giljae

Write acceptance criteria that make scope testable and aligned.

Improve user activation by identifying key moments to value.

Refine backlog items to improve readiness and prioritization.

Generate and expand product or feature ideas from a goal, problem, or opportunity.

Summarize the business model using the classic canvas structure.

Plan work against team capacity and constraints.

Choose and compare acquisition, distribution, or communication channels.

Compare initiatives by expected benefits, costs, and risk-adjusted value.

Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions.

Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time".

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".

Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy".

Safety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode".

Chief Security Officer mode. Performs OWASP Top 10 audit, STRIDE threat modeling, attack surface analysis, auth flow verification, secret detection, dependency CVE scanning, supply chain risk assessment, and data classification review. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".

Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pages. Creates DESIGN.md as your project's design source of truth. For existing sites, use /plan-design-review to infer the system instead. Use when asked to "design system", "brand guidelines", or "create DESIGN.md". Proactively suggest when starting a new project's UI with no existing design system or DESIGN.md.

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site.

`/ai-use-case-score` scores personal AI use cases on Value x Feasibility x Safety and tiers them into Do Now, Do This Quarter, Park, or Avoid.

`/data-insights` analyzes CSV or Excel data and produces plain-English insights. Use when the user wants quick answers about targets, trends, anomalies, segments, top/bottom performers, averages, and totals.

`/decision-memo` drafts a 1-page decision memo that forces a yes/no call: context, complication, options, recommendation, risks, and ask.

`/deck-pipeline` runs a four-step presentation workflow: strategist, builder, critic, fixer. Use for high-stakes decks that need narrative structure and a critique pass.

`/gamma-deck` generates a Gamma presentation from a storyline or content file. Use after `/storyline` when the user wants a PPTX or Gamma URL.

`/issue-tree` breaks a complex problem into MECE branches and testable hypotheses. Use before analysis, work planning, strategy decomposition, or case-style problem solving.

`/mckinsey-critic` reviews decks, memos, outlines, and strategies like a consulting engagement manager: grade, section issues, top fixes, and what to preserve.

`/meeting-prep` prepares outcome-driven meetings with a 3-bullet pre-read, time-boxed agenda, top talking points, and likely objections with rebuttals.

Phase 3. Act as the Engineering Manager. Audits architecture, sets up isolated environments, extracts AST repo map, and creates atomic plans.

Phase 1. Act as the strategic visionary and brainstormer. Integrates /office-hours and brainstorming rules.

Phase 2. Act as the ruthless CEO. Aggressively challenges the design document to cut scope.

Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

Fast-track composite skill that chains CEO, Design, and Engineering reviews automatically, dumping a final spec and AST context.

The execution engine. Merges subagent-driven-development, executing-plans, and test-driven-development into a ruthless coding machine.

The diagnostic clinic. Mashing /investigate and systematic-debugging. Blocks naive code patching without evidence.

Browser-based automatic QA. Replicates /qa capability.

Connect an external inspiration source (Mobbin, Savee, Dribbble, Behance, etc.) as a first-class source in all Lazyweb design skills. Authenticates via headless browser, persists session cookies, and registers the source so future design research automatically includes it alongside Lazyweb. Trigger on: "add inspo source", "add inspiration source", "connect Mobbin", "connect Savee", "add design source", "connect inspiration", "add Dribbble", "link Behance".

Cross-pollination design brainstorm. Deliberately searches outside the obvious category to find novel patterns that could be applied in unexpected ways. The "zig when everyone zags" skill — finds inspiration from domains nobody in your space is looking at. Trigger on: "brainstorm design ideas", "creative alternatives for", "design exploration", "what if we tried", "unconventional approach to", "fresh ideas for", "think outside the box", "surprise me".

Capture a screenshot of the user's current design, find similar screens in Lazyweb, and generate concrete improvement ideas backed by real references. Use when the user has an existing design and wants feedback or improvement suggestions. Trigger on: "improve this design", "how can I make this better", "critique my design", "design feedback", "what should I change", "make this look better", "compare my design to", "design review".

Deep design research combining Lazyweb's screenshot database with web research. Produces a structured research report with downloaded reference screenshots. Use when the user needs competitive analysis, best practices research, or wants to understand how the best apps handle a specific design problem. Trigger on: "best practices for", "how should I design", "what do top apps do", "competitive analysis for", "design research on", "what works well for", "research how others do".

Find app screenshots and UI references quickly. Downloads results locally and groups them by pattern. Use when the user wants to see examples of a specific screen, UI element, or flow without a full research report. Trigger on: "show me examples of", "how do other apps do", "design inspiration for", "UI reference for", "what does X's app look like", "find screenshots of", "show me how", "references for".

Disconnect an inspiration source from Lazyweb design skills. Lists connected sources and removes the selected one. Trigger on: "remove inspo source", "remove inspiration source", "disconnect Mobbin", "remove design source", "unlink source".

Enterprise collaboration standard for technical enablement and stakeholder alignment in Antigravity.

Basic "make no mistakes" instruction for Antigravity.