Skill rating

Evaluate performance fairly when output is AI-assisted — what still measures the human, what now measures the tooling, and how to run the review conversation. Use when reviewing someone whose work is

Verify work actually meets its brief BEFORE declaring it done — a structured self-review pass that catches the gaps, unmet requirements, and untested claims that 'looks finished' hides. Use before han

Score a subcontractor's performance across schedule reliability, quality, safety, paperwork, and change-order behaviour with weighted anchors. Use when asked to evaluate a sub, build a subcontractor s

Review a vendor/SaaS contract against a practical checklist before you sign. Use when asked to review a vendor contract, check a SaaS/MSA/subscription agreement, flag risky terms, or prepare negotiati

Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut toke

Decode a care-home contract before a parent moves in — the fee-escalation clause with no cap, the needs-can-no-longer-be-met eviction trigger, the guarantor line that quietly makes you personally liab

Decode a mortgage Closing Disclosure line by line — which fees are real, which are shoppable or junk, and what changed since the Loan Estimate. Use when asked to decode my closing disclosure, review m

Decode a timeshare contract before signing — the lifetime cost math, the perpetuity and fee-escalation clauses, the rescission window, and the honest resale reality. Use when asked to review this time

Audit a landing page or funnel step and produce a prioritised CRO test plan. Use when asked to improve conversion rate, audit a landing/signup/checkout page, reduce funnel drop-off, or plan A/B tests

Simulate enterprise procurement and security review of your product before your first big deal meets it for real — the questionnaire, the gaps, the deal-slowing findings. Use when asked to prep for en

Find out how a dashboard, KPI report, or metrics slide is lying to you — before you repeat its story in a bigger room. Use when numbers feel too tidy, a narrative rests on one chart, or you inherited

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonom

Parse error logs, stack traces, and crash reports into a structured root cause diagnosis. Use when an application is throwing exceptions, crashing, or producing unexpected errors and you need to under

Run a self-audit of a food establishment before the health inspector arrives, focused on the violations that actually close kitchens. Use when asked to prep for a health inspection, do a food-safety s

Decode a severance agreement before you sign it — what you're giving up, what's negotiable, and the deadlines that decide your leverage. Use when asked to decode my severance, is this severance offer

Review a product/codebase for internationalization readiness before you localize. Use when asked if a product is ready to localize, to review i18n readiness, find hard-coded strings/locale bugs, or pr

Analyse competitor moves and translate them into strategic implications for your product roadmap. Use when a competitor announces a new feature, pricing change, partnership, or strategic shift, or whe

Structure a literature review that argues, not lists — thematic synthesis from your sources with the debate mapped and the gap identified. Use when asked to write or structure a literature review, org

Interrogate a demand forecast before the business commits supply and inventory to it. Use when asked to review a demand plan, challenge a forecast, check forecast accuracy, decompose baseline vs uplif

Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready,

Assess and reduce the risk of exposing a confidential journalistic source. Use when a reporter is working with a confidential source, a whistleblower, or sensitive leaked material and needs to protect

Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end. Use when implementing multi-part features, refactor

Get a landlord to actually fix things — the repair request that creates a record, the escalation ladder from reminder to habitability leverage, and the jurisdiction-flagged map of tenant remedies with

Simulate the due-diligence call where an acquirer's or investor's analyst takes your metrics apart — the questions behind the spreadsheet, the moment a number wobbles, and a debrief on which answers c

Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or C

Run an NPI phase-gate review for EVT, DVT, or PVT — exit criteria per phase, open-issue triage, yield readout, waiver discipline, and a go/no-go call. Use when asked to run a gate review, decide EVT e

Assess an injection-mold or production tooling decision before cutting steel — soft vs hard tooling tradeoff, tool life vs forecast, cavitation math, T1 sample timeline, cost of design changes after t

Use AI personas for early-stage research signal — with hard guardrails on what synthetic methods can and cannot validate. Use when asked to run synthetic user testing, simulate user reactions with AI

Decode a counteroffer after you resign — what the raise, promotion promise, or title bump really signals, the statistics-informed risks of staying, and a clear-eyed decision framework. Use when asked

Simulate the exact customer who will quietly cancel in month 4 — their internal monologue through the lifecycle and the honest exit interview they never gave you. Use when asked why do customers reall

Sanity-check a greenhouse gas inventory before it goes into a report or gets audited. Use when asked to review a carbon footprint, check a GHG inventory, validate scope 1/2/3 numbers, explain a year-o

Assess physical and transition climate risk for a site, product, or portfolio with scenario-based structure. Use when asked to run a climate risk assessment, evaluate physical or transition risk, prep

Audit your own marketing and report claims for greenwashing risk before a regulator, journalist, or competitor does. Use when asked to review sustainability claims, check marketing copy for greenwash,

Resolve a document's forty review comments systematically — triage by type (accept, push back, conflict, out-of-scope), batch the mechanical fixes, draft the disagreement replies, and reconcile review

Map an organisation's risks against its insurance policy portfolio to find what's uncovered, underinsured, or double-covered. Use when asked to run a coverage gap analysis, review an insurance program

Run a pre-renewal review of an insurance programme: scan coverage gaps against current operations, test limit adequacy against inflation and exposure growth, read the claims experience into pricing ex

Design a voice AI agent for phone or in-app conversations — call flows, interruption handling, escalation to humans, and the metrics that catch a bad voice experience. Use when asked to design a voice

Analyse a construction bid or tender package for scope gaps, risk-shifting exclusions, unit-rate red flags, and front-loading in the schedule of values. Use when asked to review a bid, level bids, che

Produce a regulatory impact analysis (RIA) weighing the costs, benefits, and alternatives of a proposed rule. Use when asked to assess a regulation's impact, do a cost-benefit analysis of a policy, ju

Build a weighted RFP evaluation matrix and defensible award recommendation. Use when asked to score RFP responses, compare vendor bids, build a supplier evaluation matrix, run a sourcing event scoreca

Turn field returns into a structured failure-analysis report — RMA triage taxonomy (NTF vs real failures), Pareto by verified failure mode, 8D-style containment→root-cause→corrective-action structure,

Decompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result integration that catches contradictions. Use when work can genuinely parall

Simulate a consular visa interview — the 90-second assessment, the questions behind the questions, and a debrief on which answers helped and hurt. Use when asked prep me for my visa interview, simulat

Run a quarterly loan covenant compliance review: covenant table with required vs actual vs headroom, trend and trajectory-to-breach analysis, waiver and amendment options with pricing implications, ea

Draft an honest, audit-ready ESG disclosure section in a CSRD/ESRS-flavored structure, adaptable to other frameworks. Use when asked to write a sustainability report section, draft an ESRS or CSRD dis

Plan a full-funnel marketing strategy from awareness to retention. Use when asked to build a marketing funnel, map the customer journey to tactics, plan demand generation, or diagnose where a funnel l

Plan a new manager's first 90 days — first-time or new-to-team — as listen/decide/move phases: the 1:1 listening tour with real questions, the early-judgment traps, the quick-wins filter, and the 30/6

Set inventory policy for an item class: segmentation, safety stock, and replenishment method. Use when asked to set safety stock levels, segment items by ABC/XYZ, choose reorder points vs min-max, def

Prepare an S&OP cycle readout that surfaces the demand-supply gaps and forces the three decisions the meeting must make. Use when asked to prep an S&OP meeting, build the executive S&OP deck, summariz

Design an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI agents. Use when asked to spec an MCP server, expose a product to agents, d