranked by importance to [stakeholder].
Given these figures: [paste data], describe three trends, one anomaly, and one question the data cannot answer. Avoid speculation beyond the numbers.
Steelman the strongest case FOR and AGAINST [position] in two 150-word passages, then identify the crux that actually separates them.
Here is an error and the relevant code: [paste]. List the three most likely root causes in order of probability, the fastest way to confirm each, and the minimal fix.
Review this function for correctness, readability, and edge cases: [paste code]. Point to specific lines, then show a revised version.
Propose a refactor plan for [module description] that can ship in [3] small, independently testable steps. Note the risk of each step.
Write [unit] tests for this function covering the happy path, boundary values, and one failure mode: [paste code]. Use [framework].
Explain what this code does as if to a developer new to [language], then list two things that could break under load: [paste code].
Critique this API endpoint design for naming, status codes, and versioning: [describe endpoint]. Suggest a corrected spec.
Generate 5 headline variants for [product] aimed at [audience]. Vary the angle: outcome, pain point, curiosity, social proof, urgency. Max 9 words each.
Write a landing-page hero for [product]: headline (max 8 words), subheadline (max 20 words), and 3 benefit bullets. Tone: plain, confident, no hype words.
Draft a 3-email onboarding sequence for [product]: welcome, activation nudge, social proof. Subject lines plus 80-word bodies. One clear CTA per email.
Write a positioning statement for [product]: for [audience] who [need], unlike [alternative], it [key difference]. Then translate it into one casual sentence.
Turn this announcement into 3 platform-specific posts (X, LinkedIn, newsletter blurb): [paste announcement]. Match each platform's tone and length norms.
List the top 5 objections [audience] would have to [offer], and write a one-paragraph response to each that concedes what's true before countering.
Explain [concept] to someone new to the field. Use one everyday analogy, one concrete example, and end with the single most common misconception.
Build a [4]-week study plan for learning [skill] at [2] hours per week. Each week: a goal, the type of resource to use, and one self-test. Assume no prior background.
Create a 10-question quiz on [topic]: 6 multiple choice, 3 short answer, 1 applied scenario. Include an answer key with one-line explanations.
Act as a Socratic tutor on [topic]. Ask me one question at a time, adapting to my answers. Never explain directly until I ask or fail twice.
Give three analogies for [concept] drawn from [cooking / sports / city planning], and note where each analogy breaks down.
Here is my understanding of [topic]: [paste]. Identify what's right, what's subtly wrong, and what's missing — in that order.
Draft a [30]-minute meeting agenda to decide [decision]: pre-reads, 3 timed discussion blocks, a decision protocol, and owner assignments.
Here is my task list: [paste]. Group into Now / Next / Later using impact vs urgency, flag anything delegatable, and identify the one task that unblocks others.
Turn this idea into a one-page project brief: [idea]. Sections: problem, success metric, scope (in/out), risks, first milestone.
Build a weighted decision matrix for choosing between [options] using criteria: [list them, or propose 5]. Show the scoring and how sensitive the result is to the weights.
Run a written retrospective on [project]: what worked, what didn't, what we'd change, plus one experiment for the next cycle. Keep each section to 3 bullets.
Summarize this thread and draft a reply: [paste]. The reply should confirm decisions, list open questions, and propose the next step in under 120 words.
Review this prompt for ambiguity, missing context, and potential for harmful or biased output: [paste prompt]. Suggest a safer, clearer rewrite.
List every factual claim in this text and rate each: well-established / needs source / likely wrong. Text: [paste].
Identify framing, selection, and wording bias in this passage: [paste]. Rewrite one paragraph in a neutral register.
Flag any personal or identifying information in this text and return a redacted version with placeholders: [paste].
Evaluate this source for reliability: [link or description]. Score authorship, evidence, recency, and incentives from 1–5, with one-line justifications.
Before I publish this, check for: unsupported claims, tone slips, missing caveats, and legal red flags. Return a pass/fix table. Text: [paste].
Templates work because they pin down the parts models guess at: the role, the audience, the output format, and the limits. Replace every bracket before running — a half-filled template produces vague output. Change one variable at a time when iterating, so you know what caused the improvement.
When a customized version works well, save your own copy; the best template library is the one you grow yourself. For long-running agent tasks, start from a system-prompt preset above and refine it in the generator.
Common questions about using these prompt templates.
Know the Claude Fable5 cost math, the safeguard behavior, and the right tier before you commit. Create a free account to get notified when specs, prices, or access channels change.