dotfiles

End-to-end Jira ticket creation harness. Gathers a summary and rough description, enhances the description in a chosen writing style, confirms with the user, and creates the ticket via the Atlassian MCP. Use when the user says "create a ticket", "open a Jira ticket", "file a bug", "draft a ticket", "new issue for ...", or otherwise asks to create work in Jira. Supports an optional writing style passed up front (e.g. "create a ticket in bug_report style"); when no style is given, the harness asks which style to use.

End-to-end Jira ticket implementation harness. Fetches ticket from Jira, creates an implementation plan, executes it with proper branching, commits, quality gates, and opens a PR. Use when the user says "implement TICKET-ID", "work on TICKET-ID", "pick up TICKET-ID", "start TICKET-ID", or provides a Jira ticket key (e.g., PREFIX-1810, TICKET-450) with implementation intent. Covers bugs, tasks, stories, and any other Jira issue type.

Review a GitHub pull request end-to-end and produce specific, actionable change requests classified as "required" or "good_to_have". Use when the user invokes the /review-pr command with a PR link, says "review this PR", "review pull request", or asks for a code review on a GitHub PR URL. Detects PR ownership via the gh CLI — for the user's own PRs, outputs findings locally; for collaborator PRs, presents findings as approve/reject/change questions and then posts approved feedback as inline review comments at file and line (or as a general PR comment when not line-specific).

Use this skill when writing, reviewing, or refactoring Ruby and Rails code in Develoz's preferred Rails style. Applies to Rails models, controllers, services, jobs, helpers, mailers, views, tests, routing, and architecture. Emphasizes clear Rails conventions, rich domain models, pragmatic service objects, RESTful defaults with practical exceptions, Hotwire, Tailwind, RSpec, FactoryBot, and simple infrastructure choices.

Perform comprehensive code audits of Ruby on Rails applications based on thoughtbot best practices. Use this skill when the user requests a code audit, code review, quality assessment, or analysis of a Rails application. The skill analyzes the entire codebase focusing on testing practices (RSpec), security vulnerabilities, code design (skinny controllers, domain models, PORO with ActiveModel), Rails conventions, database optimization, and Ruby best practices. Outputs a detailed markdown audit report grouped by category (Testing, Security, Models, Controllers, Code Design, Views) with severity levels (Critical, High, Medium, Low) within each category.

Debug and optimize slow ActiveRecord queries in a Ruby on Rails application. Use this skill when the user reports slow pages or jobs, suspects N+1 queries, asks to "optimize", "speed up", "profile", "add indexes", or "explain" an ActiveRecord query, or mentions tools like Bullet, rack-mini-profiler, pghero, pg_stat_statements, EXPLAIN/EXPLAIN ANALYZE, load_async, strict_loading, or query log tags. Also triggers on database-specific performance questions for PostgreSQL, MySQL, or SQLite inside a Rails codebase.

Expert company and product naming skill for founders and brand strategists. Use this skill any time a user asks for help naming a company, product, startup, feature, or service, or asks for a rebrand, rename, or evaluation of an existing name. Also trigger for requests like "what should I call my...", "help me name...", "name ideas for...", "is this a good name?", "brand naming", or any request involving naming something for business purposes. This skill produces names grounded in brand strategy, linguistic quality, domain and trademark awareness, and proven naming frameworks used by top naming agencies and VCs.

Review code changes and remove AI-generated patterns.

Run commands inside Docker Compose services. Use when services are only reachable from inside compose networks.

Fix Jest test failures systematically, one file at a time.

Fix RSpec test failures systematically, one file at a time.

Fix Vitest test failures systematically, one file at a time.

Find and fix uncovered lines and branches from lcov coverage reports.

Write in Steven's voice—pragmatic, curious, pedagogical. Opens with measurable payoffs, builds mental models from first principles, uses worked examples, and handles uncertainty honestly. Use for essays, blog posts, and technical articles.