akornmeier

Compatibility command for the streamlined unattended developer workflow. Plans a software task with sl-plan when needed, then routes execution through sl-run in mode:unattended. Prefer sl-plan followed by sl-run for new workflows.

Run an explicit, non-mutating compatibility diagnostic for the super-looper plugin. Use only when validating a Claude Code or Codex installation, runtime adapter, bundled reference and script resolution, interactive question support, and one-worker subagent…

Compatibility command for interactive implementation. Plans a software task when needed, then routes canonical Markdown execution through sl-run in mode:interactive. Prefer sl-run directly for new workflows.

Compatibility command for the streamlined unattended developer workflow. Plans a software task with sl-plan when needed, then routes execution through sl-run in mode:unattended. Prefer sl-plan followed by sl-run for new workflows.

Explore requirements and approaches through collaborative dialogue, then write a right-sized requirements document. Use when the user says "let's brainstorm", "what should we build", or "help me think through X", presents a vague or ambitious feature request,…

Document a recently solved problem to compound your team's knowledge or CONCEPTS.md, the project's shared domain vocabulary.

Create a compact cross-session handoff for research, debugging, design, or other non-run work whose important context is not already durable. Do not use for sl-run work: its state path and review packet are the handoff.

Run an explicit, non-mutating compatibility diagnostic for the super-looper plugin. Use only when validating a Claude Code or Codex installation, runtime adapter, bundled reference and script resolution, interactive question support, and one-worker subagent…

Transform an OpenSpec change phase into UI-ready build prompts through a 3-step pipeline. PRD generation, then UX specification, then build-order prompts. Use when starting implementation of an OpenSpec feature phase, or when the user mentions…

Refine and clarify PRD documentation through structured questioning using the visual AskUserQuestion tool

Convert a rough MVP idea into a demo-grade PRD (Steps 1-7)

Use when translating PRDs, feature specs, or product requirements into UX specifications for mockup tools like Google Stitch, Figma, or similar. Use before creating visual designs, wireframes, or component specs.

Use when translating UX specifications into build-order prompts for UI generation tools. Triggers when user has a UX spec, PRD, or detailed feature doc and needs sequential, self-contained prompts for tools like v0, Bolt, or Claude frontend-design.

Adapter for executing OpenSpec change proposals using subagent-driven-development. Parses OpenSpec structure, groups tasks by phase, and creates one PR per phase.

How to use Chrome DevTools MCP for browser debugging. Use when you need to inspect pages, take screenshots, debug UI issues, or verify visual changes.

Use when building React UIs with component libraries, implementing forms, dialogs, navigation, or data display. Use when user mentions shadcn, Radix UI, Base UI, or asks about accessible React components. Proactively suggest when building UI that would…

Design-engineering guidance for UI motion, interaction polish, gesture physics, Apple-style fluid interfaces, animation terminology, motion opportunity audits and plans, animation code reviews, and throwaway interaction prototypes. Use when animation or…

Monitors GitHub pull requests through CI and automated review. Use when the user asks to watch, monitor, or babysit a PR, investigate failed checks, or respond to review-bot comments.

Automates browsers with Playwright CLI for UI testing, screenshots, navigation, scraping, and parallel browser sessions. Use when a task requires headless browser interaction or verification without a user-driven browser.

Builds and reviews bespoke D3.js visualizations, including SVG or canvas charts, networks, hierarchies, maps, scales, zooming, brushing, and transitions. Use when a task mentions D3 or needs custom interactive visualization beyond a standard chart library.

Creates polished technical and product diagrams as standalone HTML with embedded CSS and inline SVG. Use for architecture, flowchart, sequence, state, ER, timeline, swimlane, quadrant, nested, tree, layer, Venn, and pyramid diagrams that need editorial page…

Generates spoken audio with the ElevenLabs text-to-speech API. Use when converting text, summaries, or narration into an audio file or when the user asks to play generated speech aloud.

Creates concise GitHub pull requests from the current branch and diff. Use when the user asks to file, open, or create a PR.

Designs or runs multi-agent improvement loops with isolated builders, fresh critics, inspectable quality bars, iterative repair, and progress tracking. Use for reference-driven artifact improvement, independent review, blind comparison, or Gauntlet Loop…

Monitor a pull request through review and CI. Use when the user asks to monitor, watch, or babysit a PR.

File a concise pull request. Use when the user asks to file, open, or create a PR.

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui in React projects (Next.js,…

Manages shadcn-vue components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn-vue in Vue or Nuxt projects, component registries,…

Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.

Creates, improves, and reviews Claude Code Agent Skills. Use when the user wants to author a new skill, package a workflow or domain expertise into one, rightsize a skill that has grown too long, work out why a skill never fires, or health-check the whole…

Creates, updates, and executes HTML implementation plans saved to specs/. Use when the user asks to plan, spec, or design work before building it; to revise or re-reference an existing plan; or to implement a plan that already exists. Handles embedded…

Drive cmux — the terminal multiplexer / agent-surface control CLI — from natural language. Use this whenever a prompt asks you to open, inspect, prompt, read, or tear down cmux windows, workspaces, panes, surfaces, or agent sessions. Prefix orchestration…

Use when a bug, stack trace, failing test, or regression is reported ("X is broken", "crash on Y", "failing since Z"). Creates a `pipeline` debug team — researcher → debugger → reviewer-correctness → developer → tester — coordinated through a `TaskList`…

Use when code has been written and needs multi-lens critique ("review this", "audit", "check the PR", "lint this change"). Creates a `parallel-panel` review team with three named teammates (`reviewer-architecture`, `reviewer-correctness`, `reviewer-security`)…

Use when the user wants a plan taken to implemented+reviewed+tested in one shot ("ship it", "full cycle", "end-to-end", "take the plan to green"). Creates a `staged-team` whose members rotate per stage — work → review → test — so each downstream stage checks…

Use when an approved plan doc exists and the user wants code written ("implement the plan", "build phase 2", "code this up"). Parses the plan to classify frontend/backend/full-stack. Frontend-only and backend-only paths run as a `solo` developer dispatch;…

Use when the user has selected an idea from an ideation doc (or names a concrete feature directly) and needs it expanded into user stories and acceptance criteria. Produces `docs/brainstorms/<YYYY-MM-DD>-<slug>-requirements.md` with Given/When/Then criteria,…

Use at the end of a full cycle (after `/ship` or `/debug`) to harvest the run into durable signal — a solution doc in `docs/solutions/<category>/` plus curated memory files. Dispatches `docs-writer` then `/memory-curate` for families near the soft limit.…

Use when the user asks to explore options, brainstorm directions, or propose approaches for a fuzzy problem ("what could we do about X", "propose", "spitball", "ideas for"). Produces a ranked set of 3–5 scored ideas in `docs/ideation/<YYYY-MM-DD>-<slug>.md`…

Use when an agent's memory file has exceeded the soft or hard character limit and needs consolidation. Runs three stages in order — dedupe, score-and-drop, summarize — and stops as soon as the file is under the soft limit. Invoked by the orchestrator when…

Encodes Emil Kowalski's craft sensibility for UI polish, motion, and the invisible details that make software feel great. Use whenever the user is reviewing UI code, designing or critiquing an animation, building a component (button, modal, drawer, popover,…

Autonomous execution workflow integrating OpenSpec with Ralph Wiggum methodology. Use when implementing approved OpenSpec changes with longer autonomous runs - compiles OpenSpec files (proposal.md, design.md, tasks.md) into a PRD.json for iterative execution…