dev-setup

DDD planning and review workflow for greenfield systems and brownfield codebases. Use when shaping bounded contexts, ubiquitous language, aggregates, invariants, integration boundaries, or reviewing an existing model for DDD fit.

Copy the skills collection from /Users/shrivatsa/Documents/dev-setup/skills into the current repository, another repository, or an explicit skills directory. Use when the user asks to copy, sync, install, update, or bring over their dev-setup skills.

Guide for creating effective 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, or tool integrations.

Expert HIPAA compliance assistant for healthcare and software contexts. Use this skill whenever the user mentions HIPAA, PHI (Protected Health Information), ePHI, covered entities, business associates, healthcare data privacy, medical records, health information security, BAA (Business Associate Agreements), or any compliance review involving patient data. Also trigger for requests to draft privacy notices, HIPAA policies, consent forms, security risk assessments, or breach notification letters. Use for developers building healthcare software who need technical safeguard guidance (encryption, access controls, audit logs), compliance officers reviewing documents or procedures, and anyone asking "is this HIPAA compliant?" or "what does HIPAA require for X?". When in doubt about whether a healthcare or data privacy question falls under this skill — use it.

Outcome-first architecture discovery and recommendation skill. Use when you need to iteratively clarify requirements, ask leading questions about business goals and constraints, maintain a running intake file so users do not repeat themselves, and produce a sharp architecture recommendation with tradeoffs and risks.

Add, remove, or refine research fields for an existing research outline, with concise evidence-first output.

Add, remove, or refine research items for an existing research outline, with concise evidence-first output.

Run the deep research phase for an existing research outline and produce a concise, evidence-first synthesis.

Turn research outputs into a concise final report with strong structure, evidence, and crisp writing.

Conduct preliminary research, generate a research outline, and produce concise, evidence-first results for comparisons, benchmarks, technology selection, and topic scans.

Implement the next repo phase, verify it, then update plan.md and ship the commit after confirmation.

Generate or update architecture documentation from repositories, product docs, infrastructure files, and code. Use when asked for high-level architecture, C4 diagrams, system context, container/component/deployment views, arc42 documentation, Excalidraw-ready architecture, Mermaid architecture diagrams, architecture decisions, runtime views, quality attributes, risks, or an architecture package synthesized from existing docs and source.

Use OpenAI Codex CLI for complex debugging, code analysis, or when stuck on difficult problems. Invokes Codex with a file-based question/answer pattern.

Guided tour of changes or codebase - explains how things work conceptually rather than listing changes mechanically. Use anytime you're asked to explain, review, walk through, or summarize work, branch changes, or codebase architecture.

Generate property-based tests using Hypothesis. Builds input strategies in tests/strategies.py that model the valid search-space for each function, then writes minimal, behaviour-focused tests.

Work with Logseq flashcards in file-based graphs. Use when the user asks how to create, inspect, normalize, bulk-edit, or validate Logseq flashcards or cloze cards in Markdown or Org files, especially when they want a plain-files workflow, need to understand which parts are stored in note files, or want to script or curate card content outside the Logseq UI.

Perform mutation testing on the codebase. Introduces deliberate bugs one at a time, checks whether the test suite catches each one, and reports on test suite gaps. Optionally implements missing tests.

Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.

Curate links, reading lists, TODO notes, topic maps, media links, and resource queues in a personal knowledge base, especially Logseq-style Markdown pages. Use when the user asks to add links, title/describe raw URLs, dereference shortlinks, remove noisy generated titles, dedupe entries, place links semantically near related notes, normalize YouTube/X/social links, organize a topic hierarchy, normalize tags across related pages, or maintain pages such as TODO.md in a PKM.

Imagine future bug post-mortems for the codebase. Identifies fragile code, implicit assumptions, and likely failure modes by writing realistic incident reports for bugs that haven't happened yet.