Skills for your AI
Collects, organizes, and analyzes marketing data into KPIs, ROI, segmentation, funnel, forecast, and satisfaction reports. Use when the user asks to gather marketing data, identify KPIs, benchmark competitors, compare periods or channels, evaluate campaign ROI
Runs mechanistic interpretability experiments on PyTorch models with nnsight, locally or remotely via NDIF, covering activation analysis, patching, interventions, and generation. Use when the user wants to inspect or modify hidden states, attention, or logits,
Guides causal intervention experiments on PyTorch models with pyvene, covering causal tracing, activation patching, interchange intervention training, intervention configuration, and experiment tracking. Use when a user wants to localize factual associations,
Guides mechanistic interpretability experiments with TransformerLens, covering activation patching, circuit analysis, induction head detection, activation caching, and model setup. Use when the user asks to inspect or manipulate transformer internals, replicat
Guides MLflow experiment tracking, model registry management, deployment, reproducibility, and autologging with code snippets and best practices. Use when logging runs, registering or promoting models, serving models, rerunning experiments, or enabling autolog
Generates ready-to-run TensorBoard setup, logging, comparison, and profiling code for PyTorch and TensorFlow training scripts. Use when the user asks to set up TensorBoard, log scalars, images, histograms, graphs, embeddings, hyperparameters, text, or PR curve
Analyzes mobile game performance, assets, memory, battery, network, UI/UX, analytics, A/B tests, and monetization to produce prioritized optimization recommendations. Use when a developer asks to find bottlenecks, cut file size, reduce battery or data use, imp
Analyzes network traffic, forecasts growth, and produces capacity, redundancy, and upgrade plans from provided logs, metrics, and inventories. Use when a systems administrator needs bandwidth analysis, growth projections, device or application inventory assess
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checkl
When the user wants to optimize, improve, or increase conversions on any marketing page — including homepage, landing pages, pricing pages, feature pages, or blog posts. Also use when the user says "CRO," "conversion rate optimization," "this page isn't conver
Use when Codex should act as the Personal Growth Mentor specialist from Agency Agents. Cross-domain personal development mentor for goal clarity, habit design, strategic decisions, and accountability without motivational fluff.
Analyzes player feedback, behavior, retention and community data to design engagement strategies, events, rewards and messaging. Use when a game developer needs sentiment analysis, churn analysis, personalized messages, event plans, loyalty programs, community
Forecasts policy renewals and retention from insurance data, covering data validation, trend analysis, predictive models, churn scenarios, sentiment, pricing, channel strategy, and reporting. Use when asked to forecast renewals, predict churn, segment customer
Guides PyTorch-native agentic RL experiments with Meta's torchforge, covering GRPO setup, custom loss functions, distributed training configs, and installation. Use when the user asks to set up GRPO training, implement a custom RL loss, configure multi-GPU or
Turns user behavior data into patterns, personas, personalized UX designs, A/B tests, and predictive features. Use when planning behavior data collection, analyzing engagement trends, building personas, designing personalization or onboarding, running A/B test
Designs safe, curriculum-aligned primary school science experiments, producing ideas, materials lists, safety guidelines, step-by-step instructions, troubleshooting, data collection plans, extensions, age adaptations, and cross-curricular links. Use when a tea
Analyzes, models, and improves manufacturing or operational processes through simulation, statistical analysis, root cause analysis, process mapping, experiment design, control monitoring, cost analysis, and reporting. Use when a process engineer needs to test
Router/index for the 12 product skills bundled in this plugin (RICE prioritization, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery, roadmaps, spec-to-repo, landing pages, SaaS scaffolding). Use when a product request
Turns product usage data into reports, behavior segments, churn risk, upsell leads, adoption and A/B insights for customer success managers. Use when asked to analyze usage exports, predict churn, segment users, find upsell targets, prioritize features, or ben
Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines for production AI features. Triggers: 'manage prompts in production', 'pro
Organizes, retrieves, and protects physical and electronic records with compliant filing systems, retention schedules, and audit-ready processes. Use when setting up filing systems, entering or cleaning data, retrieving or archiving documents, managing retenti
Turns recruitment funnel data into weekly reports, conversion and time-to-fill analyses, source and diversity breakdowns, cost-per-hire figures, benchmarks, and optimization recommendations. Use when asked for a recruitment funnel report, stage conversion rate
When the user wants to design, launch, or optimize a referral or affiliate program. Use when they mention 'referral program,' 'affiliate program,' 'word of mouth,' 'refer a friend,' 'incentive program,' 'customer referrals,' 'brand ambassador,' 'partner progra
Designs referral programs with incentives, triggers, copy hooks, and operational rules. Use when the user asks to launch or improve referrals.
