Loading
Reusable AI skills, evaluations and playbooks drawn from real client work - each governed, measured and made to survive contact with a live business.
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.
Given a URL or page description, recommends the optimal Schema.org types, properties, and outputs valid JSON-LD with a unified @graph structure. Analyses the page's purpose, content, and business context to select the most specific applicable Schema.org types, populates required and recommended properties, establishes @id references to site-wide entities, and produces copy-paste-ready JSON-LD that passes both Schema Markup Validator and Google Rich Results Test. Handles all common page types: homepage, about, services, products, blog posts, events, FAQs, contact, location pages, and portfolio/case study pages.
Constructs a knowledge graph specification from business entities, relationships, and attributes. Produces node and edge definitions suitable for graph database implementation (Neo4j, Dgraph), JSON-LD @graph representation, or application-level entity stores (Supabase/PostgreSQL with JSONB). Goes beyond page-level Schema.org markup to build a comprehensive entity graph that captures the full semantic model of a business domain — including entities, their properties, typed relationships, hierarchies, and connections to the broader web of data. Designed for businesses building content knowledge graphs, product graphs, or domain-specific entity stores for SEO, AI agent consumption, and internal data organisation.
Takes a business or domain description and outputs a complete entity-relationship model with Schema.org type mappings, consistent @id structures, and sameAs connections to authoritative external profiles. Produces both a human-readable entity-relationship diagram and a machine-readable JSON-LD @graph specification. Designed for businesses building their structured data foundation — connecting Organisation, People, Services, Products, Locations, Content, and Events into a coherent knowledge graph that search engines, LLMs, and AI agents can traverse. Handles multi-location businesses, service-product hybrids, and complex organisational structures.
Takes survey responses, customer reviews, NPS data, CSAT scores, support ticket feedback, or any qualitative/quantitative feedback data and produces an actionable insights report. Performs sentiment analysis, theme extraction, priority scoring, and segment comparison. Transforms unstructured feedback into structured findings with specific business recommendations. Handles both quantitative data (ratings, scores, scales) and qualitative data (open-text responses, verbatim comments). Designed for businesses analysing customer feedback, employee surveys, client satisfaction data, product reviews, and user research findings.
Designs ETL/ELT pipeline architectures given source systems, transformation requirements, and destination databases. Takes inventory of data sources, volume, freshness requirements, and transformation logic as input, then produces a complete architecture document with data flow diagrams, transformation specifications, orchestration design, error handling strategy, monitoring configuration, and implementation code. Targets Supabase (PostgreSQL), BigQuery, and common small-business data stacks. Designed for solo developers and small teams who need reliable pipelines — not enterprise data engineering, but production-grade automation that runs unattended.
Creates rule-based and statistical anomaly detection systems for business metrics — revenue drops, traffic spikes, conversion rate changes, churn increases, cost overruns, and operational irregularities. Takes metric definitions and historical context as input, then produces detection rules with thresholds, SQL queries for automated checking, alerting configurations, and investigation playbooks for when anomalies trigger. Designed for businesses using Supabase/PostgreSQL, Google Analytics, and standard business tools — not enterprise observability platforms, but practical detection that runs on a cron job and sends a Slack message when something's off.
Helps businesses design and implement multi-touch attribution models for marketing spend. Takes channel data, touchpoint information, and conversion definitions as input, then outputs a model design with weighting logic, implementation steps, SQL/code for calculation, and a decision framework for interpreting results. Covers rule-based models (first-touch, last-touch, linear, time-decay, position-based, W-shaped) and provides guidance on when to use data-driven approaches. Designed for small-to-mid businesses that need practical attribution — not enterprise-grade marketing mix modelling, but frameworks that work with Google Analytics, CRM data, UTM tracking, and real-world messy attribution data.
Designs cohort analysis frameworks from user/customer data. Takes a business context and data schema as input, then outputs ready-to-run SQL (PostgreSQL/Supabase by default), visualisation specifications, and interpretation guidance. Supports time-based cohorts (signup month, first purchase), behaviour-based cohorts (feature usage, plan tier), and size-based cohorts (revenue bracket, order frequency). Covers retention cohorts, revenue cohorts, cumulative LTV cohorts, and churn cohorts. Produces the full analytical pipeline: cohort definition → activity mapping → period calculation → aggregation → visualisation spec → interpretation framework.
Takes a dataset description — schema, sample data, data dictionary, or plain-language explanation — and produces a comprehensive data quality report. Assesses completeness, validity, consistency, uniqueness, timeliness, and accuracy across all fields. Identifies missing values with missingness pattern classification (MCAR/MAR/MNAR), distribution anomalies, outliers (statistical and domain-based), type mismatches, referential integrity issues, and structural problems. Produces prioritised cleaning recommendations with specific techniques, code snippets (Python/SQL), and risk assessment for each issue. Designed for analysts, developers, and business users working with business data, customer data, transactional data, and operational datasets — not academic or scientific research datasets.
Generates polished stakeholder communications — investor updates, board reports, advisory briefs, client status reports, team updates, and partner communications — from raw business metrics and unstructured notes. Adapts structure, tone, depth, and metric selection for the specific audience type. Transforms messy data dumps and bullet points into clear, narrative-driven briefs that build trust, demonstrate competence, and drive the specific outcome the sender needs (continued investment, board approval, client confidence, team alignment). Handles the full spectrum from a solo founder updating angel investors to an agency sending quarterly client reports.
Builds a complete KPI framework for a given business type and stage. Selects the right mix of leading and lagging indicators across financial, operational, client, and team health categories. Defines each KPI with measurement formula, data source, frequency, ownership, target-setting methodology, and alert thresholds. Produces a dashboard specification showing exactly what to build, where to pull data from, and how to structure review cadences. Designed for service businesses, agencies, consultancies, SaaS companies, and hybrids — not generic KPI lists but frameworks calibrated to how the business actually operates and what stage it's at.
Takes workflow descriptions from service businesses, agencies, consultancies, and small software companies and systematically identifies operational bottlenecks, single points of failure, capacity constraints, and automation opportunities. Applies Theory of Constraints principles adapted for knowledge work — where the "factory floor" is calendars, inboxes, project boards, and human expertise. Maps workflows stage by stage, scores each stage on throughput, wait time, dependency risk, and failure modes, then produces a prioritised action plan with estimated impact and implementation effort. Designed for businesses where the constraint is usually a person, a process, or an approval — not a machine.
Evaluates a business's current pricing against competitor positioning, cost structure, value delivery, and willingness-to-pay signals. Analyses pricing model fit (hourly, project, retainer, subscription, usage-based, tiered, value-based), identifies pricing power indicators and leakage points, and recommends specific model changes with revenue impact modelling. Covers service businesses, SaaS, and hybrids. Incorporates frameworks including Van Westendorp price sensitivity logic, competitive positioning maps, and margin-based floor/ceiling analysis to produce actionable pricing recommendations — not just theory.
Takes business inputs — revenue model, cost structure, acquisition costs, lifetime value drivers, churn, margins, and utilisation — and produces a complete unit economics model with scenario analysis. Handles service businesses (agencies, consultancies), SaaS/product businesses, and hybrids. Calculates core metrics (CAC, LTV, LTV:CAC ratio, payback period, contribution margin, effective hourly rate, utilisation, revenue per head), flags unsustainable metrics against industry benchmarks, and runs best/base/worst scenario models to stress-test the business. Outputs a financial narrative that translates raw numbers into strategic decisions.
Maps current and potential revenue channels for service-based businesses — agencies, consultancies, freelancers, and small software companies. Scores each channel across six dimensions (revenue potential, implementation effort, scalability, time to revenue, margin potential, strategic fit) using weighted composite scoring that adjusts to business stage and growth goals. Analyses funnel health across an AAARRR framework adapted for services (Awareness → Acquisition → Activation → Revenue → Retention → Referral), identifies systemic gaps, concentration risks, and margin issues, then produces a prioritised channel matrix with a 90-day action roadmap.