dotfiles

Creates TDD implementation plans where tests ARE the plan. Specifies test specs and structural context per phase — implementation emerges during execution, not planning. Verification is fully automated; no manual verification step. Use when planning features test-first, creating TDD plans from design artifacts, or when the user asks for a test-driven implementation plan. NOT for executing a plan test-first (the Red-Green-Refactor cycle during implementation) — that is practicing-tdd.

Breaks an epic into an ordered backlog of vertical, sprint-sized user stories. Use when splitting an epic into stories, planning a feature's story backlog, or when a story feels too large but isn't ready for task breakdown. Produces 4-8 demoable stories, each independently shippable and grounded in user-visible behavior. NOT for sub-story implementation slicing (see slicing-elephant-carpaccio) or for writing one story's full BDD spec (see writing-agile-stories).

Slices a single feature or story into ultra-thin vertical increments (minutes-to-hours each) using Alistair Cockburn's Elephant Carpaccio methodology. Use during implementation planning when one story or feature is too large to build in a session and you need demoable increments across layers. Produces an ordered backlog of 10-20 thin slices, each independently working, testable, and demoable. NOT for splitting an epic into sprint-sized stories (see decomposing-epics).

Write well-scoped, verifiable development tasks for non-user-facing work — refactors, test work, and dependency/tooling changes. Use to "write a dev task", create a "refactor task", a "tech-debt ticket", a "test task", or a "dependency upgrade task"; to capture "non-user-facing work" or a "technical task"; or to write a "definition of done for a refactor". Produces an implementation-focused task with a verifiable Definition of Done. For user-facing behavior, use writing-agile-stories instead.

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Examines a git-machete stack of dependent branches and drafts preemptive PR comments warning reviewers that code in an earlier PR is already refactored, renamed, moved, deleted, or fixed later in the stack. Output is DRAFT ONLY — the user pastes it manually; the skill never posts to GitHub. Use for stacked PRs, a git-machete stack, when reviewers comment on code that is "already fixed/refactored/handled later in the stack", to preempt reviewer comments on superseded code, to draft PR comments for a branch stack, or to find code in an earlier branch that a later branch supersedes.

Researches and documents existing codebase implementations. Use when exploring how code works, understanding architecture, answering 'how does X work?' questions, or gathering context before making changes. Produces structured research documents with code references.

Enforces test-first development with Red-Green-Refactor cycle. Use when implementing features, fixing bugs, writing tests, or when someone mentions TDD, test-driven, "test first", or "write a failing test".

Pragmatic code review for source code changes. Use when code has been written or modified and needs review - after implementing features, completing refactors, or before merging PRs. Focuses on catching actual problems rather than enforcing theoretical purity. Does not review documentation or non-code files.

Evaluates test quality using Dave Farley's 8 properties. Use when reviewing tests, assessing test suite quality, or analyzing test effectiveness against TDD best practices.

Write Tim Pope-style Git commit messages. Honors repo-specific commit templates when present. Forbids AI attribution. Use when committing staged changes, amending commit messages, or when someone mentions commit message, git commit, or commit format.

Write behavior-focused Agile user stories with BDD-style acceptance criteria. Use when defining features, clarifying requirements, creating development tickets, writing acceptance criteria, converting requirements to testable specs, or discussing user needs. Produces narrative-form stories with Given-When-Then scenarios.

Write Shape Up style pitches (Basecamp / Ryan Singer). Use when shaping a raw idea, refining a draft pitch, distilling notes into a pitch, or when the user mentions Shape Up, pitch, shaping, appetite, rabbit holes, no-gos, or fixed time / variable scope. Produces a pitch document with Problem, Appetite, Solution, Rabbit holes, and No-gos.

Build Product Requirements Documents from Product Briefs. Use when transforming product vision into actionable requirements for engineers and designers. Produces high-level design principles, use case compendiums, and milestone definitions. A PRD focuses on what, not how.

Write Product Briefs that align teams on goals before discovery. Use when defining a new product vision, articulating problem statements, creating one-pagers, or crafting north star scenarios. Produces vision documents with thesis/antithesis, target audience, metrics, and narrative scenarios.

Interview the user rigorously about an idea — a plan, design, or half-formed direction — until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test their thinking, get grilled on a design, explore a vague direction, or mentions "grill me".

git-machete command-line expertise covering branch tree management, fork-point mechanics, rebase-driven syncing, and stacked-PR workflows on GitHub. Use when building or maintaining a tree of dependent branches, rebasing chains of feature branches against `main`, debugging fork-point inference after force-pushes or squashes, or driving stacked GitHub PRs with `git machete github` subcommands. Also use for `.git/machete` edits, `traverse` flag selection, and `advance`/`slide-out` after merges.

Design-first collaboration using a five-level progressive framework (Capabilities → Components → Interactions → Contracts → Summary). Adapts to OOP or FP paradigms based on project language. Produces design output with mermaid diagrams. Use when designing features before implementation, planning architecture, aligning on design decisions, or when the user mentions "design first", "design session", or wants to think through a feature before coding.

Reviews pull requests using the PERFECT code review methodology — 7 principles applied in strict priority order (Purpose, Edge Cases, Reliability, Form, Evidence, Clarity, Taste). Use when reviewing a PR, conducting code review, or when the user mentions PERFECT review methodology.

Writes documentation for two audiences: human developers and LLMs. Covers three doc types: code-level docs (module headers, function docs, inline comments), architecture docs (ADRs, design docs, system overviews), and project docs (READMEs, guides, CLAUDE.md). Language-agnostic. Use when asked to "document", "add docs", "write a README", "create an ADR", "add module docs", "document this function", "write architecture docs", "create a getting started guide", "write CLAUDE.md", or "add comments".

Expert guidance for creating, auditing, and improving Claude Code agent definition files (.md). Use when working with ~/.claude/agents/ files, authoring new sub-agents, improving existing agents, or understanding agent configuration and system prompt best practices.

Expert guidance for writing Vitest tests for React applications using React Testing Library. Covers component tests, custom hooks, utility tests, sociable testing philosophy, and the RTL query priority system. Favors sociable tests over heavy mocking, stubs over mocks. Use when working with .test.ts/.test.tsx files, vitest.config.ts, React Testing Library, @testing-library/user-event, @testing-library/jest-dom, renderHook, or when discussing React testing patterns, component testing, hook testing, or test organization.

Provides expert guidance for writing ExUnit tests in Elixir. Covers core ExUnit patterns, assertions, sociable testing philosophy, Ecto sandbox and database testing, Phoenix controller/LiveView/channel tests, and external API testing with Bypass and Req.Test. Use when working with ExUnit tests, assertions, describe blocks, test organization, Bypass, Req.Test, factories, ExMachina, Ecto sandbox, ConnTest, LiveViewTest, ChannelTest, or test helpers.

Browser automation via playwright-cli (microsoft/playwright-cli), the AI-agent-focused CLI for controlling browsers through Bash commands. Covers element reference system, snapshot workflow, session management, cookies, storage, network interception, and content capture. Use when the user asks to automate a browser, scrape a webpage, fill a form, test a UI flow interactively, capture screenshots, manage cookies/storage, intercept network requests, or drive any browser interaction from the terminal. NOT for npx playwright test runner or codegen.

Manages Linear issues via CLI using linearis (czottmann/linearis). Use when the user mentions Linear issue identifiers (e.g., 'ENG-123'), teams, cycles, projects, labels, issue management, or workflow automation. Handles issue CRUD, comments, cycle/project/label/team/user listing, document management, file embeds, search, and GitHub/GitLab PR linking via issue identifiers.

Refactors bloated agent instruction files (CLAUDE.md, AGENTS.md, COPILOT.md, .cursorrules, etc.) to follow progressive disclosure — minimal root file linking to categorized files in guidelines/. Use when agent instructions are too long, hard to maintain, contain contradictions, or need reorganization.

Post-processing rewrite skill that transforms dense LLM-generated documentation into scannable, concise, human-readable text. Covers vocabulary tics, structural anti-patterns, BLUF rewriting, and word-level editing. Use when other skills need to produce user-facing prose: READMEs, guides, tutorials, or commit messages. Loaded by other skills as a post-processing step — not a standalone command.

Datadog CLI for searching logs, querying metrics, tracing requests, and viewing dashboards. Use this when debugging production issues or working with Datadog observability.

Identifies code smells and applies refactoring patterns for OOP and FP codebases. Use when improving code structure, reducing technical debt, cleaning up messy code, or when the user mentions refactoring, code smells, or "make this cleaner".

jq command-line JSON processor expertise covering filter syntax, object/array manipulation, data transformation, and CLI tool integration patterns. Use when processing JSON output from CLI tools (jira, gh, curl), extracting fields from API responses, transforming JSON data structures, or formatting JSON for shell consumption. Also use for jq filters, JSON parsing in bash, or when piping JSON through command-line tools.

Comprehensive Elixir/Phoenix development expertise covering Phoenix controllers, routing, channels; LiveView components and real-time features; Ecto schemas, queries, migrations; OTP patterns (GenServer, Supervisor); functional domain modeling; GraphQL with Absinthe; and ExUnit testing. Use when working with .ex/.exs files, mix projects, Phoenix applications, or when the user mentions Elixir, Phoenix, Ecto, LiveView, OTP, GenServer, Supervisor, Absinthe, or ExUnit. Also use for defmodule, mix.exs, umbrella apps, or iex sessions.

Interacts with Jira via CLI for ticket operations. Use when the user mentions ticket identifiers (e.g., 'ABC-123'), discusses work tracking, references Jira projects, or needs search, create, edit, transition, comment, assign, or sprint/epic management. Handles JQL queries, workflow automation, and bulk operations using jira-cli (ankitpokhrel/jira-cli).

Material-UI component library patterns including sx prop styling, theme integration, responsive design, and MUI-specific hooks. Use when working with MUI components (@mui/material), styling with sx prop, theme customization, or MUI utilities. Supports v5, v6, and v7.

Shell scripting expertise covering POSIX-compliant and Bash-specific patterns, defensive scripting practices, cross-platform compatibility, and command-line automation. Use when working with .sh files, shell scripts, or when the user mentions Bash, POSIX, shell scripting, shebang, pipelines, or CLI automation. Also use for set -e, traps, parameter expansion, or cross-platform shell compatibility.

Comprehensive TypeScript/React development expertise covering advanced type systems, React component architecture, hooks patterns, state management, GraphQL integration with Apollo, performance optimization, and React Testing Library. Use when working with .ts/.tsx files, React components, or when the user mentions TypeScript, React, hooks, Context, Apollo, GraphQL codegen, React Testing Library, Vite, or Next.js. Also use for generic types, component patterns, or bundle optimization.

Guides technical evaluation of code review feedback before implementation. Use when receiving PR comments, review suggestions, GitHub feedback, or when asked to address reviewer feedback. Emphasizes verification and reasoned pushback over blind agreement.

Applies Swiss/International Typographic Style principles to create clear, functional output. Use when designing interfaces, data visualizations, documentation, CLI output, or any output where clarity matters. Recognizes requests like "make it cleaner", "reduce clutter", "too busy", "improve readability", "visual hierarchy", "simplify the layout".

Provides structured reasoning patterns that produce visible, auditable output. Use when the user asks to "think through", "reason about", "work through", "show your thinking", or wants step-by-step reasoning. Also invoked with /thinking or /thinking <pattern>.

Write agentic prompts including system prompts, workflow prompts, delegation prompts, and meta prompts. Use when creating commands, automating workflows, making tasks reusable, or when the user says "write a prompt", "create a command", or "automate this".