proofbridge-liner

Use the belt CLI — run 250+ AI apps, manage knowledge, search skills, connect MCP servers

Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Audit websites for SEO, performance, security, technical, content, and 16 other issue categories with 249+ rules using the squirrelscan CLI. Returns LLM-optimized reports with health scores, broken links, meta tag analysis, and actionable recommendations. Use to discover and asses website or webapp issues and health.

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

PREREQUISITE TO ART OF CHOKE. Enforces that the entire CI pipeline runs start-to-finish before any push or deploy. No skipped phases, no soft failures, no 'works on my machine.' Before a single line ships, the full chain must execute and pass in a production-like environment.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples.

Use this skill when designing, auditing, or extending an agent ecosystem: agent roles, skills, MCP servers, tool boundaries, memory conventions, repo automation, handoff protocols, safety checks, and multi-agent workflows. Trigger when the user asks how agents should collaborate, what skills to add, how to wire MCP tools, or how to structure agent operating procedures.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

Use this skill when reviewing Ubuntu Pools UX, layout structure, product information architecture, dashboard hierarchy, trust/ledger/governance flows, or React/Next.js components related to Ubuntu Pools. Trigger when the user asks to review, audit, restructure, improve, or critique Ubuntu Pools screens, routes, navigation, dashboards, waitlist pages, trust components, ledger views, compliance surfaces, or community-savings user journeys.

Use this skill when a user asks to think deeply, ultrathink, rev a plan, pressure-test an implementation approach, de-risk a multi-step change, or turn a vague objective into an execution-ready engineering plan. Trigger before high-blast-radius edits, branch/rebase/push operations, architecture changes, security-sensitive work, deployment changes, and complex debugging sessions.

VVU architectural decision records and coding standards. Load when naming a new service or event, choosing between patterns, reviewing code for VVU conventions, or designing a new integration. This is 'What Would The Architecture Review Say' — the encoded standards Mino and the team have established across ProofBridge, SafeKrypte, Ubuntu Pools, SafeGrid, and Ekasi. Load it before naming anything, structuring any API, or choosing any technology pattern. Prevents the quality debt that compounds when each agent-generated PR introduces a different convention.

What Would The Compliance Gate Say. Load before any Tier-3 change touching ProofBridge Liner, SafeKrypte, Ubuntu Data Bus, GovernanceAnchor.sol, ED25519 VCT governance, CircuitBreaker, or HMAC webhooks. Encodes the 18 audit findings and 5 hard-failure release blockers from the ProofBridge compliance-fabric v2 audit. Functions as Lindiwe's behavioral quality reviewer — analogous to a QA engineer opening the product and walking real flows before a PR merges. Do not skip for changes that look small. The 30-commit main-branch incident started with a change that looked small.

VVU Specification-Driven Development workflow. Load for any Tier-2 or Tier-3 feature work, plan generation, or spec writing. Implements the SDD pattern that eliminates vibe-coding from VVU's core systems: plan before code, spec before plan, approve before build. Without this skill, agent-generated code arrives at review without compliance tracing, behavioral coverage, or architectural alignment — creating quality debt that compounds into shipping anxiety, brittle tests, and customer-found regressions. Load at the start of any non-trivial change. Generates INVESTIGATION.md, PLAN.md, and VALIDATION.md — the three files that make every change traceable from business intent to deployed code.