Browse Skills

Use when establishing product positioning, defining ideal customer profiles, or updating marketing messaging and audience strategy.

Use when building lean, opinionated products with the 37signals method: shaping pitches, betting six-week cycles, running small teams, or cutting...

Use when auditing WCAG 2.2 Level A/AA accessibility, fixing violations in React, Next.js, Vue, Angular, Svelte, or HTML, checking color contrast, or...

Use when planning or designing an A/B test/experiment, or building a systematic growth-experimentation program with hypotheses, sample sizing, and...

Use when the user wants to plan, design, or implement an A/B test or experiment — hypothesis, sample size, variants, statistical significance, or...

Use when conducting systematic literature reviews, evaluating research methodologies, and synthesizing evidence across published sources for...

Use when ensuring WCAG 2.2 compliance, testing with screen readers, validating keyboard navigation, and implementing ARIA patterns.

Use when the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid ad...

Use when the user wants help planning, targeting, or optimizing paid ad campaigns on Google, Meta, LinkedIn, TikTok, or X — budgets, bidding...

Use when reviewing recent code changes or a PR before merge and you want a genuinely critical review, not agreeable rubber-stamping, that surfaces...

Use when planning content for AI-first audiences, auditing E-E-A-T signals, tracking LLM citations, or building a citation strategy for ChatGPT...

Use when install and configure agent collections, resolve dependencies, and validate environments

Use when an autonomous agent takes a consequential, side-effecting action (deploy, delete, pay, grant-access, model decision) that may need proof...

Use when architecting multi-agent systems, selecting orchestration patterns, or evaluating agent performance.

Use when building bounded agentic loops with verified task execution and state machines.

Use when C-suite agents query each other, coordinate cross-functional analysis, or run board meetings with multiple roles: invocation syntax, loop...

Use when designing multi-agent workflows with explicit patterns, handoffs, and cost controls.

Use when multiple approaches should compete in parallel — code optimization, content variants, or research exploration — then be scored and the best...

Use when writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing the...

Use when building production AI applications with LLM integration, RAG pipelines, agent frameworks, or embedding strategies.

Use when the user wants content cited by AI systems (ChatGPT, Perplexity, AI Overviews, Gemini, Copilot) — AEO, GEO, LLMO, AI visibility, or AI...

Use when doing AI-system intake, preparing for EU deployment, or running the annual compliance refresh — the EU AI Act's 6-question, Article-cited...

Use when assessing AI/ML systems or LLM agents for prompt injection, jailbreak risk, model inversion, data poisoning exposure, or tool abuse, mapped...

Use when preparing for ISO/IEC 42001 certification stage 1, running an annual internal audit cycle, or onboarding a new AI system into an existing AI...

Use when setting up analytics tracking, measuring marketing results, configuring GA4 or GTM, or implementing conversion tracking.

Use when building a tracking plan, auditing GA4/GTM for gaps, debugging missing events, or setting up conversion tracking and event taxonomy.

Use when the user wants a blunt, market-first pressure-test of a venture, feature, or career bet, a product-market-fit check, or a daily 3x5-card...

Use when building enterprise applications with Angular 17+, signals, standalone components, RxJS, and NgRx state management.

Use when designing REST or GraphQL APIs with versioning, pagination, and OpenAPI specs.

Use when building API reference documentation with OpenAPI/Swagger, Redoc, and interactive examples including versioning and change tracking.

Use when designing or implementing an API gateway — routing, rate limiting, authentication proxying, or traffic transformation between clients and...

Use when reviewing a PR that adds or changes API endpoints, auditing an existing REST API before a v2 migration, or establishing shared API design...

Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests.

Use when the user asks about ASO, app store rankings, metadata, titles/descriptions, or visibility on Apple App Store or Google Play — keyword...

Use when auditing iOS/macOS/watchOS/visionOS interfaces against HIG, checking accessibility standards, or designing native Apple UI.

Use when the user wants to audit or optimize an App Store or Google Play listing, improve app visibility or ranking, or compare their app's listing...

Use when adding or removing Jira/Confluence users, changing permissions, configuring SSO, managing Atlassian groups, installing marketplace apps, or...

Use when building or updating Jira/Confluence templates, blueprints, page layouts, reusable components, or standardized content structures across an...

Use when optimizing ML experiments using tree search—design experiments, generate code, evaluate results, iterate systematically.

Use when asked to design AWS architecture, pick a serverless/microservices/three-tier/GraphQL pattern, draft CloudFormation/CDK/Terraform infra, or...

Use when designing Azure infrastructure, creating Bicep/ARM templates, optimizing Azure costs, planning CI/CD, or migrating workloads to Azure...

Use when building Node.js backend APIs with Express, Fastify, middleware patterns, and performance optimization.

Use when developing, stress-testing, or validating a systematic trading strategy's backtest for robustness, parameter sensitivity, or overfitting.

Use when conversation is emotionally charged or user requests more human-like responses ('be real', 'behuman', 'mirror mode'). NOT for technical...

Use when designing performance benchmarks, load tests, comparative evaluations, and reproducible measurement methodologies with statistical rigor.

Use when building smart contracts, Web3 applications, or blockchain systems using Solidity, Hardhat, and EVM-compatible patterns.

Use when the user wants to create uncontested market space via value innovation, mentions blue/red ocean, strategy canvas, ERRC, or non-customers, or...

Use when coordinating between agents via AgentHub message board. Read, post, and browse channels for agent coordination.

Use when assembling board/investor decks. Covers structure, narrative framework, bad news delivery, financial summary, metrics dashboard, section...

Use when running structured C-suite deliberation on a strategic question. 6-phase protocol: context, isolated independent analysis, critic review...

Use when preparing for a board meeting, investor update, or fundraising presentation — mastering numbers cold, anticipating hard questions, and...

Use when a decision spans multiple C-suite domains (e.g., pricing change, funding vs. cuts). Runs 6-phase deliberation: context, isolated analysis...

Use when applying, documenting, or enforcing brand guidelines for color systems, typography, logo usage, imagery, and tone of voice consistency.

Use when analyzing market breadth via the S&P 500 Breadth Index or US Stock Market Uptrend Stock Ratio, assessing market health, or building...

Use when the user has VCP (volatility contraction pattern) screener results and wants Minervini-style breakout trade plans with entry/stop/target...

Use when framing a strategic decision before boardroom deliberation. Outputs one-page brief with context, options (min 2), assumptions, constraints...

Use when automating browser tasks: scraping sites, filling forms, capturing screenshots/PDFs, extracting structured data, or building Playwright...

Use when running Playwright tests on BrowserStack cloud grid for cross-browser and cross-device testing.

Use when optimizing build systems and compilation pipelines including bundlers, caching, and artifact production.

Use when performing requirements analysis, process mapping, gap analysis, and aligning stakeholders on technical projects.

Use when a growth/revenue request doesn't clearly match one skill — customer health, RFP analysis, pipeline forecast accuracy, or contracts — and...

Use when evaluating whether to invest in equipment, real estate, a new business, hiring, or technology, or for ROI/IRR/NPV/payback analysis...

Use when diagnosing or designing internal business operations: process bottlenecks, vendor SLAs, capacity planning, internal comms, SOP/runbook...

Use when invoking C-suite advisors. 13 cs-* agents + 21 /cs:* commands: office hours, boardroom deliberation, strategic sprint pipeline, decision...

Use when exploring the C-level advisory bundle (33 skills, 14 roles). Find the right skill, entry points (cs-onboard, chief-of-staff routing...

Use when pressure-testing an AI plan — shipping without an eval set, choosing API vs. fine-tune vs. build, or classifying a use case under the EU AI...

Use when analyzing marketing campaign performance, ad performance, attribution models, funnel conversion rates, or calculating marketing ROI, ROAS...

Use when the user wants a CANSLIM stock screen: growth-stock analysis, momentum identification, or ranking stocks by earnings, growth, and price...

Use when running CAPA investigations, 5-Why or fishbone root cause analysis, corrective action planning and tracking, effectiveness verification, or...

Use when sizing an ops team (Support, CX, BizOps, IT, Finance ops) handling queued work — headcount planning, utilization risk, or a quarterly hiring...

Use when the user dumps a chaotic stream of thoughts, tasks, or ideas and wants it turned into a structured, actionable summary with nothing dropped.

Use when you want terse, caveman-mode responses: drop filler, abbreviate, fragment OK. Stay active until explicitly stopped.

Use when gross retention is slipping, before approving CS headcount, or when deciding which customer segments to keep, downgrade, or fire.

Use when validating training-data consent before an AI project, choosing a data architecture, or valuing a data asset for productization or M&A.

Use when planning strategy, prepping for a board meeting, managing investors, shaping culture, or making a major executive or fundraising decision.

Use when building financial models, analyzing unit economics, planning a fundraise, managing cash runway, or preparing board financial materials.

Use when a plan commits meaningful spend (hiring wave, fundraise, new channel budget). Numerate interrogation of unit economics, runway, and capital...

Use before significant resource commitment, presenting to board/investors, or when feedback is one-sidedly positive. Pre-mortem analysis to uncover...

Use when announcing a reorg, tool migration, strategy pivot, or leadership change. Apply ADKAR (Awareness, Desire, Knowledge, Ability...

Use when generating release notes from Conventional Commits, computing semantic version bumps, cutting releases, or planning hotfixes.

Use when reviewing direct vs. partner-led channel economics — computing fully-loaded cost to serve, channel ROI, and optimal channel mix during a...

Use when validating system resilience through controlled fault injection, failure mode analysis, and chaos experimentation.

Use when planning, running, or reviewing a chaos experiment: fault injection, gameday, blast radius, steady state, abort criteria, Chaos Toolkit...

Use when deciding API vs fine-tune vs build, classifying an AI use case under EU AI Act/NIST AI RMF, calculating API-to-self-hosted breakeven, or...

Use when designing retention strategy, decomposing GRR vs NRR, segmenting customers for differential investment, sizing a CS team's coverage model...

Use when deciding whether to train models on customer data, choosing warehouse/lakehouse/mesh architecture, valuing customer data for fundraising or...

Use when a founder question needs routing to the right advisor, when a decision spans multiple domains, or when a hard call needs a full board...

Use when building hiring plans, designing comp frameworks, restructuring teams, managing performance, building culture, or when user mentions CHRO...

Use when the user wants to reduce churn, build cancel flows or save offers, recover failed payments, or set up dunning and retention strategies.

Use when bootstrapping CI, refactoring pipelines, or standardizing deployment workflows across repos from detected project stack.

Use when building security programs, justifying security budget, selecting compliance frameworks, managing incidents, assessing vendor risk, or when...

Use when launching features that handle customer data, before a SOC 2 / ISO audit, or after any incident or near-miss.

Use when the user wants to personal coach that teaches users to become claude power users. use this skill the first time a user asks to "learn...

Use when discussing architecture layers, the dependency rule, hexagonal/onion/screaming architecture, where business logic should live, decoupling...

Use when cleaning up code, a function is too long, code smells, naming conventions, single responsibility, unit test quality, or reviewing a pull...

Use when building robust CLI tools using Commander.js, yargs, clap with polished interfaces and shell completion.

Use when designing a prospective clinical study: selecting/classifying endpoints, estimating sample size and power, or scoring phase-gate feasibility...

Use when building data-oriented systems with Clojure, REPL-driven development, persistent data structures, and Ring/Compojure.

Use when designing scalable, secure, cost-efficient multi-cloud infrastructure with IaC and well-architected patterns

Use when assessing cloud infrastructure for security misconfigurations: IAM privilege escalation, S3 exposure, open security groups, or IaC gaps...

Use when designing brand strategy, selecting growth models (PLG vs sales-led vs community-led), allocating marketing budgets, building marketing...

Use when launching a campaign or repositioning, or when CAC is rising and the one-sentence positioning test fails.

Use when finding co-marketing partners, planning a joint campaign, or evaluating partnership fit — mentions of partner marketing, cross-promotion, or...

Use when conducting code reviews to catch bugs, improve quality, and mentor through constructive feedback on patterns, security, and performance.

Use when reverse-engineering a frontend, backend, or fullstack codebase into a business-readable Product Requirements Document detailed enough to...

Use when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers...

Use when analyzing test coverage gaps and planning improvements.

Use when writing B2B cold outreach emails, prospecting campaigns, or follow-up sequences that convert.

Use when launching or scaling a marketplace, social, or collaboration product with network effects -- chicken-and-egg growth, atomic networks, hard...

Use when the user wants a session retrospective or AI-contribution analysis: what Amara contributed vs. what the developer drove. Triggers on 'what...

Use when building a quarterly bookings forecast, ARR projection, pipeline forecast, NRR projection, or a commit/best-case/pipe-only board number with...

Use when designing or revising discount rules, approval thresholds, exception flows, or the discount matrix governing how deals get discounted off...

Use when reviewing or routing commercial questions on pricing, deal discounts, partnerships, channel mix, commercial policy, RFP response, or...

Use when a user wants to build, launch, or grow an online community (Discord, Slack, forum) for retention, advocacy, or word-of-mouth.

Use when building a company from scratch as OKF (Open Knowledge Format) markdown. Guides 12-phase interview with conformant frontmatter, links, and...

Use when setting up company operations, selecting a management framework (EOS, Scaling Up, OKRs), designing meeting rhythms, building accountability...

Use when mapping competitive landscapes, analyzing feature positioning, and identifying strategic differentiation opportunities across comparable...

Use when analyzing competitors, building sales battlecards, tracking market moves, positioning against alternatives, or when user mentions...

Use when analyzing competitors, building sales battle cards, preparing a product roadmap session, responding to a competitor's pricing change, or...

Use when given competitor URLs and asked to produce structured, comparable competitor profiles covering positioning, product, pricing, customers, and...

Use when building competitor comparison or alternative pages for SEO and sales enablement — vs pages, alternative pages, or competitor-vs-competitor...

Use when creating SEO competitor comparison pages, alternative pages, battle cards, or positioning your product against competitors.

Use when evaluating software against SOC 2, GDPR, HIPAA compliance frameworks and establishing continuous compliance monitoring.

Use when standing up a multi-framework compliance program, planning the annual audit calendar, or preparing for certification stage 1 across multiple...

Use when adopting a new compliance framework, finalizing the annual audit calendar, or signing off on certification stage-1 readiness across...

Use when building image classification, object detection, segmentation pipelines using OpenCV, PyTorch, and inference optimization.

Use when building or restructuring a Confluence space, designing page hierarchies and permissions, authoring documentation templates, embedding Jira...

Use when designing shareable features, engineering word-of-mouth or virality, building referral programs, or figuring out why content isn't...

Use when planning content strategy, building editorial calendars, conducting keyword research and topic clustering, writing SEO-optimized content, or...

Use when the user wants to plan a content strategy, decide what content to create, build topic clusters, or figure out what to write about next.

Use when a request for content creation routing is needed. Identifies user intent and routes to content-production for writing/SEO tasks or...

Use when content sounds robotic, overuses AI clichés, lacks personality, or needs brand voice injected after a first draft is already written.

Use when writing a blog post, article, or guide end-to-end — from research and brief through drafting to SEO and readability optimization.

Use when context window optimization, progressive loading, and strategic compaction

Use when starting any C-suite advisor session, when context looks stale or missing, or before sending company data to an external service.

Use when building a weekly cadence of customer interviews, an Opportunity Solution Tree, assumption testing, or connecting product discovery to the...

Use when drafting a freelance contract, client proposal, SOW, NDA, or MSA needing jurisdiction-aware clauses for US, EU, UK, or DACH markets.

Use when designing operations, setting up OKRs, building processes, scaling teams, analyzing bottlenecks, planning operational cadence, or when user...

Use when the user wants to edit, review, tighten, or refresh existing marketing copy — proofreading, polishing, sharpening messaging, or updating...

Use when writing marketing copy for web pages, landing pages, or product pages that need to persuade and convert.

Use when the user asks about COT report analysis, crowded futures positioning, who is "trapped" in a market, or a Jason Shapiro-style...

Use when analyzing test coverage gaps across a codebase.

Use when setting product vision, managing a product portfolio, measuring product-market fit, designing the product org, prioritizing at the portfolio...

Use when committing a quarter's roadmap, deciding whether to kill a feature, or claiming PMF without a retention curve.

Use when optimizing conversion rates on marketing pages, landing pages, or forms that aren't converting well.

Use when designing the revenue engine, setting quotas, modeling NRR/GRR, building board revenue forecasts, evaluating pricing, or scaling sales...

Use when auditing why a landing page or funnel isn't converting, designing A/B test hypotheses, mapping objections, or diagnosing checkout/signup...

Use when pipeline coverage drops below 3x, win rates trend down, forecasting misses targets, or before scaling the sales team.

Use when a high-stakes memo needs independent sanity check before boardroom approval—e.g., major pivots, fundraising terms, or decisions that cost >6...

Use when planning tech go-to-market from early adopters to mainstream -- beachhead selection, whole product, positioning against incumbents, or...

Use when setting up C-suite advisors for the first time, or when company context is missing or >90 days old—e.g., after a fundraise or pivot.

Use when building applications on .NET 8+ with ASP.NET Core, Entity Framework Core, minimal APIs, and async patterns.

Use when assessing technical debt, scaling the engineering team, evaluating build-vs-buy, making architecture decisions, writing ADRs, or setting...

Use when committing to architecture changes, planning for 10x load, weighing rebuild against vendor, or when SLOs are missed.

Use when building company values, assessing culture health, designing cultural rituals, creating culture codes, handling culture clashes, or when...

Use when the user wants to conduct, analyze, or synthesize customer research — interviews, surveys, support tickets, reviews, or personas built from...

Use when building customer support infrastructure: ticket triage automation, knowledge base systems, workflow automation, or customer health scoring...

Use when analyzing customer accounts, scoring churn risk, reviewing retention or health metrics, or identifying expansion/upsell opportunities across...

Use when building data pipelines with ETL/ELT workflows, Spark, data warehousing, or pipeline orchestration.

Use when extracting meaningful insights from datasets through statistical analysis, pattern recognition, and evidence-based reasoning.

Use when Statistical analysis, data visualization, hypothesis testing, and exploratory data analysis with Python

Use when Creates interactive dashboards and data visualizations using D3.js, Chart.js, Matplotlib, and Plotly with accessibility and performance...

Use when checking data quality, profiling a dataset, hunting outliers or missing values, or validating data before analysis or model training.

Use when validating market analysis documents or blog articles before publication for price-scale, notation, date/weekday, allocation-total, and unit...

Use when designing database schemas, optimizing queries, managing replication, backups, and high-load operations

Use when tuning database performance: query optimization, EXPLAIN ANALYZE diagnostics, indexing, partitioning, connection pooling, or capacity...

Use when designing database schemas, planning data migrations, optimizing queries, choosing between SQL and NoSQL, or modeling data relationships.

Use when the user asks to create ERD diagrams, normalize database schemas, design table relationships, or plan schema migrations.

Use when choosing a database, weighing SQL vs NoSQL, diagnosing replication lag or a partitioning strategy, reasoning about consistency vs...

Use when reviewing an inbound deal before close: a discount exceeds AE authority, a customer redlined the MSA, or discount approval needs routing to...

Use when an approved boardroom memo becomes durable company memory—e.g., right after boardroom conclusion with founder approval.

Use when logging decisions after a board meeting, reviewing past decisions, or checking overdue action items—invoked automatically after boardroom...

Use when conducting rigorous, multi-source investigations backed by ≥3 independent sources per claim, parallel sub-agents, adversarial review, and...

Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, or marketing video from screenshots or...

Use when auditing and updating project dependencies for security, compatibility, license compliance, and minimal bloat.

Audit and manage dependencies across multi-language projects. Identifies vulnerabilities, license conflicts, transitive dependency risks, and...

Use when designing zero-downtime deployments, blue-green strategies, canary releases, and feature flag systems

Use when a product feels confusing or unintuitive — apply affordances, signifiers, constraints, feedback, and conceptual models to diagnose...

Use when the user wants to prototype and test a product idea with real users fast, mentions a "design sprint," or a team is stuck debating a...

Use when a user wants a project's brand — colors, fonts, style — captured or reset before producing branded HTML, a report, or slides.

Use when building an internal developer portal — service catalogs, self-service infrastructure, templates, or platform engineering tooling with...

Use when building CI/CD pipelines, container infrastructure, Kubernetes operations, GitOps workflows, and production monitoring

Use when planning or executing directory, Product Hunt, and review-site submissions for backlinks, discovery, and AI-citation, sequenced behind the...

Use when the user wants dividend growth stocks (12%+ dividend CAGR) pulled back to an RSI oversold level (≤40), for total-return-focused dividend...

Use when building applications with Django 5+ and Django REST Framework, including ORM optimization, migrations, and async views.

Use when optimizing a Dockerfile, creating/improving docker-compose configs, implementing multi-stage builds, auditing container security, reducing...

Use when creating technical documentation including API references, guides, tutorials, and architecture decision records.

Use when modeling software around the business domain: bounded contexts, aggregates, ubiquitous language, domain events, or splitting a monolith into...

Use when the user needs decision-grade background research on a specific company, person, nonprofit, or gov org (meeting prep, due diligence...

Use when a user wants typical correction lengths by sector or market-cap tier, historical drawdown recovery times, or realistic holding-period...

Use when deciding whether new trade risk is allowed today, based on realized P&L, losing-streak cooldowns, and weekly/monthly drawdown limits.

Use when designing motivation systems, fixing broken gamification or rewards, or addressing team disengagement using the Autonomy, Mastery, Purpose...

Use when the user wants a reproducible quality score for a skill's content, combining structural checks with a qualitative content review.

Use when improving developer experience through tooling ergonomics, workflow automation, and environment standardization.

Use when building e-commerce systems with product catalogs, shopping carts, inventory management, and order processing workflows.

Use when the user wants a weekly earnings calendar, asks which companies report earnings next week, or requests a review of upcoming market-moving...

Use when the user wants post-earnings trade analysis, momentum screening, earnings gap scoring, or the best recent earnings reactions, scored 0-100...

Use when the user asks about upcoming economic events, central bank decisions, employment, inflation, or GDP releases, or wants a market-moving...

Use when turning market observations into reproducible research tickets, exporting ideas as strategy.yaml + metadata.json, or checking...

Use when abstracting raw detector tickets and hints into reusable edge concepts with thesis and invalidation logic before strategy drafting or export.

Use when converting daily market observations, anomalies, and news reactions into structured hints.yaml for downstream concept synthesis or...

Use when coordinating the full edge research pipeline end-to-end, from candidate detection through strategy design, review, revision, and export.

Use when consolidating outputs from multiple edge-finding skills into one weighted, deduplicated, contradiction-flagged conviction dashboard before...

Use when converting abstract edge concepts into concrete strategy draft variants and exportable ticket specs for edge-candidate-agent.

Use when quality-gating strategy drafts from edge-strategy-designer against edge plausibility, overfitting, and export-readiness criteria before...

Use when building learning management systems with SCORM/xAPI compliance, adaptive learning engines, and learner analytics capabilities.

Use when building or reviewing an Electron desktop application — IPC design, native OS integration, performance, security hardening, or auto-update...

Use when building fault-tolerant, concurrent applications with Elixir, Phoenix, OTP supervision trees, LiveView, and BEAM.

Use when creating or optimizing email sequences, drip campaigns, automated email flows, nurture sequences, onboarding emails, or lifecycle email...

Use when adding transactional email to a product, migrating providers, refactoring templates for a11y, or adding i18n. Covers React Email, Resend...

Use when creating email sequences, drip campaigns, automated flows, or lifecycle email programs for nurture and conversion.

Use when developing firmware for resource-constrained microcontrollers and embedded Linux platforms with RTOS integration

Index of 37 advanced engineering agent skills for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Use when browsing or choosing among the...

Index of the engineering-team skills bundle for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend...

Use when auditing .env files for committed secrets, planning a credential rotation, debugging a missing-env-var production incident, or hardening a...

Use when building a cinematic, immersive website with scroll-driven depth, parallax, and motion using flat PNG assets, CSS, and JS only. Also for...

Use when handle errors across multi-agent workflows, implement recovery strategies, and prevent cascading failures

Use when investigating production errors, analyzing stack traces, generating reproduction steps, and identifying root causes.

Use when Builds robust data pipelines with schema evolution, data quality checks, incremental loading, and fault-tolerant processing

Use when classifying an AI system's EU AI Act risk tier, planning Article 43 conformity assessment for a high-risk system, or scoping...

Use when results from multiple teammates who attempted the same task need to be scored, compared, and a winner picked — by metric, by LLM judge, or...

Use when designing event-driven systems: event sourcing, CQRS, message queues, and distributed communication.

Use when a logged decision needs to become an operating plan—e.g., turning approved strategy into weekly milestones with named DRIs and kill criteria.

Use when a plan needs stress-testing before the board sees it, before a hard call with no good options, or after something went wrong and needs an...

Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with...

Use when deciding equity exposure by synthesizing breadth, regime, and flow signals into an exposure ceiling, growth/value bias, participation read...

Use when the user asks to save, package, or reuse a recurring pattern, workaround, or debugging solution as a standalone skill, or references...

Use when handling FDA submission pathway selection (510(k)/PMA/De Novo), QMSR/ISO 13485 compliance, medical device HIPAA assessments, or device...

Use when prepping an annual internal FDA QSR audit or inspection readiness review, or responding to a Form 483, Warning Letter, MDR event, or recall...

Use when Designs feature stores, feature pipelines, and encoding strategies that ensure consistent feature computation across training and serving

Use when adding, retiring, or auditing feature flags: rollout plans, kill switches, stale flag debt, or choosing a flag provider (LaunchDarkly...

Use when a finance request doesn't clearly match one approach and needs routing — e.g. statement analysis, DCF valuation, SaaS metrics, or a single...

Use when analyzing financial statements, building valuation models, assessing budget variances, or constructing financial projections, forecasts, or...

Use when building financial systems with precise arithmetic, regulatory compliance, audit trails, and transaction integrity

Use when the user describes stock-screening criteria (English or Japanese) and wants a FinViz screener URL built and shared, e.g. high-yield small...

Use when a Playwright test fails or passes intermittently. Diagnose using taxonomy and apply targeted fixes.

Use when building cross-platform mobile and desktop applications with Flutter 3+, Dart, state management, and platform channels.

Use when the user asks to fix, debug, or make a whole feature/module work end-to-end, not a quick single-bug fix. Triggers: "make X work", "fix the Y...

Use when optimizing a lead capture, contact, demo request, application, survey, or checkout form on fields, copy, layout, or completion rate.

Use when a founder feels like the bottleneck, struggles to delegate, is burning out, is transitioning from IC to executive, managing a board, or...

Use when a founder asks any strategic question without knowing which advisor fits—e.g., runway pressure routes to CFO, gross retention dropped routes...

Use when planning, evaluating, or building a free tool for lead generation, SEO value, or brand awareness — calculators, generators, graders, or...

Use when deciding whether to build a free marketing tool — a calculator, generator, checker, or grader — and how to design, gate, and launch it.

Use when an irreversible decision was made under pressure — e.g. a layoff plan or multi-year contract — and deserves a cooling-off lock before...

Use when architecting React/Next.js features, optimizing performance, or reviewing frontend design patterns.

Use when the user asks if the market is bottoming, whether it is safe to buy after a correction, about Follow-Through Days, rally attempts, or...

Use when capturing full-page screenshots with lazy-loaded content, SPAs, and tall pages via Chrome DevTools Protocol.

Use when building complete features across frontend, backend, and database layers end-to-end.

Use when designing game systems, logic, and architecture patterns for Unity, Godot, and custom game engines

Use when reviewing a term sheet before signing, redlining a customer MSA, or checking IP assignment and regulatory exposure on a new product.

Use when designing GCP infrastructure, deploying to GKE or Cloud Run, configuring BigQuery pipelines, optimizing GCP costs, or migrating workloads to...

Use when prepping an annual internal GDPR review, a post-breach audit, DPA investigation readiness, or acquisition due diligence on a target's...

Use when running GDPR/DSGVO compliance assessments, privacy audits, DPIA generation, or data subject rights (DSAR) tracking, e.g. checking GDPR risk...

Use when reviewing any contract or term sheet, deciding when to engage outside counsel, defining IP strategy, or evaluating regulatory exposure...

Use when generating production-ready Playwright tests from user stories, URLs, components, or feature descriptions.

Use when building GIS applications with PostGIS, spatial queries, mapping APIs, tile servers, and geospatial data processing pipelines

Use when designing Git branching strategies, CI integration patterns, and repository workflow automation.

Use when running multiple feature branches simultaneously, isolating experimental work, or coordinating multi-agent development so each worktree gets...

Use when writing Go code with emphasis on concurrency patterns, interfaces, error handling, testing, and module management.

Use when formulating or auditing real strategy — turning goal lists into a diagnosis, guiding policy, and coherent action (Rumelt's strategy kernel)...

Use when advising on Google Workspace administration or automation via the gws CLI — Gmail, Drive, Sheets, Calendar, Docs, Chat, Tasks setup...

Use when the user asks about NIH research funding — finding grants, positioning a research idea, or matching it to institutes/mechanisms (e.g...

Use when designing GraphQL schemas, implementing resolvers, federation, or optimizing query performance with DataLoader

Use when the user wants to stress-test a plan, get grilled on their design, or mentions "grill me" — interviews relentlessly until reaching shared...

Use when stress-testing a plan against documented domain language, or the user mentions "grill with docs" — challenges terms against CONTEXT.md and...

Use when implementing A/B testing frameworks, analytics instrumentation, funnel optimization, and data-driven growth experiments.

Use when handing off the conversation to a fresh agent, or starting a session that picks up prior work — compacts it into a handoff doc referencing...

Use when every option is painful and a structured 10/10/10 + regret-minimization pass is needed — e.g. choosing between a layoff and a down round, or...

Use when writing pure functional code in Haskell with type-driven design, monads, type classes, and GHC extensions.

Use when building HIPAA-compliant healthcare systems with HL7 FHIR interoperability, medical data pipelines, and clinical workflow integration

Use when creating or reviewing Helm charts, designing values.yaml, writing template helpers, auditing chart security (RBAC, network policies, pod...

Use when running 1:1s, structuring a manager's calendar, setting OKRs, delegating by task-relevant maturity, or preparing performance reviews, per...

Use when a site is slow, diagnosing Core Web Vitals, HTTP/2 or HTTP/3, resource hints, render-blocking resources, TCP/TLS optimization, caching...

Use when designing habit-forming product loops (Trigger, Action, Variable Reward, Investment), re-engagement or notification strategy, streaks, or...

Use when creating or improving an offer -- value equation, bonus stacking, guarantees, ethical scarcity, offer naming, or justifying premium pricing...

Use when the user wants a daily post-close market-deterioration check, before increasing TQQQ/QQQ exposure, or to evaluate an uptrend's vulnerability...

Use when the user wants to create, generate, edit, or optimize marketing images — blog heroes, social graphics, product mockups, banners, or brand...

Use when diagnosing retention, activation, onboarding friction, or churn. Applies the Fogg Behavior Model (B=MAP), the Ability Chain, and Tiny Habits...

Use when the user wants to set up email triage for the first time: a one-time interview builds the taxonomy, voice, and preference records...

Use when the user wants their inbox processed on a recurring or on-demand basis: classified, researched, drafted (never sent), and reported, after...

Use when coordinating rapid production recovery, triaging incidents, executing runbooks, maintaining stakeholder communication

Use when declaring an incident, coordinating a multi-team response during an outage, leading a post-mortem, or setting up on-call practices. Covers...

Use when a security incident is declared and needs classification, triage, escalation routing, or forensic evidence collection. Covers SEV1-SEV4...

Use when writing persuasive copy, testimonials, or urgency messaging. Applies Cialdini's seven principles: reciprocity, commitment, social proof...