CleanExpo

Dispatch the eight operational roles against a task, each grounded in the vault before it reads any code, with a live view of what is running. Use for work that wants several independent lenses at once — map, plan, build, verify, review, security, CI, release…

Thin wrapper around the Pi-CEO Hour-1 provisioner. Given a client slug + email, invokes `swarm/inbox/provisioner.py` to spin up the full Linear project + Supabase portal_content + ContextBot Telegram intake bot + welcome email + Phill ping. Use when the user…

PM-Core — the first autonomous execution agent. Claims the highest-priority agent-ready ticket from the Unite-Group Linear board, clones the repo, implements the fix on a feature branch, runs CI, and opens a PR. Model: claude-sonnet-5 (senior agent tier).…

Full SEO toolkit for Claude Code, powered by the DataForSEO API. Replaces the data layer of an SEO agency: keyword research, competitor analysis, rank tracking, backlink audits, technical site crawls, content gap analysis, and client-ready PDF reports — all…

Use before any git push, pull-request creation or ready-for-review action, including autonomous loops and follow-up fixes.

Dictate a goal and ramble at it. Grounds in the project's North Star, structures the intent, researches, drafts a build-ready brief, then has Codex challenge it until it holds.

Use when fleet machines have stale/diverged skills or config ("update didn't reach the other computer"), when setting up a new machine, or when the estate-sync log shows CONFLICT/FAIL. Owns the automatic two-way propagation of the skills-library hub…

Run every gate CI's "Quality Checks" job runs, LOCALLY, before you push or open a PR — so a locally-green branch never opens UNSTABLE. Use before any git push / gh pr create in RestoreAssist, and whenever a PR shows mergeStateStatus UNSTABLE with a red…

Senior Email Marketing Specialist (15+ yr calibration). Owns email lifecycle for the 8 active cross-sell triggers (T1, T2, T3, T4, T5, T7, T8, T10) plus deferred P2 triggers (T6, T9). Enforces foundation rules at every draft: Q2.5.3 cadence map, frequency…

Multi-brand branding enforcer for every client-facing or branded output — invoices, reports, proposals, documents, PDFs, dashboards, canvases, decks, emails, letterheads, web pages — even when the request never says the word "brand". Resolves WHICH brand…

Synthex design system enforcer. NEVER use Inter as a heading font, purple (#8B5CF6) gradients on white, or generic glassmorphism without Synthex tokens. ALWAYS use Space Grotesk headings, #FF6B35 brand orange, #0f172a slate background, and the Synthex glass…

Synthex Capability Uplift master reference. Contains the authoritative anti-patterns and replacement standards that override LLM defaults across ALL Synthex skills. ALWAYS read the relevant reference file before producing UI, content, chart, or code output.…

Synthex UI validation agent. NEVER run generic Lighthouse audits without grounding findings in Synthex's dark glassmorphic interface. NEVER reference pnpm. ALWAYS check backdrop-filter fallbacks, focus rings against the dark background (#0f172a), and Radix UI…

Authenticated 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…

Synthex campaign content enforcer. NEVER open posts with "Excited to announce", use "leverage", "game-changing", or "revolutionary", produce platform-agnostic copy, or generate content that scores below 80. ALWAYS write platform-distinct hooks, use specific…

Produce one or many consistent, on-brand faceless marketing videos end-to-end from a topic — script → ElevenLabs voiceover (with timestamps) → one styled illustration per beat via the grounded pipeline (generateImage(), auto-detect + auto-LoRA) → ffmpeg…

The authoritative environment-variable registry for the Unite-Group Nexus. Use whenever adding, reading, renaming, or debugging an env var or secret — new integration config, a `process.env.X` read, an auth/OAuth wiring, a cron secret, a "which variable holds…

Create, verify, and promote Supabase schema changes via database branches. Every schema change/migration must be validated on a Supabase database branch before prod (see CLAUDE.md line 44).

Verify production Supabase schema before shipping code that touches it. Use BEFORE writing or reviewing ANY code that reads or writes a Supabase table in the Nexus — new queries, inserts, updates, CHECK-constrained values, RLS-dependent reads, cron data…

Brand context for the ITR Button tax app (ato-ai.app) — write on-voice, factually-grounded, compliance-safe content. Fires when producing content for this AI tax-return-intake tool (org slug `ato` in credential-triage event routing). Loads brand, voice, key…

Brand context for CARSI (carsi.com.au) — write on-voice, factually-grounded content for the online restoration/cleaning training LMS. Fires when producing CARSI course, marketing, or social copy (org slug `carsi` in credential-triage event routing). Loads…

Brand context for CCW — Carpet Cleaners Warehouse (ccw-crm-web.vercel.app storefront ccwonline.com.au) — write on-voice, factually-grounded content for this trade-supply CLIENT of Unite-Group. Fires when producing CCW marketing, case-study, or CRM/ERP content…

Brand context for Disaster Recovery (disasterrecovery.com.au) — write on-voice, factually-grounded content for the consumer-facing disaster-restoration category hub. Fires when producing Disaster Recovery marketing, social, or category-authority copy (org…

Brand context for NRPG — National Restoration Practitioners Group (nrpg.business) — write on-voice, factually-grounded content for the contractor/industry-association platform. Fires when producing NRPG marketing, membership, or onboarding copy (org slug…

Route complex requests to the right specialist agent or chain of agents. This skill acts as the central brain of an agent swarm — it analyses what the user needs, determines which specialist domain(s) are required, and coordinates parallel or sequential agent…

>-

Hybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps

">"

Act 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",…

>-

Override generic LLM code output patterns. Replaces generic variable names, over-commented code, and placeholder patterns with domain-specific naming, clean architecture, and production-ready structure.

Slop-prevention middleware. Run before any design or code task to gather sources, then produce a Plan Mode block before touching any file. Eliminates hardcoded colours and generic components caused by agents assuming design decisions.

Route complex requests to the right specialist agent or chain of agents. This skill acts as the central brain of an agent swarm — it analyses what the user needs, determines which specialist domain(s) are required, and coordinates parallel or sequential agent…

>-

>-

>-

>-

>-

>-

>-

Validate Australian phone numbers, addresses, postcodes, ABN/ACN numbers, and state/territory references. Use when reviewing any content with Australian business data.

Domain 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.

Verify factual accuracy of all claims, data, and information across the platform. Use when reviewing content, service descriptions, or business information for correctness.

Validate IICRC standard references, certification claims, and technical terminology. Use when working on service pages, guides, or content that references IICRC standards.

TypeScript 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.

Typed 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.

Hybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps

Claude Chrome extension tools for personal browser automation in the user's actual browser. Use for logged-in sessions, form filling, and interactive tasks.

Catch the "same data lives in two differently-keyed tables, two features read different ones, they silently disagree" failure class. Use whenever two models hold overlapping fields, a reader picks a pricing/config/settings store, or two surfaces (e.g. Margot…

Catch the "importer reads a JSON key the external API never returns → silently imports zero rows, mocked tests stay green" failure class BEFORE it ships. Use whenever you write or change code that parses a third-party API response (Ascora, Xero, any…

Catch "content that should never have entered the shared vector corpus" BEFORE ingest — tenant-specific or product-specific dollar figures (a global rate card, cross-product training $ rates) that a no-tier-weighting retriever can surface into the wrong…

Use when producing, scripting, or shipping the RestoreAssist onboarding + walkthrough video SERIES as a batch (not one clip) — the setup-wizard / getting-started tutorial / onboarding-welcome videos need scripts written, narrated, rendered, captioned, and…

Catch the "green locally, red in CI" failure class BEFORE pushing. Use whenever you are about to claim tests pass, before a PR, or when CI "Quality Checks" fails on a test that passed (or was skipped) on your machine — especially anything under lib/setup,…

Capture browser screenshots for visual design verification (DESIGN.md Verification Gate). Use when a UI change needs an actual rendered screenshot — de-gradient passes, layout/spacing checks, light/dark comparison — rather than a static class diff. Covers the…

Use at the start of every non-trivial user request and at any feature-completion / context-45%+ checkpoint. Forces a "Translation Blueprint" interception before code, enforces Service Layer separation, runs an automatic structural audit on completed features,…

Use when designing or refactoring an API surface where the route handler / Convex action / framework endpoint has accumulated runtime mechanics (provisioning, credential reads, validation, readiness checks, restart/teardown helpers, integration fan-out).…

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled…

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a…

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a…

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Use whenever creating, editing, refreshing, or reviewing ANY CARSI course, module, lesson, quiz, course trailer, or course marketing copy. Enforces the non-negotiable Australian-production standard (Australian English, 230V/10A power, metric units,…