Loading
Reusable AI patterns, evaluations and playbooks drawn from real client work, plus the latest in AI. Each artefact is governed, measured and made to survive contact with a live business.
The frontier models came off the leash this week: GPT-5.6 reached the public and Grok 4.5 landed days later, both cheaper and more capable. The first fully autonomous AI ransomware also appeared in the wild, and the UN opened its first global forum on governing the technology. Here's your plain-English roundup and why it matters for your business.
The centre of gravity in AI shifted this week. Anthropic launched a cheaper, more agentic Claude Sonnet 5 and quietly overtook OpenAI on revenue, while OpenAI offered Washington a 5% stake and Australia's public service raced to appoint AI officers. Here's your plain-English roundup of what happened and why it matters for your business.
The AI race went global this week: China trained a 1.6-trillion-parameter model entirely on home-grown chips, OpenAI unveiled its GPT-5.6 family under government supervision, and Europe eased its AI Act. Here's your plain-English roundup of what happened and why it matters for your business.
Reusable Claude Code skills and plugins that package a workflow end to end.
Generates complete business plans in three formats — Lean Canvas (1-page), Lean Plan (3–5 pages), and Traditional Business Plan (15–30 pages) — based on business context, goals, and intended audience. Takes business description, market positioning, revenue model, team, and financial inputs, then produces a structured document with executive summary, market analysis, competitive positioning, revenue model, operations plan, financial projections, risk assessment, and milestones. Adapts depth and emphasis to the plan's purpose: internal alignment, investor pitch, bank loan application, grant submission, or strategic planning. Calibrated for service businesses, agencies, consultancies, SaaS companies, and service-product hybrids — not generic templates, but plans that reflect how these businesses actually operate.
Designs complete data models for business applications — tables, relationships, Row Level Security policies, indexes, constraints, and triggers. Outputs Supabase-compatible PostgreSQL SQL migrations ready for deployment. Takes a business domain description and application requirements as input, then produces a normalised relational schema, an entity-relationship diagram, migration SQL with proper sequencing, RLS policies for multi-tenant and role-based access, performance indexes, and seed data specifications. Designed for Next.js + Supabase applications where the database is the backbone of the product.
Estimates Total Addressable Market (TAM), Serviceable Addressable Market (SAM), and Serviceable Obtainable Market (SOM) using both top-down and bottom-up methods. Takes industry, geography, segment, and pricing inputs, then produces a market sizing report with explicit assumptions, sensitivity analysis, and confidence ranges. Designed for businesses preparing investor pitches, evaluating new service lines, entering new markets, or validating business models. Handles both product markets (units × price) and service markets (clients × contract value), with specific calibration for Australian market sizes.
Audits existing structured data on a website and produces a migration plan to a new schema version, unified @graph architecture, expanded entity coverage, or corrected implementation. Takes current markup (via URL, pasted JSON-LD, or description) and target state as inputs. Produces a gap analysis (what's there, what's wrong, what's missing), a before/after comparison for each page template, a phased migration plan with rollback strategy, and validation checkpoints. Handles common migration scenarios: scattered script blocks → unified @graph, isolated page markup → connected entity graph, outdated types → current best practices, and plugin-generated markup → custom implementation.
Creates hierarchical taxonomy structures for a given industry — product categories, service types, organisational structures, topical hierarchies, and classification systems. Maps taxonomy nodes to Schema.org types and properties wherever possible, and outputs the taxonomy in multiple formats: human-readable tree, JSON-LD ItemList structures, database schema for implementation, and SKOS-aligned vocabulary definition. Designed for businesses building structured navigation, faceted search, content organisation, product catalogues, and service directories where consistent categorisation is essential for both user experience and machine comprehension.
Resolves entity ambiguity for structured data implementations. When the same entity appears across multiple sources, pages, or systems with different names, identifiers, or attributes, this skill determines whether entities are the same or different, recommends canonical identifiers, and produces sameAs link mappings. Handles Organisation disambiguation (legal name vs trading name vs brand), Person disambiguation (same name different person, same person different representation), Product/Service disambiguation, and Location disambiguation. Produces an entity resolution report with canonical records, merge decisions, and a sameAs link map for structured data implementation.
Our skills ship as official Claude Code plugins in the official-business-plugins marketplace. Add it directly from inside Claude Code, then install the plugins you want.