AGENTS.md

Production prompt-engineering pipeline for GPT-Image-2 / OpenAI image generation. Pairs a 'media-designer' agent with a hosted searchable corpus of 3,238 community-vetted prompts, decomposed across 10 controlled vocabularies (subjects, styles, lighting, cameras, moods, palettes, compositions, mediums, techniques, usecases). Each record carries: full prompt body, twitter/X attribution link, downloaded reference image. Workflow: agent diagnoses the user brief → searches the corpus → picks a mood-aligned base → refactors the chosen prompt into a parameterised {argument} template → resolves arguments from user intent → returns the final paste-ready prompt with attribution + reference image. Use when the user wants a polished image-generation prompt for ads, posters, product shots, portraits, character sheets, UI mockups, infographics, exploded-view diagrams, or any other GPT-Image-2 / OpenAI image task.

Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Codex, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.

Starter template for creating new skills. Use when defining a new skill scaffold with frontmatter and concise execution instructions.

Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Codex, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Codex needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Codex needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Presentation creation, editing, and analysis. When Codex needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Codex needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Use AFTER any code changes (feature implementation, bug fix, refactor) to enforce mandatory dual-pass review. First pass reviews unstaged changes for correctness and convention compliance. Second pass ONLY executes if first pass made any corrections. Ensures work follows project conventions, development rules, and best practices before task completion.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications, OR when they provide screenshots/images/designs to replicate or draw inspiration from. For screenshot inputs, extracts design guidelines first using ai-multimodal analysis, then implements code following those guidelines. Generates creative, polished code that avoids generic AI aesthetics.

Use when you need to plan technical solutions that are scalable, secure, and maintainable.

Generate and maintain project structure index for fast AI navigation. Creates docs/structure.md with optimized file index. Load this skill when starting new project, after major changes, or when docs/structure.md is outdated.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Guide for creating effective skills, adding skill references, skill scripts or optimizing existing skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, frameworks, libraries or plugins usage, or API and tool integrations.

Use when the user asks to debug, diagnose, fix a bug, troubleshoot errors, investigate issues, or pastes error messages/stack traces. Triggers on keywords like "bug", "error", "fix", "not working", "broken", "debug", "stack trace", "exception", "crash", "issue".

Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected behavior, performance issues, or before claiming work complete. Prevents random fixes, masks over symptoms, and false completion claims.

Use for PLANNING documentation with phased analysis (4 phases), gap identification, and structured knowledge modeling. Best for documentation audits, completeness analysis, and documentation strategy planning. NOT for writing actual docs (use tasks-documentation instead).

Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

Use for QUICK PR reviews with structured checklists (architecture, patterns, security, performance). Provides step-by-step review process, git diff commands, and review report templates. Best for pull request reviews and pre-commit checks. NOT for deep refactoring analysis (use code-review instead).

Use for WRITING documentation with ready-to-use code templates (C# XML docs, TypeScript JSDoc, API docs, README patterns). Best for implementing actual documentation, adding code comments, and creating docs from scratch. NOT for documentation planning (use documentation instead).

Consultative UI/UX planning workflow that forces design discussion and explicit approval before implementation. Use when users ask to design, redesign, improve, or build UI and want to explore style directions, color systems, typography, and project-fit tradeoffs first. Run UI optioning with ui-ux-pro-max, then implement only after approval; use frontend-design and frontend-development as secondary skills after direction is locked.

UI/UX design intelligence with searchable database

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, and modern data stack. Includes data modeling, pipeline orchestration, data quality, and DataOps. Use when designing data architectures, building data pipelines, optimizing data workflows, or implementing data governance.

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

UI/UX design intelligence with searchable database

Use when analyzing and improving performance for database queries, API endpoints, or frontend rendering.

Use when reviewing code for security vulnerabilities, implementing authorization, or ensuring data protection.

Use when you need to plan technical solutions that are scalable, secure, and maintainable.

Use when updating specifications, comparing branches, or ensuring documentation reflects current implementation.

Use for DEVELOPER-focused unit/integration test code with xUnit (C#) and Jest (Angular) patterns. Provides ready-to-use test templates for commands, queries, entities, and components. Best for implementing actual test code. NOT for QA test specifications (use test-generation instead).

Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.

Work with MongoDB (document database, BSON documents, aggregation pipelines, Atlas cloud) and PostgreSQL (relational database, SQL queries, psql CLI, pgAdmin). Use when designing database schemas, writing queries and aggregations, optimizing indexes for performance, performing database migrations, configuring replication and sharding, implementing backup and restore strategies, managing database users and permissions, analyzing query performance, or administering production databases.