cleanexpo
- 430 skills
- 0 followers
- last month last updated
- ▌ Browser Auth · cleanexpoDrives an authenticated browser session on synthex.social (or localhost) WITHOUT the flaky Chrome extension. The reliable path is a committed Playwright script (scripts/browser/dashboard-audit.mjs) that logs in with the SYNTHEX_TEST_EMAIL / SYNTHEX_TEST_PASSWORD test account and audits every integration surface. Use whenever asked to "log in", "authenticate", "audit the dashboard", "check what's connected", or before browser-verify / site-smoke-test on /dashboard/* routes.
- ▌ Business Dna · cleanexpo bundleSynthex brand DNA extractor. NEVER produce surface-level brand descriptions ("professional and friendly"), generic persona archetypes ("busy professional aged 25–45"), or tone descriptions that could apply to any brand. ALWAYS extract vocabulary the brand actually uses, describe what the brand explicitly is NOT, and ground the audience in a specific outcome they are seeking. Activate on ANY request to extract brand identity, build a DNA profile, define a brand voice, analyse a website for brand signals, or create a persona profile.
- ▌ CLI Anything · cleanexpoCLI-Anything integration guide for Synthex. Documents how to wrap external tools (FFmpeg, Vercel, Supabase, Stripe, GitHub, Playwright, social platforms) as agent-native CLIs for both internal dev/ops and client-facing automation. Use when adding new CLI-based capabilities to the autopilot or workflow engine, or when wiring a new external tool for agent consumption.
- ▌ Fable Engine · cleanexpoTurn a plain-English vision or task into a verified, build-ready spec before any code. Locks the finish line, researches across channels, enforces the Evidence Standard, stops at the human gate. Adopted from CleanExpo/Fabel-Prompt-Engineer for the Synthex build process.
- ▌ Ship Loop Pr · cleanexpoPush + open PR child loop. Pre-conditions all five inner layers (build, test, sanity, watch, smoke) green AND staged/uncommitted local changes detected. Refuses to push from main branch. On non-fast-forward push rejection, rebases on origin and retries once. Records PR URL into ship-loop-state.json. Use standalone via /loop ship-loop-pr or wired into the master orchestrator.
- ▌ SQL Hardener · cleanexpo bundleSQL cleanup and security hardening for Supabase. Audits SQL files for missing indexes, weak RLS policies, and security gaps. Generates optimised migrations using the Supabase CLI. Use when cleaning up schema, strengthening security, or preparing for production deployment.
- ▌ Token Health · cleanexpoConnection token-health for Synthex integrations. Diagnoses "what's connected / why is the dashboard empty" by reading live connection state from the DB (no login needed), explains the refresh/monitor crons that keep tokens alive, and gives the reconnect runbook for connections that can't self-heal. Use on ANY "is X connected", "nothing's working", "tokens expired", "GA4/GSC/LinkedIn not loading", or integration-health question.
- ▌ Video Engine · cleanexpo bundleVideo generation pipeline guide for Synthex. Documents the 4-provider architecture (Runway, Synthesia, D-ID, Remotion), FFmpeg post-processing, media library integration, and God Mode gating.
- ▌ Auth Patterns · cleanexpoAuthentication and authorisation pattern guide for SYNTHEX. Documents the four auth layers (Supabase session, JWT token, RBAC permissions, owner bypass), when to use each, and the common mistakes that cause auth drift. Use when creating or modifying any authenticated endpoint or middleware logic.
- ▌ Browser Debug · cleanexpoAutonomous browser-based debugging of production and development issues. Captures console errors, network failures, JS stack traces, auth problems, and React hydration mismatches — and maps them to root causes and fixes. Use when a feature is broken in the browser but the server logs look clean, when a user reports a blank page or error, when auth is behaving unexpectedly, or when "it works in tests but not in the browser". Also use for "why is X broken?", "debug the dashboard", "check console errors".
- ▌ Heygen Avatar · cleanexpo bundleHeyGen avatar-video provider reference for Synthex. Documents the real env-driven HeyGen v2 client and its ElevenLabs voice pairing. NEVER call createAvatarVideo without a consent record. NEVER hard-code HEYGEN_API_KEY (Vercel env only). NEVER silently mock a live call — no key hard-blocks unless allowMockFallback is explicitly set. ALWAYS prefer an ElevenLabs audio_url (lip-sync) over HeyGen text TTS. Activate on ANY request to generate, poll, or debug HeyGen avatar videos, or wire avatar+voice generation.
- ▌ Research Lead · cleanexpoSenior Research Lead (15+ yr calibration · regulatory analysis · standards-body tracking · competitive intelligence · academic literature triage). Identifies + analyses external developments (product launches · regulatory changes · standards revisions · competitor moves · academic research) and translates them into integration-readiness analysis grounded in the locked Synthex/Unite-Group foundation. Output is structured findings · honest about verified vs hypothesised · references foundation rules + verification gates the new development affects · never fabricates sources. Reads ceo-foundation.md + verification-gates.md at every invocation.
- ▌ Route Auditor · cleanexpoSynthex API route compliance scanner. NEVER apply generic REST conventions without grounding in Synthex's specific security pattern. ALWAYS audit against: getUserIdFromRequestOrCookies() auth, { organizationId } on every query, Zod safeParse() on all mutations, withRateLimit() on AI routes, and migrate diff + db execute for schema changes. Activate on ANY request to audit a route, check API security, review an endpoint, or scan for auth or org-scope issues.
- ▌ Analytics Lead · cleanexpoSenior Analytics Lead (15+ yr calibration). Day-to-day narrative-from-data layer. Pairs with performance-attribution-lead — performance lead produces structured metrics, analytics-lead produces the storyline that ends in "this week, do X because Y, because if Z then we know we were right by D+N." Calibrated against Phase 1.4 hybrid data-then-instinct decision style — surfaces data picture + strategic framing + divergence + falsifiable hypothesis rather than smoothing it over. Reads ceo-foundation.md + verification-gates.md + reporting-templates.md at every invocation.
- ▌ Browser Verify · cleanexpoAutonomous browser-based verification of implemented features. Closes the verification gate without human intervention by navigating to a URL, capturing a screenshot, checking for console errors, confirming visible elements, and producing a structured PASS/FAIL report. Use immediately after implementing any UI feature, fixing a visual bug, or as the final step in the verification-gate.md checklist. Also use when the user asks "check if X is working in the browser", "verify the dashboard", or "confirm the page loads".
- ▌ Client Manager · cleanexpo bundleCampaign and client data management via Prisma ORM. Handles CRUD operations on campaigns, posts, projects, and user preferences. Tracks analytics and API usage. Use when user says "create campaign", "list campaigns", "update post", "delete project", "client data", or "manage analytics".
- ▌ Cro Specialist · cleanexpoSenior CRO Specialist (15+ yr calibration). Owns funnel architecture across all 4 brand conversion structures (RA A1–A4 · DR D1–D5 split · NRPG N1–N6 · CARSI Snapshot funnel · CCW Hub→Cart). Surfaces friction-fix proposals from locked friction audits — but ONLY after Gap audit verifies which hypothesised frictions are real, and only as single-variable tests with explicit kill thresholds and rollback plans. Reads ceo-foundation.md + verification-gates.md + gap-audit-playbooks.md at every invocation.
- ▌ Playwright CLI · cleanexpoAuthenticated browser automation for Synthex — drive real Chrome to log in, screenshot, and audit dashboard/integration surfaces. Use for live visual verification, "audit the dashboard", "check what's connected", or closing the verification gate on /dashboard/* routes. Two backends: the Playwright MCP server (interactive, in-session tools) and the committed CLI scripts (scripts/browser/*.mjs, reliable + headless). RUNS WHERE THE BROWSER + NETWORK + AUTH EXIST — i.e. a local machine, not a network-restricted sandbox.
- ▌ Ship Loop Test · cleanexpoJest test suite child loop. Runs `npm test` (uses jest.worktree.cjs per package.json), records pass/fail counts and failing suite paths into ship-loop-state.json. Only fires if last ship-loop-build was green. Applies one recovery recipe (jest config / mock generation / worktree cleanup) on failure, retries once, escalates. Use standalone via /loop ship-loop-test or wired into the master orchestrator.
- ▌ Spec Generator · cleanexpo bundle"No implementation without specification" enforcement. Auto-generates specification documents before any feature or project work begins. Two templates: project-phase (10 sections) and feature (8 sections). Specs are written to `.claude/specs/`. Includes detection logic to intercept implementation tasks that lack a spec.
- ▌ Synthex Design · cleanexpo bundleThe Synthex marketing creative engine. Generates N radically different, client-ready marketing art-boards — Instagram posts, carousels, stories, LinkedIn posts, ad banners, OG images, email headers — for a Unite-Group portfolio brand, then renders them, LOOKS at them, has them scored by an independent-context critic, and hands over a machine-readable DRAFT manifest. Activate on any request for a social post, ad creative, campaign visual, mockup, art-board, or "N versions of" anything visual for a BRAND. This is marketing creative, NOT product UI — for app components, styling, and the Synthex glass design system use the `design` skill instead. All output is DRAFT; this skill never publishes.
- ▌ Database Prisma · cleanexpoSynthex database operations enforcer. NEVER use prisma db push for schema changes — use migrate diff + db execute. NEVER add non-nullable columns without defaults. NEVER write Prisma queries without organizationId scope. ALWAYS use backward-compatible migrations and validate with prisma validate first. Activate on ANY request to change schema, write a query, create a migration, add a model, or modify database operations.
- ▌ Local SEO Agent · cleanexpo bundleOrchestrates google-search-console, google-business-profile, competitive-local-strategy, and google-updates-sentinel skills into a unified local SEO strategy with monthly audit cadence. Use when running local SEO campaigns, onboarding new clients, or performing monthly audits.
- ▌ Nexus Viral Run · cleanexpoHuman-triggered runner for the nexus-viral 1→8 short-form pipeline. Composes brief → Gate A → copy → generate_video → poll → Gate B → derive_cuts as one gated agent session over the real studio/MCP tools. Draft-first spend; every gate aborts BEFORE any paid generation. NO publish primitive — releasing cuts is a separate human-gated route (WS4). Use when a human wants to take one viral idea from brief to inert, review-ready platform cuts in a single action.
- ▌ Project Scanner · cleanexpo bundleCodebase analysis, dependency auditing, and architecture mapping for the Synthex platform. Scans file structure, dependency health, TypeScript errors, unused exports, security vulnerabilities, and documentation gaps. Use when user says "scan project", "audit dependencies", "check codebase", "architecture map", "security scan", or "code health".
- ▌ Ship Loop Build · cleanexpoBuild + type-check + lint child loop for ship-loop-master. Runs `npm run type-check && npm run lint && npm run build`, records pass/fail per command into ship-loop-state.json, applies one recovery recipe on failure (from ship-loop-shared/recovery-recipes.md), retries once, escalates on second failure. Use standalone via /loop ship-loop-build for debugging or wired into the master orchestrator.
- ▌ Ship Loop Merge · cleanexpoMerge to main child loop. Default mode (auto_merge=false) HALTS at "ready for human review" — escalates to ship-loop-escalations.md and lets the master loop continue monitoring CI. Auto-merge mode (auto_merge=true) requires literal --enable-auto-merge flag at master-loop activation; runs `gh pr merge --squash --delete-branch` only when CI is green. Use standalone via /loop ship-loop-merge or wired into the master orchestrator.
- ▌ Ship Loop Smoke · cleanexpoFull system smoke child loop. Wraps scripts/overnight-smoke.mjs --iterations=1 to run the existing 4-layer rig (surface health + CSP hydration + API contract + fault injection) once per tick. Aggregates JSONL output into ship-loop-state.json. Lifts P0/P1 findings into ship-loop-escalations.md. "Until 100% green" = if any P0/P1 detected, sets state to red so master re-triggers next cycle. Use standalone via /loop ship-loop-smoke or wired into the master orchestrator.
- ▌ Ship Loop Watch · cleanexpoChrome MCP browser-watch child loop. Navigates synthex.social surfaces, captures console errors / CSP violations / 4xx-5xx network requests / hydration failures. Runs on a 15-min cadence via the master orchestrator. Classifies findings using the browser-debug skill mappings, applies recipe lookups for known patterns. Use standalone via /loop ship-loop-watch for production-side debugging or wired into the master orchestrator.
- ▌ Site Smoke Test · cleanexpoRuns a structured autonomous smoke test of synthex.social (or localhost:3000) covering all critical paths: landing page, auth, dashboard, API health, and key features. Produces a pass/fail matrix across 8 critical paths. Use before merging a PR, after a production deploy, when checking if the site is healthy, or when asked "is the site working?", "run a health check", "smoke test the app", "check synthex.social". Also use as part of Phase 6 E2E verification in the autonomous deployment pipeline.