Coding and Data AI Prompts

Audit this interface against the supplied interaction and markup. Check semantics, heading order, keyboard operation, focus visibility, accessible names, form errors, contrast assumptions, zoom, motion and screen-reader announcements. Do not infer compliance from a screenshot alone. Mark what needs browser or assistive-technology testing. Markup: [HTML OR COMPONENT]. Styles: [CSS]. Interaction: [USER FLOW].

Customize: HTML OR COMPONENT, CSS, USER FLOW

Create a risk-based QA plan for this change. Map each requirement to a test, then cover integration boundaries, permissions, failure recovery, concurrency, data migration, observability and rollback. Prioritize by impact and likelihood. Product change: [CHANGE]. Requirements: [REQUIREMENTS]. Architecture: [ARCHITECTURE]. Known incidents: [INCIDENTS OR NONE].

Customize: CHANGE, REQUIREMENTS, ARCHITECTURE, INCIDENTS OR NONE

Evaluate this regular expression as production input validation. Explain what it accepts, then design positive, negative and adversarial test cases. Include empty input, Unicode, extreme length, ambiguous boundaries and likely ReDoS cases. Do not claim the expression is safe unless the evidence supports it. Regex: [REGEX]. Intended rule: [RULE]. Engine: [ENGINE].

Customize: REGEX, RULE, ENGINE

Diagnose this bug using only the supplied evidence. Build a timeline, separate observations from hypotheses, rank the likely causes, and propose the cheapest discriminating test for each hypothesis. Do not propose a code change until one cause is supported. Symptom: [SYMPTOM]. Logs: [LOGS]. Recent changes: [CHANGES]. Environment: [ENVIRONMENT]. Reproduction: [STEPS].

Customize: SYMPTOM, LOGS, CHANGES, ENVIRONMENT, STEPS

You are reviewing an unfamiliar codebase. Explain the supplied code before proposing changes. Identify the entry point, data flow, dependencies, state changes, error paths and external side effects. Separate facts visible in the code from assumptions. Then list the three highest-risk areas to inspect next. Code: [PASTE CODE]. Runtime and version: [RUNTIME]. Known behaviour: [KNOWN BEHAVIOUR].

Customize: PASTE CODE, RUNTIME, KNOWN BEHAVIOUR

Review this change against the stated requirements. Report only issues introduced or exposed by the patch. For each issue, give severity, exact file and line, the failure scenario, and the smallest safe correction. Do not report style preferences unless they cause a defect. Requirements: [REQUIREMENTS]. Patch: [DIFF]. Relevant tests: [TESTS].

Customize: REQUIREMENTS, DIFF, TESTS

Review this SQL query using the supplied schema and expected result. Check join cardinality, null handling, duplicate rows, filtering order, transaction assumptions, injection risk and index use. Propose a corrected query only when needed, and explain how to verify it with EXPLAIN or the database equivalent. Database: [DATABASE AND VERSION]. Schema: [SCHEMA]. Query: [QUERY]. Expected result: [EXPECTED RESULT].

Customize: DATABASE AND VERSION, SCHEMA, QUERY, EXPECTED RESULT

Convert this feature request into an architecture decision record. State the problem, constraints, quality attributes, two or three viable options, trade-offs, security implications, operational cost and a reversible recommendation. Mark missing evidence as unknown. Feature: [FEATURE]. Existing system: [SYSTEM]. Constraints: [CONSTRAINTS]. Expected scale: [SCALE].

Customize: FEATURE, SYSTEM, CONSTRAINTS, SCALE

I want you to act as an Information Security Analyst Manager. I will provide you with the company's security policies and procedures, and I want you to assess the current security risks and vulnerabilities and develop a comprehensive plan to mitigate them. My first request is "Conduct a thorough risk assessment of the company's IT infrastructure and develop a comprehensive plan to mitigate identified risks and vulnerabilities."

Audit this website redesign brief: [BRIEF]. The audience and primary conversion task are [AUDIENCE AND TASK]. Check information architecture, content hierarchy, responsive behavior, accessibility, performance assumptions and measurement. Identify missing evidence and conflicting requirements before suggesting a page structure. Return a prioritized issue list, a revised scope and acceptance tests. Do not invent user research.

Customize: [BRIEF], [AUDIENCE AND TASK]

Build a risk-based test plan for [FEATURE]. The requirements, users, environment and known failure history are [CONTEXT]. Map each important requirement to happy-path, boundary, failure, security and accessibility tests. Rank tests by impact and likelihood. Ask for missing acceptance criteria instead of inventing them. Include test data, expected results and the evidence required to mark each test passed.

Customize: [FEATURE], [CONTEXT]

Create a defensive threat model for [SYSTEM]. The architecture, users, data and trust boundaries are [DETAILS]. Identify assets, entry points, likely abuse cases and existing controls. Rank risks by likelihood and impact without inventing vulnerabilities. Recommend preventive and detective controls, owners and verification steps. Do not provide exploitation instructions. Ask for missing architecture details before making high-confidence claims.

Customize: [SYSTEM], [DETAILS]

Create an SVG icon for [CONCEPT] at [SIZE]. Use a simple viewBox, scalable paths, currentColor where appropriate and no external resources. If the icon conveys meaning, include a concise title and explain the accessible name needed in HTML. If it is decorative, mark it for aria-hidden use. Return the SVG code, a short usage example and checks for contrast, focus and scaling.

Customize: [CONCEPT], [SIZE]

Debug this R code: [CODE]. The R version, package versions, input data shape and exact error are [ENVIRONMENT]. First reduce the problem to a minimal reproducible example. Explain the likely cause, propose the smallest correction, and provide commands for verifying the result. Do not invent package behavior or pretend to run the code. Mark any conclusion that depends on missing data.

Customize: [CODE], [ENVIRONMENT]

I want you to act as a Machine Learning Engineer. I will provide you with a dataset of customer behavior on an e-commerce website, and I want you to develop a recommendation system using collaborative filtering to suggest products to customers based on their purchase history. My first request is "Develop a recommendation system using collaborative filtering to suggest products to customers on an e-commerce website based on their purchase history."

Review this Solr query and schema context: [QUERY AND SCHEMA]. The Solr version, analyzers, expected matches and problematic results are [CONTEXT]. Explain parsing, filters, scoring and analyzer effects. Propose one change at a time, include an observable test for relevance and latency, and distinguish schema changes from query changes. Do not invent index statistics.

Customize: [QUERY AND SCHEMA], [CONTEXT]

Dry-run this SQL query against the supplied schema and sample rows. Schema: [SCHEMA]. Sample data: [ROWS]. Query: [QUERY]. State the SQL dialect. Check syntax, column resolution, join cardinality, null behavior and result ordering. Show the expected result table only when it can be derived from the supplied data. Otherwise identify exactly what information is missing. Do not pretend to execute a database.

Customize: [SCHEMA], [ROWS], [QUERY]

I want you to act as a machine learning engineer. I will write some machine learning concepts and it will be your job to explain them in easy-to-understand terms. This could contain providing step-by-step instructions for building a model, demonstrating various techniques with visuals, or suggesting online resources for further study. My first suggestion request is "I have a dataset without labels. Which machine learning algorithm should I use?"

Create a regular expression for [ENGINE] that should match [POSITIVE EXAMPLES] and reject [NEGATIVE EXAMPLES]. Explain anchors, groups and escaping. Prefer the simplest readable pattern. Include executable test cases for the named language or tool, note Unicode or multiline assumptions, and warn about catastrophic backtracking when relevant. If examples conflict, ask for clarification instead of guessing.

Customize: [ENGINE], [POSITIVE EXAMPLES], [NEGATIVE EXAMPLES]

I want you to act as an Information Security Analyst Manager. I will provide you with the organization's security policies and procedures, and I want you to manage the security team to ensure compliance and protect the organization from security threats. My first request is "Conduct a security audit and vulnerability assessment of the organization's information systems and develop a plan to address any identified weaknesses."

Review this Python code without pretending to execute it: [CODE]. The target Python version is [VERSION]. Predict the output or error, explain the evaluation order and identify version-dependent behavior. If the result depends on the environment or external state, say exactly what must be tested. Provide a minimal command the learner can run locally to verify the prediction.

Customize: [CODE], [VERSION]

Review this machine learning experiment plan: [PLAN]. The data source, target, split strategy, baseline and success metric are [CONTEXT]. Check for leakage, label quality, class imbalance, inappropriate metrics, missing baselines and reproducibility gaps. Separate facts from assumptions. Recommend the smallest experiment that can disprove the main hypothesis before suggesting a more complex model.

Customize: [PLAN], [CONTEXT]

Review this interface description or screenshot notes: [INTERFACE]. The users are [AUDIENCE] and their main task is [TASK]. Identify friction in navigation, hierarchy, labels, forms, keyboard use, focus order, contrast and error recovery. Separate observed problems from assumptions. Rank the five most important fixes by user impact and implementation effort, then propose a test for each fix.

Customize: [INTERFACE], [AUDIENCE], [TASK]

I want you to act like a PHP interpreter. I will write you the code and you will respond with the output of the PHP interpreter. I want you to only reply with the terminal output inside one unique code block, and nothing else. do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English, I will do so by putting text inside curly brackets {like this}. My first command is {your command}

Customize: {like this}, {your command}