Claude Skills by heyJordanParker

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Use when presenting architectural options, designing systems, or discussing tradeoffs. Append to any prompt.

Use when working with Claude Code itself - skills, agents, hooks, settings, documentation. Covers building, testing, sharing skills, updating Claude.md files, and plugin distribution.

Process for syncing this skill with new Claude Code releases.

Autonomous async execution mode. The architect hands off, walks away, and the agent drives the task to done — makes every architectural call via /trace + /pcc + ranking, executes through /subagents (or /team for 3+ subtasks), validates by exercising the user-facing flow (real browser via the tester agent for UI), and returns finished code plus a decision log for review. TRIGGER when the architect says "code-first", "/code-first", "execute with /subagents", "execute directly & autonomously", "...

MANDATORY when writing commit messages. Structures commits with type prefix, what+why body, and architectural file tree.

Run N independent architects debating architectural options through structured rounds. Use when the user wants multiple competing solutions evaluated, or when 3+ distinct approaches need comparison. Triggers on "debate", "competing solutions", "run architects", "architecture debate". Invocation /debate [count] "problem"

Use when encountering bugs, test failures, or unexpected behavior. Combines systematic debugging framework, root cause tracing, and defense-in-depth validation.

Use when building UI components, styling pages, or making visual/interaction decisions. Guides design thinking, anti-patterns, CSS architecture, and responsive patterns.

Generate Excalidraw diagrams with a hand-drawn aesthetic. Pushes elements to a live Excalidraw canvas via HTTP API, or renders to PNG/SVG.

Orchestration SOP for executing implementation plans. Assigns slices to a persistent team, runs validation gates per slice. The orchestrator coordinates — it does not implement.

Use when creating or updating GitHub issues. Enforces self-contained issues that an AI agent can implement without conversation history. Use when user says "create an issue", "file an issue", "gh issue", "update the issue", or wants to turn a plan into a trackable issue.

Run N identical parallel subagents on the same task for independent validation. Use when you want consensus through redundancy — multiple agents independently analyze, review, or test the same thing, then results are compared for agreement, disagreements, and unique finds. Invocation: /independent-review [count] "task"

Apply when writing, reviewing, or refactoring Laravel PHP code — controllers, models, migrations, queries, jobs, caching, validation, security, and architectural patterns. Also triggers for Inertia, Livewire, Breeze, and Jetstream work.

Review and update Claude.md files — check template compliance, surface missing requirements/boundaries, and propose ledger entries.

Transform shaped parts into a concrete model — DB schema, UX flows, and architecture. The modeling step between shaping and planning.

MANDATORY for naming any code identifier — variable, function, file, folder, class, database column, route, CSS class. Always returns a 5-10 candidate slate; the consumer picks. TRIGGER when proposing or choosing a name, on /naming, on "rename", "ideas", "options", "what should I call", or any new file/class/method/column/route. DO NOT TRIGGER when editing a body that does not introduce or change an identifier, when restructuring code (architecture, not naming), or when labeling UI for end us...

Add pros/cons/confidence to solutions. Append to any prompt.

Dispatch 5 parallel persona subagents for diverse takes on a question. Each persona applies their philosophy within the user's constraints.

Use when user says KISS, pragmatic, don't overengineer, ship it, keep it simple. Also for planning features, reviewing code, or architectural decisions.

Apply this skill whenever writing, reviewing, or refactoring React code. This includes creating or modifying components, hooks, forms, data fetching, state management, routing, testing, and TypeScript patterns. Triggers for performance issues (re-renders, bundle size, waterfalls), composition patterns, effect anti-patterns, accessibility violations, security concerns, and architectural decisions. Also use for React code reviews and refactoring existing React code to follow best practices. Cov...

Use when checking changes for capability regressions — loss of user-facing capability ("the user can no longer X") or loss of system capability ("our system can no longer Y"). Maps a diff to affected user flows and system capabilities, traces each through the code, reports any that no longer work. Triggers on "/regressions", "check for regressions", "regression review", or before merging changes that touch user flows or system functions.

Reviews planning artifacts — shapes, models, slices, and plans. Dispatches 5 parallel specialized agents. Use when reviewing any artifact from the shaping → modeling → slicing pipeline.

Use for code review - runs all reviewers in parallel on uncommitted changes

Use this methodology when collaboratively shaping a solution with the user - iterating on problem definition (requirements) and solution options (shapes).

Use when exploring/explaining code, designing/updating architecture, or when asked to visualize structure. Shows annotated file trees inline.

Takes a shaped and modeled feature and produces vertical implementation slices with acceptance criteria and validation requirements. Each slice ends in demo-able functionality. The plan becomes an immutable contract.

Framework for working solo — no subagents, deep full-file reads, thorough research before acting. Use when context window can absorb the full picture. For agent-based work, use /subagents or /team.

Framework for dispatching one-shot subagents that complete a task and return. Covers prompting (WHAT/WHY, never HOW), prompt structure (Story/Business/Goal/DoD/Workflow), and validation via DoD. For persistent teams, use /team.

Framework for creating and coordinating persistent teams. Teams persist across slices and turns — teammates accept new work via SendMessage. Covers team lifecycle and dispatch patterns. For one-shot agents, use /subagents.

Code intelligence for the local codebase — search, callers, definitions, symbols, complexity, file/method reads with rich architectural context. Use whenever you need to find, understand, or trace relationships in code instead of reaching for raw grep or unfiltered file reads.

Tests code changes by tracing real user flows. Lists flows affected by uncommitted changes, spawns one subagent per flow to trace execution and find gaps, then evaluates architecturally. Use when user says "user test", "test the flows", "trace user flows", or after completing a feature.