bluzir

Build an HTML slide deck (1920×1080, keyboard nav, exportable) when user asks for a presentation, pitch deck, slides, or keynote. Uses deck_stage.js starter and Claude Design taste rules.

Screenshot + console sweep + visual inspection of an artifact for layout/color/typography regressions. Silent on pass, reports only on issues. Use after /done reports clean and before end-of-turn.

Build animated motion design (explainer, transition reel, product intro). Uses Stage/Sprite timeline from animations.jsx for in-browser compositions or Remotion for full video/MP4 workflows.

Apply buffered tweaks from pending.yaml to the source HTML file. Invoked when user says "save tweaks", "apply tweaks", "persist panel changes", or runs /apply-tweaks.

Generate a working demo artifact on dummy content so the user can see a reference implementation. Use when user says "show me an example deck", "what does a prototype look like", "give me a starter", "I want to see an example of X". Generates live — not from a static gallery.

Extract or build a design system (tokens, components, style guide). Use for "design system", "style guide", "tokens", "UI kit".

First-run setup + health check. Verifies Chrome DevTools MCP, installs optional deps (monolith, pptxgenjs, puppeteer), creates working dirs, runs smoke test. Use on fresh clone or when things feel broken.

Export an HTML artifact to PDF via headless Chromium (puppeteer Page.pdf). For multi-slide decks one page per <section>.

Execute quality-gated multi-step workflows with evaluator checks, approval gates, and typed results. Orchestrates Claude Code and Codex CLI skills into reproducible flows with auto-retry on failure.

Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).

Designer's eye review of a live site. Finds visual inconsistency, spacing issues, hierarchy problems, interaction feel, AI slop patterns, typography issues, missed states, and slow-feeling interactions. Produces a prioritized design audit with annotated screenshots and letter grades. Infers your design system and offers to export as DESIGN.md. Report-only — never modifies code. For the fix loop, use /qa-design-review instead.

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead.

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.

Import cookies from your real browser (Comet, Chrome, Arc, Brave, Edge) into the headless browse session. Opens an interactive picker UI where you select which cookie domains to import. Use before QA testing authenticated pages.