dev-skills

Check domain name availability. Routes to a fast, cheap model for straightforward domain lookups.

Structured, detached evaluation of component or system architecture clarity and intent. Use when reviewing medium-fidelity design docs, component boundaries, or system flow sketches to assess whether they communicate ownership, direction, and rationale clearly.

Review architecture specifications for completeness, appropriate abstraction level, and separation of concerns. Use when reviewing top-level, implementation-agnostic architecture documents that define system boundaries, responsibilities, flows, and constraints without prescribing implementation details.

Check domain name availability and find alternatives.

Use on the first user message of every new session — before any tool use, file reads, or repo exploration. Forces a brief understanding replay so the user can catch misinterpretations before execution begins.

Collaborative discussion mode for exploring ideas, designs, and implementation approaches before taking action. Activates when the user says "let's discuss", "discuss mode", "discuss this", "let's think about", "I want to talk through", "help me reason about", "before we build", "let's explore", or "what do you think about". This skill prevents premature implementation and ensures Claude and the user are aligned before any code is written, files are created, or artifacts are produced. Use this skill whenever the user signals they want to explore or reason about a problem collaboratively rather than jump straight to building.

This skill should be used when the user asks to "audit documentation", "check if docs are up to date", "verify docs match code", "run a doc drift audit", "find stale documentation", "check README accuracy", or after large refactors that may have left documentation out of sync with the codebase. Detects factual mismatches between markdown documentation and code — wrong names, signatures, paths, behaviors. Does not rewrite, reformat, or improve docs.

Task intake for implementation and bug-fix assignments. Activates when the user says "/intake", "here's your task", "implement this", "fix this bug", "there's a bug", or provides a task reference (step number, PR, doc path) with instruction to understand before coding. The agent reads all referenced documents and explores the codebase, then demonstrates understanding in a structured playback before auto-transitioning to plan mode. For bug fixes, the playback includes a proposed failing test that proves the broken behavior. Prevents guessing, spec rewriting, and premature implementation.

Comprehensive job search strategy toolkit for analyzing job postings, discovering hidden insights, interviewing candidates to match skills, developing targeted skills, and executing creative outreach strategies. Use when helping candidates strategize their job search, prepare tailored applications, or develop competitive advantages in their job hunt.

Codebase investigation and findings report without solution proposals. Only invoke when the user explicitly calls /rpi-research. Do not auto-trigger from natural language. Use when exploring a problem space before committing to an approach — no spec required, no auto-transition to planning. Reports findings, risks, and unknowns, then stops.

Tweak iOS simulator settings via xcrun simctl. Use when granting app permissions, changing UI appearance, simulating location, or overriding status bar. Triggers on "simulator settings", "grant permission", "privacy", "dark mode", "light mode", "location", "status bar", "simctl".

Review and improve existing Claude Code skills. Use when evaluating skill quality, auditing skill collections, asking "review my skill", "is this skill effective", "improve skill description", or maintaining a skill library.

Clean, maintainable Package.swift creation and editing using the static property pattern from Facebook iOS SDK. Use when creating new Package.swift files, refactoring existing ones, adding modules/targets to Swift packages, or organizing Swift Package Manager manifests for better maintainability.

Use when the user needs a concise description of a component, module, product, or entire codebase for someone with zero project context. Triggers on "synopsis", "describe this for outsiders", "write a description", "explain what this does", "elevator pitch", or when producing text for READMEs, marketplace listings, or onboarding docs.

Interactive Test-Driven Development workflow with reviewer-in-the-loop. Implements the RED-GREEN-REFACTOR cycle with two mandatory verification gates where a reviewer (human or AI) approves work before progression. Applies to any code development that follows test-first methodology: features, bug fixes, refactoring, or enhancements. Invoked when TDD discipline with step-by-step verification is required.

Evaluates test name scaffolds for TDD readiness by determining if each test name provides enough specification clarity to write a failing test. Use when reviewing test scaffolds, evaluating executable specifications, or assessing whether test names clearly define testable behavior without implementation ambiguity.