Coding & Development.

You are a senior application security engineer. Review this [language] code and identify: 1) Security vulnerabilities (rate each Critical/High/Medium/Low with CVSS-like reasoning), 2) Performance issues, 3) Code quality problems. For each finding: file location, description, risk, and a corrected code snippet. Format as a structured security report. [PASTE CODE]

You are an expert debugger. I have a bug in my [language] application. Symptom: [describe behavior]. Error log: [paste error]. Relevant code: [paste code]. Think step by step: 1) Form 3 hypotheses about the root cause, 2) Evaluate each against the evidence, 3) Identify the most likely cause, 4) Provide a fix, 5) Suggest how to prevent this class of bug. Use chain-of-thought reasoning.

You are a test-driven development expert. Write comprehensive unit tests for this [language] function. Cover: happy path, edge cases, null/empty inputs, boundary values, and error scenarios. Use [testing framework]. Include: test description, setup, the test itself, and teardown where needed. Aim for 90%+ branch coverage. [PASTE FUNCTION]

Translate this [Source Language] code to [Target Language]. Ensure you use idiomatic patterns of the target language. Preserve logic exactly but adapt structures (e.g., from Python list comprehensions to JavaScript map/filter). Include comments explaining major differences in implementation. [PASTE SOURCE CODE]

You are a principal engineer at a FAANG-level company. Design the backend architecture for [system, e.g., "a real-time collaborative document editor like Notion"]. Walk through each phase using chain-of-thought: 1) Requirements clarification — functional vs non-functional, scale assumptions (DAU, QPS, data volume), 2) High-level design — core components and data flow diagram in ASCII or Mermaid, 3) Deep dives — database schema (justify SQL vs NoSQL), caching strategy (Redis/CDN layers), message queue design, 4) API design — key endpoints with request/response shapes, 5) Bottleneck identification and mitigation, 6) Trade-offs you consciously accepted. Constraints: 10M DAU, 99.99% uptime SLA, global deployment.

You are a technical writer specializing in developer documentation. Generate complete API documentation for the following endpoint. Include: 1) Overview paragraph (what it does and when to use it), 2) Authentication requirements, 3) Request specification (method, URL, headers, path params, query params, request body — each with type, required/optional, description, and example), 4) Response specification (all status codes: 200, 400, 401, 403, 404, 429, 500 — with response body schema and example), 5) A working code example in [language], 6) Rate limits and pagination notes, 7) Common errors and how to resolve them. [PASTE ENDPOINT DEFINITION OR CODE]

You are a database performance engineer specializing in PostgreSQL. Analyze this slow-running query and optimize it. Step 1: Parse the query and identify anti-patterns (e.g., SELECT *, correlated subqueries, missing indexes, implicit type casts). Step 2: Explain the likely query plan the optimizer is choosing. Step 3: Rewrite the query for performance — show the optimized version with inline comments explaining each change. Step 4: Recommend specific indexes to create (include the CREATE INDEX statement). Step 5: Estimate the performance improvement. Table schemas: [paste schemas]. Query: [paste query]. Current execution time: [X ms]. Row counts: [approximate].

You are an AI systems architect in 2026 with deep expertise in agentic AI design. Design a production-grade AI agent for the following task: [describe the agent's goal, e.g., "autonomously research companies and draft personalized outreach emails"]. Deliverables: 1) Agent Loop Design — reasoning loop (ReAct/Plan-and-Execute/Reflexion), 2) Tool Manifest — list each tool with its function signature, input schema, and failure mode, 3) Memory Architecture — short-term (context window), episodic (vector store), and semantic memory layers, 4) Guardrails — safety checks, human-in-the-loop triggers, and cost controls, 5) Evaluation Framework — how to measure task completion rate, error rate, and latency, 6) Deployment considerations — async queuing, observability, model fallback strategy. Stack: [e.g., LangGraph, Claude 4, GPT-5 tools].

You are a software modernization consultant. I need to migrate a legacy [language/framework, e.g., PHP 5.6 monolith] to [target stack, e.g., Node.js microservices]. Codebase size: ~[X] lines of code. Team size: [N] engineers. Timeline: [X months]. Create a migration plan: 1) Risk Assessment — identify the top 5 migration risks and mitigation strategies, 2) Strangler Fig Pattern — how to run old and new systems in parallel, 3) Phase Breakdown — 3-4 phases with goals, deliverables, and definition of done, 4) Database Migration Strategy — how to handle schema changes without downtime, 5) Testing Strategy — how to ensure behavioral parity, 6) Rollback Plan — what to do if phase N fails. Highlight the 3 decisions that will most impact success.

You are a senior engineer and patient mentor. Explain this code to a junior developer who knows the basics of [language] but has never seen this pattern before. Your explanation must: 1) Start with a one-sentence summary of what the code does and why it exists, 2) Walk through it line by line (or block by block for longer code) using plain English — no assumed knowledge, 3) Explain any design patterns or algorithms used and why the author chose them, 4) Point out any potential "gotchas" or non-obvious behaviors, 5) Suggest one improvement the developer could make as a learning exercise. [PASTE CODE]

You are a DevOps engineer specializing in containerization. For my [language/framework] application, create: 1) An optimized multi-stage Dockerfile — minimize final image size, use non-root user, leverage layer caching correctly, add health check, 2) A Docker Compose file for local development with hot-reload, 3) A GitHub Actions CI/CD pipeline YAML that: runs linting and tests on PR, builds and pushes image to [registry] on merge to main, deploys to [environment: ECS/K8s/Cloud Run], and notifies Slack on failure. App details: [describe app, dependencies, env vars needed]. Environment variables must use GitHub Secrets (list which ones are needed).

You are a Staff Frontend Engineer. Review this React component and provide: 1) Performance audit — identify unnecessary re-renders, missing memoization (useMemo/useCallback/React.memo), and bundle size concerns, 2) Accessibility audit — WCAG 2.2 compliance issues with specific fixes, 3) Refactoring plan — identify if this should be split into smaller components (apply Single Responsibility Principle), 4) Custom Hook extraction — which logic should become a reusable hook, 5) TypeScript improvements — strengthen the prop types and return types, 6) Test coverage plan — list the 5 most important test cases. Rewrite the component incorporating your top 3 suggestions. [PASTE COMPONENT]

You are a prompt engineer who has shipped LLM features used by millions of users. I need a production-grade system prompt for an AI assistant that will: [describe the AI's role and tasks]. Requirements: 1) Persona definition — role, expertise, communication style, 2) Scope constraints — what the AI should and should not do (with explicit refusal language), 3) Output format instructions — structured response schemas for each task type, 4) Chain-of-thought reasoning instructions for complex tasks, 5) Few-shot examples — write 2 example interactions (user input → ideal AI response), 6) Edge case handling — what to do when the request is ambiguous, out of scope, or potentially harmful. Also evaluate your own system prompt for: jailbreak surface area, instruction following robustness, and token efficiency.

You are a senior engineering consultant performing a technical debt audit. Analyze the following codebase description and architecture diagram and produce a structured Technical Debt Report. Sections: 1) Executive Summary — overall debt level (Low/Medium/High/Critical) and top 3 risks if unaddressed, 2) Debt Inventory — categorize debt as: Code Quality, Architectural, Dependency, Test Coverage, Documentation, Security, 3) For each item: description, business impact (what will break or slow down), effort to fix (S/M/L/XL), recommended priority (P1-P4), 4) Debt Payback Roadmap — a phased 6-month plan balancing new feature work with debt reduction, 5) "Buy vs Build vs Deprecate" recommendation for the 2 most expensive components. Codebase context: [describe your tech stack, team size, codebase age, and known pain points].

You are a regex expert. I need a regular expression to match: [describe what you need to match, e.g., "all valid email addresses including subdomains" or "ISO 8601 datetime strings"]. Provide: 1) The regex pattern for [target language/engine: JavaScript/Python/Go/etc.], 2) A visual breakdown of each component of the pattern using a table (token | meaning | example match), 3) A list of strings it WILL match, 4) A list of edge cases it will NOT match (and why), 5) Any known caveats or performance concerns with this pattern, 6) A function wrapper in [language] that uses this regex safely (null check, error handling). Also provide a version for any major dialect differences (e.g., PCRE vs RE2).