cleanexpo
- 430 skills
- 0 followers
- last month last updated
- ▌ Brand Ambassador 2 · cleanexpoAct as a brand ambassador — create authentic, platform-specific social media content that embodies a brand's identity and connects with audiences. Use this skill whenever the user asks to "create social media content for a brand", "act as a brand ambassador", "write ambassador posts", "promote [brand] on social media", "create influencer-style content", "write authentic brand content", "social media ambassador", or any request involving representing a brand through social content. Also triggers on "ambassador voice", "brand promotion posts", "influencer content", "authentic brand posts", "UGC-style content", or when someone wants social media content that sounds like a real person recommending a brand rather than corporate marketing copy. Even if the user just says "help me promote [brand]" or "I need content for [brand]'s social channels" — use this skill.
- ▌ Grill Me 2 · cleanexpoForces explicit scope clarification before any code change. Invoked at Stage 2 of the Synthex development loop (see prd.md). Produces 3–7 scope-defining questions and waits for human confirmation before implementation begins. No code may be written until the Grilled scope is written to HANDOFF.md.
- ▌ Boardroom 2 · cleanexpoMulti-model triangulation. Runs the same prompt through 2–4 LLMs in parallel (typically Gemma 4 local + DeepSeek V4 + Claude Sonnet) and synthesises a single answer that captures consensus, surfaces disagreement, and resolves divergence with senior reasoning. Auto-escalates to Claude Opus when panel divergence is high. Invoke for high-stakes decisions where one model's voice is not enough — brand strategy, architecture choices, sensitive client communications, copy with measurable conversion stakes. Skip for routine tasks (use standard intent routing instead).
- ▌ Creative Director 2 · cleanexpoSenior Creative Director (15+ yr calibration). Cross-channel Creative Director enforcing Phase 4 Remotion Evidence Protocol (REM-1 Direct Sourcing · REM-2 No Projected Earnings · REM-3 AEO Companion-Page Bridge) on every visual asset. Owns named-but-not-Phill expert byline framework (CCW L9 carve-out). Pairs with senior-copywriter on Hub articles + LinkedIn posts + Remotion scripts. Closes every visual with an attribution-hypothesis, EXIF/permission verification, and a companion-page schema link. Reads ceo-foundation.md + verification-gates.md at every invocation.
- ▌
- ▌
- ▌
- ▌
- ▌ API Contract 2 · cleanexpoTyped API contract patterns enforcing consistency between FastAPI backend (Pydantic response models) and Next.js frontend (Zod response schemas). Covers schema location conventions, OpenAPI documentation, error response contracts, and versioning strategy.
- ▌
- ▌ Health Check 2 · cleanexpoLiveness, readiness, and deep dependency health endpoints for Next.js and FastAPI. Codifies the project's three-tier health probe architecture, Docker healthchecks, cron-based monitoring, and system health script.
- ▌
- ▌
- ▌
- ▌ CSV Processor 2 · cleanexpoStreaming CSV parse and generate patterns for large file support across Next.js frontend and FastAPI backend. Covers row-by-row streaming, Zod row validation, Pydantic export models, Australian locale formatting (DD/MM/YYYY dates, AUD currency), and memory-safe chunked processing.
- ▌
- ▌
- ▌
- ▌ Skill Manager 2 · cleanexpo bundleAnalyse project skill gaps, generate new skills, browse skill catalogues, and validate skill health. Triggers on "skill gap", "generate skill", "skill catalogue", "skill health", "missing skills", or when the project needs new agent capabilities.
- ▌ State Machine 2 · cleanexpoFinite state machine patterns for complex flows using Python Enums and TypeScript union types. Covers state definition, transition validation, guard conditions, and side effects for orchestrator tasks, workflow execution, and UI component states.
- ▌ Vector Search 2 · cleanexpopgvector embedding queries, similarity search, hybrid search, and multi-provider embedding generation for Supabase/PostgreSQL. Codifies the project's existing Memory Store and RAG Pipeline vector infrastructure.
- ▌
- ▌
- ▌
- ▌ Claude Browser 2 · cleanexpoClaude Chrome extension tools for personal browser automation in the user's actual browser. Use for logged-in sessions, form filling, and interactive tasks.
- ▌ Cron Scheduler 2 · cleanexpoScheduled task management patterns for Vercel cron jobs, Next.js API route handlers, and backend periodic tasks. Covers cron expression conventions, CRON_SECRET authentication, overlap protection, timezone handling (AEST/AEDT), and failure alerting.
- ▌
- ▌ Email Template 2 · cleanexpoResponsive transactional email templates using React Email and Resend. Covers Scientific Luxury dark-theme email design, Australian locale formatting, template composition, preview tooling, and integration with the project's cron jobs and notification flows.
- ▌
- ▌ Error Taxonomy 2 · cleanexpoStructured error codes, categories, and user-facing messages for consistent error handling across FastAPI backend and Next.js frontend. Enforces a unified error contract between API responses and client-side handling.
- ▌
- ▌
- ▌
- ▌ Data Validation 2 · cleanexpoZod and Pydantic validation patterns for input sanitisation, schema definition, and type-safe data contracts across the Next.js frontend and FastAPI backend. Enforces validation at system boundaries.
- ▌
- ▌
- ▌
- ▌ Blueprint Engine 2 · cleanexpoHybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps
- ▌ Council Of Logic 2 · cleanexpoMathematical first principles validation for code quality. Triggers on "optimise", "algorithm", "performance", "complexity", "O(n)", or when reviewing code for efficiency. Enforces Turing (algorithmic), Von Neumann (architecture), Bezier (animation), and Shannon (compression) principles.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Metrics Collector 2 · cleanexpoDatabase-backed metrics instrumentation for Supabase/PostgreSQL with standardised metric types (counters, gauges, histograms), naming conventions, time-series aggregation, and optional OpenTelemetry export. Codifies the project's existing AgentMetrics and analytics patterns.
- ▌ Scientific Luxury 2 · cleanexpoDesign system enforcement for Scientific Luxury tier UI. Triggers on "design", "UI", "component", "styling", "animation", or when creating React components. Enforces OLED black backgrounds, spectral colours, single-pixel borders, physics-based animations, and timeline layouts.
- ▌
- ▌
- ▌ System Supervisor 2 · cleanexpo bundleArchitecture drift detection, silent failure scanning, hallucination prevention, and feature completeness auditing. Activates at phase boundaries, before merges, or on explicit audit requests.
- ▌
- ▌ Dashboard Patterns 2 · cleanexpoReal-time dashboard patterns codifying the project's Status Command Centre component library, timeline/orbital layout, Supabase Realtime integration, and Scientific Luxury design enforcement for all data visualisation surfaces.
- ▌ Execution Guardian 2 · cleanexpo bundlePre-execution governance with dynamic validation gates, risk/confidence scoring, and structured error format. Activates before destructive, multi-layer, or security-impacting operations to assess safety.
- ▌ Input Sanitisation 2 · cleanexpoXSS, SQL injection, and command injection prevention patterns for the Next.js frontend and FastAPI backend. Covers output encoding, parameterised queries, and OWASP Top 10 input handling.
- ▌
- ▌ Playwright Browser 2 · cleanexpoPlaywright CLI and MCP tools for headless browser automation, E2E testing, screenshots, and web scraping. Use for CI-safe browser operations.
- ▌ Structured Logging 2 · cleanexpoJSON-structured logging patterns with correlation IDs, log levels, and contextual metadata for the FastAPI backend (structlog) and Next.js frontend (Logger class). Enforces consistent observability across the stack.
- ▌
- ▌
- ▌
- ▌ Genesis Orchestrator 2 · cleanexpoAutonomous project orchestration protocol for Next.js full-stack builds. Triggers on "build", "implement", "create feature", "plan", "architecture", or when starting new phases. Enforces phase-locked execution, token economy, and sectional verification gates.
- ▌
- ▌ Notebooklm Second Brain 2 · cleanexpoNotebook First retrieval policy — query NotebookLM notebooks before web search or context dumping
- ▌ Storm 2 · cleanexpoUse when the user wants a comprehensive, neutral, citation-grounded article, report, briefing, or explainer researched from scratch on a topic — invoked as /storm or by asking to "STORM" a topic. Reproduces the Stanford STORM method (perspective discovery + retrieval-grounded multi-perspective Q&A → outline → grounded long-form write-up). Not for quick factual lookups, opinion pieces, or topics that need private/internal data.
- ▌ Skybridge 2 · cleanexpo bundleGuide developers through creating and updating ChatGPT and MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging, running dev servers, deploying and connecting apps to ChatGPT. Use when a user wants to create or update a ChatGPT app, MCP app, MCP server or use the Skybridge framework.
- ▌ Readiness Architect 2 · cleanexpoGenerates a complete SPM-ready readiness scope for any project, product, app, authority site, CRM, contractor network, training platform, marketing engine, mobile app, internal operating system, AI agent system, or launch-readiness task. Use when preparing a project for /spm, /judge, /goal, shipit, launch, production readiness, operational readiness, connector readiness, security readiness, or client purchase readiness.
- ▌ Spm 2 · cleanexpoSenior Project Manager spec command. Use before implementation to convert a rough task, feature, bug, idea, ticket, PR, or repo area into a decision-grade spec.md with specialist review, judge-style challenge, verification, stress tests, and goal-ready acceptance criteria.
- ▌ Judge 2 · cleanexpoMandatory pre-build challenge gate. Use before approving or building any feature, connector, automation, agent, hook, MCP server, UI change, database change, or architecture plan. Performs first-source evidence review, devil's advocate critique, existing capability review, UX review, security/privacy review, test/stress review, and return-on-effort scoring.
- ▌ Session Handoff 2 · cleanexpoGenerate a precise handoff before stopping, changing terminals, handing work to another agent, opening a PR, or resuming later. Captures summary, starting point, locked decisions, shipped work, key files, running state, verification, deferred questions, and exact pickup point.
- ▌ Resume From Handoff 2 · cleanexpoResume work from a session handoff. Reads the latest handoff, verifies current repo state against it, reconciles drift, then continues from the documented pickup point without re-deriving old context. Verification is read-only and mandatory before any work resumes.
- ▌ Fact Checker · cleanexpoVerify factual accuracy of all claims, data, and information across the platform. Use when reviewing content, service descriptions, or business information for correctness.
- ▌ Iicrc Validator · cleanexpoValidate IICRC standard references, certification claims, and technical terminology. Use when working on service pages, guides, or content that references IICRC standards.
- ▌ Disaster Recovery Domain · cleanexpoDomain knowledge for Australian disaster recovery and restoration services. Use when working on content, service descriptions, or any feature related to the DR/NRPG business model.
- ▌ Typescript Coding Standards · cleanexpoTypeScript coding standards for the DR-NRPG platform. Loaded automatically when working on .ts/.tsx files. Covers types, async patterns, error handling, naming, and best practices.
- ▌ Australian Business Validator · cleanexpoValidate Australian phone numbers, addresses, postcodes, ABN/ACN numbers, and state/territory references. Use when reviewing any content with Australian business data.
- ▌ Tdd · cleanexpoUse when implementing any feature or bug fix. Hard gate — no production code without a failing test first. Applies to vitest (apps/web/) and pytest (apps/backend/). Triggers on "implement", "add feature", "fix bug", "new component", "new endpoint", or any code-writing task.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Git Worktrees · cleanexpoCreates isolated git worktrees for feature development with automatic dependency installation, baseline test verification, and .gitignore safety checks. Extends the /minion isolation model with a formal worktree workflow. Triggers on "new feature", "isolate", "worktree", multi-session work, or when parallel development is needed.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Xaem Theme UI · cleanexpo bundleTwo-pass theme generation and code translation pipeline. Pass 1 generates high-entropy visual themes (colour palettes, glow intensities, animation timing, typography weights). Pass 2 translates themes into CSS variables, TypeScript design tokens, Tailwind config, and Framer Motion presets. Complements scientific-luxury by handling creative generation before constraint enforcement.
- ▌
- ▌
- ▌
- ▌
- ▌