varunk130

Performs rigorous Software as a Service (SaaS) cohort analysis: retention curves, Lifetime Value (LTV), Customer Acquisition Cost (CAC) payback, Net Revenue Retention (NRR), Gross Revenue Retention (GRR), and expansion versus churn decomposition with dollar-weighted and logo-weighted views. Use when diagnosing retention problems, forecasting Annual Recurring Revenue (ARR), evaluating pricing changes, segmenting customer health, validating product-market fit, or preparing board and investor key-performance-indicator reports.

SaaS financial modeling engine that generates unit economics models, feature ROI calculators, pricing scenario analyses, TAM/SAM/SOM sizing, build-vs-buy comparisons, and revenue projections from natural language inputs. Use when building business cases, calculating LTV/CAC/payback, modeling pricing changes, estimating feature revenue impact, running sensitivity analyses, or preparing financial justifications for product investments. Produces actual calculations with explicit assumptions and sensitivity ranges.

Models cash burn, runway, and scenario-based cash flow with explicit triggers, default-alive versus default-dead diagnosis, and a 13-week rolling forecast. Use when planning a fundraise, deciding on layoffs, evaluating hiring plans, modeling a downturn, presenting cash position to the board, or pressure-testing a Chief Financial Officer (CFO) operating plan.

Ranks competing investments using Net Present Value (NPV), Internal Rate of Return (IRR), payback period, Profitability Index (PI), and strategic option value - then produces a portfolio-level recommendation. Use when evaluating capital expenditure requests, comparing Mergers and Acquisitions (M&A) targets, sizing Research and Development (R&D) bets, prioritizing engineering investments, sun-setting initiatives, or preparing a board capital allocation memo.

Builds a transparent Discounted Cash Flow (DCF) valuation with a 5-10 year forecast, terminal value, Weighted Average Cost of Capital (WACC) derivation, sensitivity tables, and a football-field summary. Use when valuing a company, business unit, acquisition target, or capital project; pressure-testing an investment thesis; preparing a board valuation memo; or stress-testing assumptions against precedent transactions and trading comparables.

Performs structured fundamental analysis of annual reports (Form 10-K, Form 10-Q): ratio analysis, quality of earnings, working-capital efficiency, segment decomposition, accounting red flags, and Management's Discussion and Analysis (MD&A) parsing. Use when underwriting an investment, evaluating a competitor, preparing for an earnings call, building peer comparables, or screening for accounting risk.

Models multi-round competitive interactions: who reacts, how fast, with what move, and what payoff outcome - using reaction functions, commitment value, and signaling theory. Use when planning a pricing change, market entry, product launch, capacity addition, or any move where competitor reaction will determine whether the move pays off.

Designs auctions, matching mechanisms, pricing schemes, and incentive structures using mechanism-design principles - Incentive Compatibility (IC), Individual Rationality (IR), revenue equivalence, and budget balance. Use when designing a marketplace pricing model, a referral program, an internal resource allocation, a Request for Proposal (RFP) or procurement process, an auction format, or any allocation rule where participants act strategically.

Customer analytics framework - cohort retention, lifecycle funnels, engagement scoring, segmentation, and behavioral diagnostics for product and CS teams. Use when: customer analytics, cohort analysis, retention curve, engagement score, customer segmentation, behavioral analysis, lifecycle funnel, RFM, activation diagnostics, usage analysis.

Account-Based Marketing playbook builder - tiered account list (1:1, 1:few, 1:many), buying-group mapping, coordinated multi-channel plays per account, and pipeline acceleration plays for in-cycle accounts. Use when: ABM playbook, account-based marketing, target account list, tiered accounts, 1:1 marketing, buying group, named-account strategy, ABM plays, pipeline acceleration, in-cycle account acceleration.

On-demand sales battlecards for live competitive deals - positioning matrix, top objections with responses, trap questions, proof points, and a "do not say" list. Use when: competitor surfaced in deal, sales battlecard, competitive enablement, deal-specific battlecard, objection handling, competitive trap questions, why we win against, why we lose to, displacement playbook.

Customer advocacy program design - advocate identification, reference orchestration, case study pipeline, community amplification, and influence-to-revenue attribution. Use when: customer advocacy, customer reference program, case study program, advocate identification, customer marketing, peer review acceleration, G2 / Gartner Peer Insights, customer-led growth, reference architecture.

Customer Success operating system - segmented coverage model, health scoring, risk playbooks, value reviews, and expansion motions tied to net revenue retention. Use when: customer success strategy, CS operating model, health score, risk playbook, EBR / QBR design, churn prevention, net retention, NRR, GRR, success plan, value realization, customer journey post-sale.

Lead nurture orchestration - multi-track nurture design by intent stage, scoring, behavioral triggers, MQL→SQL handoff, and revival of cold leads. Use when: lead nurture, drip campaign, nurture track, lead scoring, MQL to SQL, lifecycle marketing, nurture sequence, behavioral trigger, lead revival, MQL handoff.

Customer loyalty and lifecycle orchestration - tiered loyalty design, lifecycle journey programs, milestone triggers, and retention economics for B2B and B2C. Use when: loyalty program, customer lifecycle program, tiered loyalty, milestone marketing, retention program design, lifecycle journey, loyalty economics, member tiers, retention motion.

Referral program design - referrer / referee incentive structure, viral mechanics, fraud and abuse controls, attribution, and channel placement. Use when: referral program, refer a friend, viral loop design, K-factor, advocacy referrals, partner referrals, customer referral incentives, referral attribution, viral coefficient.

WCAG 2.2 Level AA accessibility audit for AI product surfaces - color contrast, focus order, ARIA usage, keyboard navigation, motion/animation, reduced-motion respect, alt text, and form label association. Use when: accessibility audit, a11y review, WCAG audit, screen reader compliance, keyboard-only navigation, color contrast check, focus management, ARIA review, accessible AI UX.

Design user experiences for autonomous AI agents that act on behalf of users - control panels, consent flows, action previews, audit trails, and undo mechanisms. Use when: agentic AI, autonomous agents, AI autonomy controls, agent UX, AI actions, computer use, agent consent, agent audit trail.

Design conversational AI interfaces that feel natural, recover from failures gracefully, and build user trust through dialogue. Use when: chatbot UX, conversational UI, dialogue design, AI assistant interface, chat flow, turn-taking, AI persona voice, multi-turn context.

Design graceful failure experiences for AI products - hallucinations, uncertainty, wrong outputs, and edge cases. Use when: AI hallucination UX, error handling for AI, uncertainty design, graceful degradation, AI failure recovery, confidence thresholds, safe fallbacks.

Design feedback mechanisms that help AI systems learn from users - thumbs up/down, preference ranking, corrections, and human-in-the-loop escalation. Use when: RLHF UX, user feedback for AI, thumbs up down design, AI correction flow, human in the loop, feedback signal design, AI improvement loops.

Map human-AI interaction journeys - trust arcs, capability discovery paths, autonomy progression, and AI-specific touchpoints. Use when: AI user journey, human-AI interaction mapping, trust arc mapping, AI capability discovery, AI adoption journey, AI experience map.

Design how AI presents results across text, code, images, charts, and mixed media - response formatting, output hierarchy, and cross-modal transitions. Use when: AI output design, response formatting, AI results display, multimodal output, AI-generated content presentation, code output UX, AI visualization.

Design onboarding experiences that help users build accurate mental models of AI capabilities, set expectations, and discover features progressively. Use when: AI onboarding, progressive disclosure for AI, capability communication, AI mental models, expectation setting, AI feature discovery, first-time AI user experience.

Adds cost (input + output tokens × model price) and latency (p50, p95) to eval results, plots model options on a Pareto frontier, and produces a quality-per-dollar composite score so production model selection is grounded in trade-offs, not just quality. Use when: model comparison, cost-aware evals, latency budget, quality-per-dollar, Pareto frontier, model selection, eval economics, picking a model for production.

Generates eval test cases for AI agents from an eval suite plan (output of /eval-suite-planner) or a plain-English agent description. Supports both single-response and conversation (multi-turn) evaluation modes. Outputs a test set table, a CSV file in the Copilot Studio import format (single-response only - used here as the primary worked example; trivially adaptable to any harness that accepts tabular test cases), and a docx report for human review.

Analyzes AI agent evaluation results - primarily from Copilot Studio (the worked example here, via its CSV export) but also from custom harnesses or any evaluator that produces per-case pass/fail rows - using Microsoft's Triage & Improvement Playbook. Returns a SHIP / ITERATE / BLOCK verdict with root cause classification, diagnostic triage, prioritized remediation, and pattern analysis.

Produces a concrete eval suite plan for AI agents - grounded in Microsoft's Eval Scenario Library and MS Learn agent evaluation guidance (Copilot Studio is the primary worked example, but the plan is platform-agnostic and adapts to any agent harness). Outputs scenario types, evaluation methods, quality signals, thresholds, and priority order - before any test cases are generated or evals are run.

Use this skill when AI agent evaluations have come back and the user needs to interpret scores, diagnose root causes of underperforming test cases, find remediation steps, or analyze patterns to improve their agent. Works against any agent platform - Copilot Studio is the primary worked example here, but the triage framework applies equally to custom harnesses, LangChain/LangGraph, AutoGen, Semantic Kernel, OpenAI Assistants, and other agent runtimes. Always use this skill when the user mentions: "eval failed", "why did this fail", "triage", "diagnose failure", "low pass rate", "fix evaluation results", "not passing", "failing test cases", "evaluation results", "improve my eval scores", or any situation where eval scores need interpretation and action.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Evaluation pattern for agents that call tools / functions - measures tool selection accuracy, argument correctness, recovery from tool errors, and avoidance of unnecessary tool calls. Pairs with eval-suite-planner. Use when: tool-use eval, function-calling eval, agent tool selection, tool invocation accuracy, tool argument validation, tool error recovery, agent tools, function-calling agent, MCP eval.

Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.

Surfaces the assumptions a product or strategy depends on, classifies them by criticality and evidence quality, and produces a prioritized test plan. Use when: assumption mapping, identify assumptions, what could go wrong, leap-of-faith assumptions, riskiest assumption test, RAT, assumption inventory, validate before building.

Structured competitive teardown for product discovery - surface the 4-6 dimensions buyers actually weigh, score every competitor on each, and identify exploitable gaps. Use when: competitive analysis, competitor teardown, market positioning, where do we win, where do we lose, competitive gap analysis, competitor audit.

Triages a backlog of raw customer feedback into a ranked list of opportunities scored on reach, severity, strategic fit, and confidence. Outputs a prioritized list with explicit "do not act" callouts for vocal-minority signals. Use when: triage feedback, prioritize feature requests, customer feedback backlog, what should we build next, opportunity scoring, RICE feedback, feedback synthesis.

Identifies a candidate North Star Metric (NSM) for a product - the single metric that captures the value the product delivers to its customers and predicts long-term business growth. Tests candidates against five criteria and surfaces input metrics that move it. Use when: north star metric, NSM, single metric that matters, primary metric, growth metric, value-capture metric, what should we measure.

Deep contract review - extract clauses, map obligations, identify defined terms and gaps. Use when: review contract, extract clauses, obligation mapping, contract terms, payment terms, IP provisions, termination clause, indemnification.

Surface relevant case law, statutes, and regulatory frameworks for legal questions. Use when: find case law, legal precedent, statutory reference, regulatory framework, GDPR requirements, CCPA compliance, employment law, contract law research.

Risk assessment and strategic legal recommendations. Use when: assess legal risk, mitigation strategy, negotiation position, risk exposure, contract negotiation strategy, legal risk profile, compliance risk.

Orchestrate multi-agent legal document analysis. Use when: legal analysis, coordinate legal review, synthesize legal findings, document analysis report, combine compliance risk and strategy findings.

Generate 5 audience-tailored communications from one product update. Use when: stakeholder update, executive summary, board narrative, customer changelog, sales enablement, translate for audience, multi-audience communication, sensitivity classification.

Multi-framework strategic analysis for product decisions. Use when: prioritize features, evaluate trade-offs, strategic decision, impact analysis, pre-mortem, ship or sunset, quarterly planning, compare options, confidence scoring.

Build financial models from natural language with sensitivity analysis. Use when: feature ROI, business case, revenue projection, pricing analysis, TAM SAM SOM, unit economics, NPV, payback period, sensitivity analysis, ship or no ship.

Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.

Deep research on any company by scanning their public website to extract customers, partners, case studies, testimonials, key metrics, and competitive positioning. Produces a polished 1-slide PowerPoint summary. Use when: research a company, find customers, who are their customers, company research, company overview, customer list, company intel, customer logos, competitive research on company, scan website for customers.