Latest Agent Skills

Write product-facing technical specs that clarify decisions, constraints, dependencies, and rollout.

Write stakeholder updates that make progress, risks, asks, and decisions easy to act on.

Analyze product health across acquisition, activation, engagement, retention, quality, and monetization.

Map the PRINCE2 management products and project documentation needed by process, including startup, initiation, stage control, product delivery, stage boundary, direction gates, and closure.

Prioritize product work with explicit criteria, scoring, tradeoffs, and decision rationale.

Design product experiments around hypotheses, audience, metrics, guardrails, and decisions.

Build a launch checklist with owners, dates, dependencies, decision gates, and follow-through.

Specify dashboards around decisions, audiences, questions, metrics, cuts, and refresh rhythm.

Turn strategy inputs into a clear narrative with stakes, choices, tradeoffs, and next moves.

Turn research inputs into concise evidence, patterns, confidence levels, and product decisions.

Build the PRINCE2 Initiating a Project pack: project initiation documentation, business case, project plan, controls, management approaches, product descriptions, and baseline decisions.

Frame pricing and packaging decisions with segments, value metrics, tiers, risks, and tests.

Assess launch readiness across product, engineering, support, sales, marketing, risk, and measurement.

Prepare implementation handoffs with states, flows, assets, edge cases, and acceptance criteria.

Create a delivery plan with goals, capacity, scope, risks, and commitments.

Create a slide-by-slide roadmap review structure for planning and leadership conversations.

Choose the right Project + Product skill for a request and sequence multiple skills when the work spans discovery, requirements, delivery, launch, PRINCE2 governance, or team rituals.

Create a market activation plan with audience, positioning, channels, enablement, and metrics.

Write executive-ready product updates with signal, tradeoffs, risks, and recommendations.

Turn meetings into decisions, owners, open questions, and follow-ups.

Map product assumptions by risk, confidence, evidence, and next validation step.

Prepare the PRINCE2 Starting Up a Project material: mandate review, project brief, outline business case, project product description, initiation stage plan, lessons, and startup decisions.

Compare a product against alternatives by positioning, capabilities, gaps, and strategic moves.

Create a clear project status brief with progress, risks, blockers, decisions, and next actions.

Create a practical onboarding plan for a new team member with outcomes, first-week structure, stakeholder introductions, learning path, and manager check-ins.

Turn sprint inputs into a kickoff-ready brief with goals, tickets, risks, and team context.

Investigate retention patterns, cohorts, drivers, warning signs, and intervention options.

Prepare PRINCE2 Closing a Project material: product acceptance, end project report, lessons report, benefits review plan, handover, follow-on actions, and closure recommendation.

Design team offsites with objectives, agenda flow, exercises, logistics, and post-offsite actions.

Write a roadmap narrative that connects customer problems, company goals, bets, and sequencing.

Design product metric trees, North Star metrics, input metrics, and instrumentation needs.

Create a role interview kit with role outcomes, interview plan, scorecard, evidence prompts, and evaluation criteria.

Frame jobs, triggers, desired outcomes, anxieties, and product opportunities.

Plan structured workshops with goals, agenda, activities, prompts, decision rules, and follow-ups.

Create product objectives, key results, initiatives, guardrails, and review cadence.

Redux middleware — the `store => next => action => {}` pipeline for side effects, logging, analytics, and async (thunk/saga). Use when writing custom middleware, wiring async thunks, ordering middleware in configureStore, or keeping side effects out of reducers.

Container/presentational component split — "smart" containers connect to the store, fetch data, and orchestrate loading/error/empty states; "dumb" children just render props. Use when extracting data logic from views, introducing custom hooks, or reviewing `*Container` components.

App Shell architecture — the cached HTML/CSS/JS skeleton (header, nav, footer) served instantly via Service Worker while dynamic content streams in. Use when building PWAs, wiring service-worker caches, inlining critical CSS, or adding offline fallbacks and skeleton loading states.

Selector functions for the chota-react-saga template — colocated with each slice, return derived view-data from the saga state shape (isLoading/isContentLoading/isActionLoading/error/<items>/<current>), filter/sort projections that combine slices (e.g. visibleTodos × selectedFilter).

Pure switch/case reducers for the chota-react-saga template — initial-state file, three-phase async cases per CRUD verb, optimistic mutations with `previousState<Items>` rollback, fall-through SUCCESS/ERROR for toggle and delete.

Plain-object Redux actions for the chota-react-saga template — three-phase async triples (REQUEST / SUCCESS / ERROR) per CRUD verb, single-phase actions for sync ops, UPPER_SNAKE type constants, and explicit hand-written action creators (no createAsyncThunk).

Atomic-design guidance for Templates — page-level wireframes that arrange organisms into layout slots (hero/main/sidebar/footer) without fetching data. Use when authoring components under ui/templates, defining reusable page skeletons, or keeping layout decisions out of pages and organisms.

Skeleton loading placeholders — gray-shape stand-ins that mirror final content dimensions, use subtle shimmer/pulse animation, and prevent layout shift. Use when replacing generic spinners with content-shaped placeholders, reducing perceived latency on slow routes, or preventing CLS on image-heavy cards.

Atomic-design guidance for Organisms — complex feature-level sections (Header, ProductGrid, CommentSection) that compose molecules, connect to state, handle loading/error/empty states, and own responsive layout decisions. Use when authoring components under ui/organisms or deciding molecule vs organism boundaries.

Atomic-design guidance for Molecules — functional groups of atoms (SearchBar = input + button + icon; FormField = label + input + error) with a single cohesive purpose. Use when authoring or reviewing components under ui/molecules, composing atoms, or deciding atom vs molecule vs organism.

Redux store wiring for the chota-react-saga template — single createStore, combineReducers per domain, applyMiddleware(sagaMiddleware), composeWithDevTools, and a one-line `sagaMiddleware.run(rootSaga)` at boot. Use when scaffolding the root store or auditing how slices and middleware compose.

Page components — the thin data-fetching layer that binds a route to a template, invoking getServerSideProps/getStaticProps and passing props down. Use when creating a new route, choosing SSR vs SSG vs ISR for a page, or reviewing whether a page is doing template-level work it shouldn't.

Redux-Saga (generator-based) middleware for async side effects — yields declarative effects (call/put/select/takeLatest/delay) instead of imperative async code, watcher-per-slice composition, optimistic updates with rollback. Use when authoring per-slice operations.js, the rootSagas composer, or reviewing saga workers.

CRUD patterns for state slices — consistent `domain/create|read|update|delete` action naming, request/success/failure triples per operation, and normalised `{ byId, allIds }` entity shapes for O(1) lookups. Use when designing a new entity slice, standardising action-type names, or refactoring array-shaped state.

Async data-fetching patterns — Fetch vs Axios, service-layer organisation, AbortController cancellation, and integration with Redux Toolkit's createAsyncThunk for pending/fulfilled/rejected state transitions. Use when writing or reviewing HTTP call sites, standardising loading/error handling, or wiring request cancellation in effects.

API service-layer patterns — axios/fetch client with interceptors, domain-scoped service objects (UserService, ProductService), auth-token refresh, request cancellation, and error normalisation. Use when adding or reviewing HTTP call sites, organising services under api/ or services/, or centralising cross-cutting request concerns.

Design-token systems — semantic CSS custom properties for colours, spacing, typography, and shadows, with light/dark theme switching via `[data-theme]` overrides. Use when setting up a token catalogue, auditing components for hardcoded colours/magic numbers, or adding dark-mode support via token swaps.

Atomic-design guidance for UI Atoms — the smallest single-purpose building blocks (buttons, inputs, icons, labels). Use when authoring or reviewing components under ui/atoms, components/atoms, or when deciding whether a component belongs at the atom level.

Create GitHub Issues from implementation plan phases using feature_request.yml or chore_request.yml templates.

Create GitHub Issue for feature request from specification file using feature_request.yml template.

Create GitHub Pull Request for feature request from specification file using pull_request_template.md template.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Cria visualizações de dados interativas e profissionais usando Highcharts.js, gerando HTML standalone com gráficos animados, responsivos e acessíveis. Use este skill sempre que o usuário pedir para criar gráficos, charts, dashboards, visualizações de dados, ou qualquer representação visual de dados numéricos/categóricos. Deve ser usado quando o usuário mencionar termos como "gráfico", "chart", "dashboard", "highcharts", "visualização de dados", "gráfico de linhas", "barras", "pizza", "scatter", "heatmap", "treemap", "gauge", "stock chart", "mapa", "gantt", "sankey", "funnel", ou quando fornecer dados (CSV, JSON, tabela, planilha) pedindo representação visual. Também deve ser ativado quando o usuário pedir gráficos bonitos, interativos, animados, com tooltip, drill-down, ou exportáveis. Funciona com dados inline, CSV, JSON, e arquivos de dados. Sempre gera HTML standalone completo e funcional.

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.