VibeCorp_PromptCEO

Builds production-grade Claude Projects and CustomGPTs, improves AI output quality using meta-thinking prompts, and architects self-improving AI systems. Use proactively when a founder wants to build a reliable AI workflow, automate a repeatable task with AI, improve the quality of AI outputs they're getting, feels stuck with generic AI responses, or wants to build internal tools powered by Claude. Trigger for "build a Claude project", "my AI outputs are generic", "how do I make Claude more specific", "build an AI workflow", "automate this with AI", or "my prompts aren't working".

One-command review pipeline. Chains CEO review → design review → eng review automatically. Surfaces only taste decisions for PD approval. Everything else runs autonomously.

Performance baseline measurement. Captures page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR.

Playbook for bootstrapped and early-stage SaaS founders based on proven case studies ($0 to $5M ARR with 6 people, and creator-to-business flywheel models). Use proactively when a founder is bootstrapped or capital-efficient, needs to grow without paid acquisition, is facing a churn crisis, wants to build a freemium or usage-based model, or asks "how do I grow without VC money". Also trigger for "PLG", "inbound-led outbound", "creator-led growth", "build in public", or "how did [bootstrapped company] grow".

Real browser automation for testing, QA, and demo verification. Provides Playwright-based browser control for navigating the live app, clicking elements, filling forms, taking screenshots, and verifying visual state.

Post-deploy monitoring. After release-engineer pushes to production, canary watches the live site for errors, performance regressions, and page failures.

The CEO's private brainstorming room and strategic sparring partner. Thinks WITH the founder before anything gets executed. Challenges assumptions, stress-tests ideas, validates strategic direction, runs thought experiments, and helps the founder decide what to command to subagents — and what NOT to. Use this BEFORE spawning any subagent swarm. Trigger for "I'm thinking about...", "does this make sense?", "help me think through...", "am I going in the right direction?", "stress test this idea", "play devil's advocate", "should I do X or Y", "I want to brainstorm", or any time the founder needs to think out loud before acting. This is not an execution agent — it never spawns other agents. It only thinks.

Generic compliance audit context. Load before any task touching verification tiers, regulated forms, document uploads, identity verification, or anything involving user identity. Also load before any task that might accidentally reintroduce payment processing or regulated contract functionality.

Write and publish PRDs, decision logs, sprint notes, and architecture docs to Confluence. Load when writing or publishing a PRD, updating a decision log, creating sprint notes, or reviewing documents on Confluence.

Diagnoses why content isn't converting and fixes it using the Trust Architecture framework. Use proactively when a founder asks why their content gets engagement but no customers, why traffic doesn't convert, why deals stall mid-funnel, or how to improve their content strategy. Also trigger for "my LinkedIn posts get likes but no leads", "my website traffic doesn't convert", "how do I build credibility faster", or any question about content ROI.

Prepares founders for all corporate structure and governance questions from investors. Covers entity formation, cap table management, board composition, founder dynamics, accounting infrastructure, and roles and titles. Use proactively when a founder mentions cap tables, equity splits, board seats, corporate structure, where they're registered, accounting setup, founder agreements, or any investor question about how the company is organized. Also trigger for "how should I structure my equity", "do I need a Delaware C-Corp", "how do I set up my cap table", or preparing the corporate section of a data room.

Chief Security Officer methodology. OWASP Top 10 + STRIDE threat model. Zero-noise — high confidence gate, false positive exclusions, independent verification. Each finding includes a concrete exploit scenario.

CSS design system rules — colour tokens, typography scale, spacing, shadows, border-radius, component classes, responsive breakpoints, and theme switching. The canonical source of truth for all visual styling decisions. Load this skill before any src/index.css or component styling work.

Build a complete design system or major design direction from scratch. Researches the competitive landscape, proposes creative risks, and generates realistic product mockups. Produces DESIGN_DIRECTION.md as the canonical design reference.

Generates production-quality HTML/React components with proper text layout, responsive reflow, and content-driven heights. No hardcoded heights. Text reflows on resize. Framework-aware for React.

Analyses reference websites to extract design system patterns — colour palettes, typography scales, spacing systems, layout structures, component patterns, and interaction states. Outputs structured design tokens that the ui-designer agent can consume. Load this skill when the task involves studying competitor or reference site designs.

Generate multiple AI design variants for any UI feature, produce a side-by-side comparison board in HTML, and iterate until PD approves a direction. Builds taste memory that biases toward PD preferences over time.

Builds owned distribution infrastructure for startups before and after product launch. Covers distribution-first strategy, waitlist engineering, community-led growth, earned media, co-marketing loops, AEO/GEO for AI search visibility, and content moat building. Use proactively when a founder asks about building an audience, organic growth, content strategy, SEO, LinkedIn presence, getting visibility in AI search tools, co-marketing, partnerships, or any question about distribution that isn't purely paid acquisition. Trigger for "how do I build an audience", "how do I get organic traffic", "distribution before product", "how do I get into ChatGPT results", or "how do I build a waitlist".

Reads every documentation file in the project, cross-references the current diff, and updates everything that drifted. Catches stale READMEs, outdated ARCHITECTURE, and missing CHANGELOG entries.

Scaffold new features with standard file structure before implementation

Prepares founders for all financial, use-of-funds, and fundraising mechanics questions from investors. Covers unit economics, valuation methodology, how much to raise, financing instruments, burn rate management, exit strategy, and fundraising execution. Use proactively when a founder mentions unit economics, CAC, LTV, burn rate, runway, valuation, SAFEs, convertible notes, use of funds, financial projections, or any investor question about numbers. Also trigger for "how do I value my company", "how much should I raise", "what are my unit economics", "am I default alive", or building the financial section of a data room or pitch deck.

Frontend data fetching patterns — React Query (TanStack Query) setup, custom hooks, caching strategies, optimistic updates, error boundaries, and API layer abstraction. Load this skill before any API integration work in src/.

Develops complete go-to-market strategies for startup founders. Incorporates Pressure Profile ICP system, C.A.R.E. framework, Offer Testing Matrix, Distribution Triangle, 4-Stage Growth Sequencing, and LinkedIn GTM systems. Use proactively when a founder mentions GTM planning, customer acquisition, ICP, messaging, channel strategy, pricing, outbound, content strategy, LinkedIn, co-marketing, distribution, or any question about how to get customers. This is the CEO growth hat — trigger it whenever the conversation shifts from building to growing. Also trigger for "who should I target", "how do I message", "which channels", or "why isn't my outreach working".

Runs a complete Head of Growth function for founders and growth leads — weekly growth audits, experiment design, channel optimization, and growth loop analysis. Use this skill whenever a founder needs to run systematic growth analysis, design experiments, audit their metrics, identify growth bottlenecks, or build a repeatable weekly growth cadence. Trigger for "analyze my growth", "what should I focus on", "design a test", "audit my channels", "weekly growth review", or any time the question is about understanding and improving metrics systematically.

Systematic root-cause debugging. Iron Law — no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fix attempts.

Investor demo readiness standards — demo data quality, mock data hygiene, known-good demo flows, data leak prevention, and presentation checklist. Load this skill before any demo preparation or when demo-tester agent runs.

Prepares founders for all intellectual property and legal readiness questions from investors. Covers IP portfolio assessment, patent strategy, regulatory risk mapping, ownership chain documentation, and vulnerability audits. Use proactively whenever a founder mentions patents, IP ownership, legal risks, regulatory compliance, product liability, who developed the technology, or any investor question about what's unique and defensible. Also trigger for "do I need a patent", "what regulatory risks apply to me", "how do I protect my IP", or preparing the IP section of a data room.

Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns. Auto-detects CLI vs MCP backend.

Manages Jira issues, projects, and workflows using Atlassian MCP. Use when asked to "create Jira ticket", "search Jira", "update Jira issue", "transition issue", "sprint planning", or "epic management".

Cross-session memory management. Accumulates patterns, pitfalls, and preferences. Review, search, prune, and export learnings so gstack gets smarter on your codebase over time.

Conducts TAM/SAM/SOM market sizing, competitive landscape analysis, and market entry timing for startup founders. Includes the T-Score Market Entry Timing Equation and Trend-Spotting OS. Use proactively whenever a founder mentions market size, TAM, "how big is this market", competitive analysis, market timing, "why now", "are we too early", "when should we launch", or preparing market slides for investors.

Transform conversations and discussions into structured Notion documentation

Prepare for meetings by gathering context and creating comprehensive agendas

Research topics and document findings in Notion with organized structure and sources

Parse specifications and create implementation plans with task tracking in Notion

Obsidian Knowledge Architecture — primary brain for all project knowledge. Vault location, folder structure, canvas architecture, session-end ritual, and Jira/Notion linkage conventions. Load this skill before writing any Obsidian files.

YC-style product discovery session. Six forcing questions that reframe the product before code is written. Pushes back on framing, challenges premises, generates implementation alternatives. Design doc output feeds all downstream skills.

Structured CEO-level review of any PRD or feature plan. Four scope modes. Challenges assumptions, finds the 10-star product hiding inside the request.

Senior Designer review of any feature plan or mockup. Rates each design dimension 0-10, explains what a 10 looks like, detects AI slop. Interactive — asks PD one question per design choice.

Engineering Manager review of any feature plan. Architecture diagrams, data flow, state machines, edge cases, test matrix. Forces hidden assumptions into the open.