AIO APEX
en

Prompt & Skill Introduction

Curated AI prompts for business, creative, and technical use cases.
The API Breaking-Change Changelog Writer
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 2.5 Pro for structured technical writing)Developer ToolsYou're a platform engineer at a payments company shipping a breaking webhook schema change that will affect roughly 400 external integrations, and you need to publish a changelog entry and migration guide before the sprint ends today.

The API Breaking-Change Changelog Writer

A structured prompt that turns a breaking API change into a clear changelog entry and step-by-step migration guide, flagging silent-failure risks before they hit your support queue.

developer-experiencetechnical-writing
The AI Decision Audit Trail Writer: Turn an AI-Assisted Call Into a Defensible Compliance Record
Works best with Claude Sonnet 5 or Opus-class models — both reliably follow the "do not fabricate missing fields" constraint and flag gaps instead of inventing plausible-sounding compliance language. GPT-6-class models perform nearly as well. Avoid smaller distilled or local models for this one: they are more likely to smooth over missing information with confident-sounding filler, which defeats the entire purpose of an audit record.Artificial IntelligenceAn HR coordinator used an AI resume-screening tool to auto-reject 40 candidates for a mid-level engineering role on a Tuesday afternoon. On Friday, legal receives a demand letter from a rejected candidate's attorney alleging discriminatory screening, and compliance needs a complete audit-trail record for this specific candidate within 48 hours — including what data went into the AI tool, what it recommended, and who signed off — before legal can respond.

The AI Decision Audit Trail Writer: Turn an AI-Assisted Call Into a Defensible Compliance Record

A structured AI prompt that turns a single AI-assisted decision — a resume screen, a credit call, a moderation action — into a factual audit-trail entry built to survive a regulator or legal-discovery request, with missing information flagged instead of invented.

complianceAI governance
The Flaky Test Triager: Turn Intermittently Failing CI Tests Into a Root-Cause-Ranked Quarantine Plan
Claude Sonnet 5 or GPT-6 — both handle structured multi-column triage well. Needs a model that can hold 15-30 test rows in a table without truncating or re-summarizing them, so avoid smaller distilled models (e.g. Haiku-class) for large test suites — split into batches of about 15 tests at a time if using one.Developer ToolsYour team's CI dashboard has quietly accumulated 18 tests tagged "flaky" over the past two months. Nobody owns the list, and new hires are simply told to click re-run when one of them turns red. On Thursday afternoon, ahead of Friday's release freeze, the QA lead exports the flaky-test tracker — test names, failure rates, and the last few stack traces for each — and runs it through this prompt to get a sprint-ready triage: which tests to quarantine today, which ones trace back to one shared root cause, and which genuinely need another engineer's eyes before anyone touches them.

The Flaky Test Triager: Turn Intermittently Failing CI Tests Into a Root-Cause-Ranked Quarantine Plan

A structured AI prompt that turns a pile of intermittently failing CI tests into a root-cause triage table, a same-day quarantine list, and a sprint plan — built for teams tired of reflexively clicking "re-run".

testingdeveloper tools
The Vendor Bankruptcy Contingency Planner: Turn Vendor Dependency Into a Risk-Ranked Exit Plan
Works with any frontier reasoning model (Claude Opus, GPT-5, Gemini 3). Best results come from a model that can hold the full context dump — contract terms, integration map, vendor signals — in one pass rather than summarizing early; avoid smaller/faster models that tend to compress multi-part context.Business & StrategyYour company's AI-powered customer support chatbot vendor just filed for Chapter 11 bankruptcy — similar to Character.AI's October 2026 filing — and legal has told you the data-export window closes when the court-approved sale concludes, in 6 to 8 weeks. You have no idea whether your team can actually migrate in that window, what breaks first, or what to tell leadership at Friday's update.

The Vendor Bankruptcy Contingency Planner: Turn Vendor Dependency Into a Risk-Ranked Exit Plan

When a vendor you depend on shows signs of financial trouble — or files for bankruptcy outright — this prompt turns panic into a phased contingency plan: exposure, failure cascade, timeline, and ranked alternatives.

risk-managementBusiness Strategy
The Product Packaging Concept Generator: Turn a Brand Brief Into Shelf-Ready Visual Directions
Works with any model capable of image generation for the visual mockups — Nano Banana Pro, Midjourney v7, or DALL-E 3 — paired with a strong reasoning model (Claude Sonnet 5, GPT-5.2) for the concept rationale and naming. The text portion runs on any capable LLM even without image generation, producing a written creative brief a designer can execute manually.creativeYou're the marketing manager at a 12-person DTC beverage startup. Your co-founder wants packaging that "pops on a Whole Foods shelf," you have no in-house designer, and the agency quote for three initial concepts is $8,000 with a three-week turnaround. You need three visually distinct directions to bring into tomorrow morning's founder meeting.

The Product Packaging Concept Generator: Turn a Brand Brief Into Shelf-Ready Visual Directions

A structured prompt that turns a one-paragraph brand brief into three genuinely different packaging design directions — complete with shelf-impact rationale and production notes a founder can bring straight into a design review.

product-designbranding
The On-Call Handoff Writer: Turn a Chaotic Shift Change Into a Clean Incident Handoff
Claude Opus 4.7 or GPT-5 (a structured-reasoning task; any strong general-purpose model works, no need for a specialized coding model)Developer ToolsAn on-call engineer wrapping up a 8-hour shift with three alerts, one resolved incident with a lingering root cause, and a flaky Redis layer, who has ten minutes before the next engineer logs on and needs to hand off clearly instead of firing off a rushed Slack message that leaves out half the context.

The On-Call Handoff Writer: Turn a Chaotic Shift Change Into a Clean Incident Handoff

Stop handing off on-call shifts with a rushed Slack message that leaves out half the context. This prompt turns scattered shift notes into a handoff the next engineer can act on in under five minutes.

The AI Agent Blast Radius Calculator: Turn a Planned Agent Deployment Into a Least-Privilege Access Plan
Claude Opus 4.7 (also works well with GPT-5 and Gemini 2.5 Pro — this is a reasoning task, not one requiring live tool access)Artificial IntelligenceAn engineering team is about to grant an AI coding agent write access to a shared GitHub repo, a staging database, and a Slack webhook so it can auto-triage and fix failing CI tests overnight, and wants to know exactly what could go wrong with that access before flipping the switch, not after.

The AI Agent Blast Radius Calculator: Turn a Planned Agent Deployment Into a Least-Privilege Access Plan

Before you give an AI agent write access to your repo, your database, or your Slack, map out exactly what it could do if it went looking for the shortest path to its goal instead of the intended one.

The Case Study Interview Question Builder: Turn a Vague Customer Win Into a Publishable Story
Works well with Claude, GPT-5, or Gemini — this is a structured-reasoning task, not a creative-writing one, so most current frontier models handle it reliably.A product marketer at a mid-size SaaS company has a 30-minute call scheduled with a VP of Operations at a customer whose onboarding time reportedly dropped significantly after adopting their tool, and needs to walk into that call with a question list that won't waste the limited time on vague answers.

The Case Study Interview Question Builder: Turn a Vague Customer Win Into a Publishable Story

A structured prompt that turns a 30-minute customer interview into a sequence of questions designed to extract specific numbers, real stakes, and a quotable human sentence — instead of generic praise nobody will read.

marketingcontent-marketing
The Skill Gap Diagnostic: Find Out What You Actually Need to Learn Before the Next Role
Works well with Claude, GPT-5, and Gemini — any model with strong reasoning and multi-step instruction-following. Avoid smaller/faster models for this one; the ranking and reality-check steps need genuine reasoning, not pattern-matching.A data analyst with 4 years of SQL experience is applying for a senior analyst role that requires Python ETL pipelines and A/B testing design — two skills the job posting lists as core requirements but that aren't in their current toolkit. They have 5 hours a week and 90 days before they plan to apply.

The Skill Gap Diagnostic: Find Out What You Actually Need to Learn Before the Next Role

A structured prompt that compares your current skills against a specific target role, ranks the gaps that actually matter, and builds a time-boxed learning plan — instead of generic upskilling advice.

professional-developmentlearning
The Character Reference Sheet Generator: Turn One Description Into a Three-View Turnaround
Works with any image model capable of multi-subject spatial consistency within one generation — tested here with Cloudflare Workers AI FLUX-1-schnell. Dedicated character-consistency tools (ConsistentCharacter-style pipelines, Midjourney character reference, or Gemini image models when available) will hold proportions and props more reliably across all three panels than a single-shot diffusion prompt.creativeA solo indie game developer has designed an NPC on paper — a dwarf blacksmith with a specific beard, apron, and hammer — and needs a turnaround sheet before handing the character off to a contract artist or feeding it into a 3D modeling reference, without paying for a full commissioned turnaround just to get the project started.

The Character Reference Sheet Generator: Turn One Description Into a Three-View Turnaround

Skip the $200+ commission for a rough character turnaround. This prompt generates a front, three-quarter, and back view of the same character in one image — good enough to keep pre-production moving while you line up a real artist.

ai-artimage-generation
The Technical Debt Prioritizer: Turn a Pile of Known Issues Into a Ranked Fix-It Backlog
Works best with Claude Opus or GPT-5-class models for multi-factor reasoning across technical and business tradeoffs. Works adequately with Gemini 2.5 Pro; smaller or faster models tend to flatten the scoring and default every item to a similar composite score, which defeats the purpose.Developer ToolsA tech lead has 40 open technical debt tickets accumulated over a year, a sprint planning meeting in two hours, and no agreed-upon method for deciding which 5 items the team will actually commit to fixing this quarter instead of just the ones the loudest engineer complained about last.

The Technical Debt Prioritizer: Turn a Pile of Known Issues Into a Ranked Fix-It Backlog

Stop prioritizing tech debt by whoever complained most recently. This prompt scores every item on blast radius, incident probability, and cost of delay — and forces a hard line on what actually fits this quarter.

prioritizationtechnical-debt
The AI Vendor Data Retention Auditor: Find Out What Your LLM Provider Actually Keeps
Claude Sonnet 5.5 or GPT-5.4. Both handle long policy documents well. Paste the full current terms, not a link: a model working from memory of a provider's policy will be out of date.Artificial IntelligenceBefore Friday's renewal, your legal team needs to know whether the AI assistant your support team uses keeps customer conversations, for how long, and whether those conversations train future models.

The AI Vendor Data Retention Auditor: Find Out What Your LLM Provider Actually Keeps

Paste your AI vendor's data terms and get a table of retention, training use, and human review for each data type, plus the questions to ask before renewal.

privacyai-procurement