keyvaluesoftwaresystems
- 198 skills
- 0 followers
- 5 repo stars
- 5 days ago last updated
- ▌ Django Tdd 3 · keyvaluesoftwaresystemsDjango testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.
- ▌ Django Patterns 3 · keyvaluesoftwaresystemsDjango architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
- ▌ Pytorch Patterns 3 · keyvaluesoftwaresystemsPyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
- ▌
- ▌ Fastapi Patterns · keyvaluesoftwaresystemsFastAPI best practices covering project structure, Pydantic v2 schemas, dependency injection, async handlers, authentication, authorization, transactional service layers, and testing with httpx and pytest.
- ▌ Build Knowledge · keyvaluesoftwaresystems bundleScan the codebase and build the living-docs knowledge base (architecture.md, plus functional and technical docs per domain with rule, invariant and change-scenario IDs), the per-repo codebase maps, and seed cross-cutting review lessons. Front door for /build-knowledge.
- ▌ Functional Testcases · keyvaluesoftwaresystemsAuthor a FUNCTIONAL test-case catalog (human-readable, black-box) for a feature by deriving cases from the acceptance criteria, the HLD, and the cross-repo contract — one case per behavior a user or client can observe, positive + negative + edge, each traceable to the criterion/operation it verifies. Black-box QA source of truth, NOT automation code. Reads the design artifacts; writes the catalog; never edits app code. Front door for /functional-testcases.
- ▌ Django Security · keyvaluesoftwaresystemsDjango security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
- ▌ Human Review Pack · keyvaluesoftwaresystemsAssemble a concise, evidence-backed PR/release review pack — what changed and why, impact, the verification proof, reviewer findings (fixed and deferred), and the exact decision needed. Read-only; writes the pack. Front door for /human-review-pack.
- ▌ Architecture Review · keyvaluesoftwaresystemsReview a high-level design before it is approved, as a reviewer who did not write it — architecture style, boundaries, interfaces, security, failure, scale, operations, and over- or under-engineering — with evidence-backed findings and a blocking verdict. Read-only; writes a review artifact. Front door for /architecture-review.
- ▌ Django Celery · keyvaluesoftwaresystemsDjango + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.
- ▌ Detect Stack · keyvaluesoftwaresystemsScan the codebase to detect its technology stack(s) and each repository's E2E suite (proposed for the engine to confirm), then install only the matching stack-tagged skills (plus the always-installed core SDLC pack) by running the installer with a --stack filter. Does not write maestro.config.yaml. Front door for /detect-stack.
- ▌ Maestro Init · keyvaluesoftwaresystemsOne-shot onboarding for a repo — detect-stack installs matching skills, then the project-config skill writes maestro.config.yaml from that result (registry.yaml names when present), then build the living-docs knowledge base only when docs are stale. Run once when adopting Maestro in a codebase. Front door for /maestro-init or $maestro-init.
- ▌ Retrospect · keyvaluesoftwaresystemsDistill a finished Maestro run into structured, keyed lessons staged for the engine to consolidate. Front door for /retrospect.
- ▌ Repo Implement · keyvaluesoftwaresystemsImplement every task slice in one selected repository, test-first, to the repository's engineering standards, and return a verifiable worktree handoff.
- ▌ Prd Interview · keyvaluesoftwaresystemsClarify product intent before a PRD is written. Summarize maintained project context, confirm the feature goal, generate feature-specific Grill questions, and resolve material behaviour and edge cases without scanning application code or drafting the PRD.
- ▌ QA Automation · keyvaluesoftwaresystemsAuthor critical-journey E2E / UI-automation tests from the acceptance criteria (not from the implementation) in the project's own E2E framework, run them in a clean env, and report; a project without one gets each case checked directly against the running system, never a new framework. Meets QA standards (risk-tiering, isolation, determinism, no weakened assertions). Edits test files only. Front door for /qa-automation.
- ▌ Hld Interview · keyvaluesoftwaresystemsClarify material architecture decisions before an HLD is finalized. Generate feature-specific technical Grill questions, audit prior answers and contradictions, and collect grouped answers without drafting design prose.
- ▌ Lld Interview · keyvaluesoftwaresystemsClarify only material repository implementation decisions before the repository LLDs are written. Audit existing answers, inspect each bounded implementation seam, and ask feature-specific questions in grouped native popups.
- ▌ Repo Review · keyvaluesoftwaresystemsReview one repository's exact implementation worktree and commit against its LLD and contract, with evidence-backed findings and a blocking verdict.
- ▌ API Contract · keyvaluesoftwaresystemsDefine the cross-repository API/event CONTRACT (OpenAPI, or AsyncAPI for events) for every interface an approved HLD lists, following the owning repository's existing API conventions, before the repository LLDs are written. Also applies a narrow requested change to an existing contract. Writes the contract; never edits app code. Front door for /api-contract.
- ▌ Lld Writing · keyvaluesoftwaresystemsWrite or narrowly repair buildable repository LLDs — one per repository — from an approved HLD and contract, confirmed decisions, and bounded code evidence, including an implementation-complete data model and the repository's exact side of the contract, in concise, skimmable technical English.
- ▌ Prd Writing · keyvaluesoftwaresystemsWrite, normalize or repair one final PRD in plain, skimmable technical English — from fully confirmed structured context, or by restructuring the client's own PRD and listing only what it leaves open. Never invent missing product decisions.
- ▌ Repo Tasks · keyvaluesoftwaresystemsBuild a validated, repo-specific parallel task DAG from an approved LLD and contract.
- ▌ Hld Writing · keyvaluesoftwaresystemsWrite or narrowly repair one decision-focused HLD from an approved PRD, maintained architecture context, and confirmed technical decisions in plain, skimmable technical English.
- ▌ Maestro · keyvaluesoftwaresystemsLead agent for Maestro workflows — drives a workflow.yaml end-to-end by carrying out engine-served lead actions, dispatching workers, and asking humans. Front door for /maestro or $maestro with a feature slug and optional workflow file. Use when the user wants to run, resume, or continue an orchestrated SDLC flow for a feature.
- ▌ Fix Loop · keyvaluesoftwaresystemsMake ONE bounded fix attempt at failing deterministic checks — root-cause first, editing only files related to the failure — then report. Front door for /fix-loop.
- ▌ Terraform Patterns · keyvaluesoftwaresystemsTerraform reference for designing and reviewing infrastructure changes — module structure, state and environments, safe plans, capacity and scaling settings, networking, secrets, and change safety. Use when a feature's HLD or LLD changes Terraform-managed infrastructure.
- ▌ Architecture Patterns · keyvaluesoftwaresystemsReference for choosing and reviewing system architecture — when each pattern fits, when it does not, and what it costs. Covers architecture style (modular monolith, services, event-driven, serverless), sync vs async integration, data ownership, outbox and idempotent consumers, sagas, CQRS, caching, BFF/gateway, resilience, horizontal scaling and partitioning, multi-tenancy, and observability. Use when writing or reviewing an HLD.
- ▌ Kubernetes Patterns · keyvaluesoftwaresystemsKubernetes, Helm and Kustomize reference for designing and reviewing workload changes — deployments, probes, resources and autoscaling, disruption budgets, config and secrets, networking and ingress, jobs, rollout, and observability. Use when a feature's HLD or LLD changes Kubernetes-managed workloads.
- ▌ React Review · keyvaluesoftwaresystemsReact review checklist — what to check in React code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Maestro Sync · keyvaluesoftwaresystemsBring Maestro up to date after a repository is added to the workspace — the engine adds a maestro.config.yaml entry for each newly cloned repo, then detect-stack and project-config fill only those repos' stack and commands, matching stack skills are installed, and build-knowledge writes the new repos' docs (codebase map, domain pages, architecture.md). Front door for /maestro-sync or $maestro-sync.
- ▌ Django Review · keyvaluesoftwaresystemsDjango review checklist — what to check in Django code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Kotlin Review · keyvaluesoftwaresystemsKotlin review checklist — what to check in Kotlin code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Python Review · keyvaluesoftwaresystemsPython review checklist — what to check in Python code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Project Config · keyvaluesoftwaresystemsWrite maestro.config.yaml from a detect-stack result. Repo names come from registry.yaml when that file exists; a workspace sandbox script's documented commands become the worktree settings, an infra script's the environment settings. Does not scan the codebase and does not install skills. Called by /maestro-init after detect-stack
- ▌ Fastapi Review · keyvaluesoftwaresystemsFastAPI review checklist — what to check in FastAPI code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Flutter Review · keyvaluesoftwaresystemsFlutter and Dart review checklist — what to check in Flutter and Dart code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Typescript Review · keyvaluesoftwaresystemsTypeScript and JavaScript review checklist — what to check in TypeScript and JavaScript code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Type Design Review · keyvaluesoftwaresystemsTypeScript type design review checklist — what to check in TypeScript type design code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Container Patterns · keyvaluesoftwaresystemsDockerfile and Docker Compose reference for designing and reviewing container changes — images, runtime config and secrets, ports, health checks, resources, local and QA stacks. Use when a feature adds or changes a containerized service or the Compose stack.
- ▌ Vue Review · keyvaluesoftwaresystemsVue review checklist — what to check in Vue code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Design Drift · keyvaluesoftwaresystemsCompare the implemented code with the approved design before release — HLD decisions, the API contract, each repository's LLD and the infrastructure changes — and report every place the code departs from it, with evidence. Read-only; writes a drift report and findings. Front door for /design-drift.
- ▌ Lld Readiness · keyvaluesoftwaresystemsCheck that a feature's repository LLDs (and test cases, when supplied) are ready to implement — no design decision left to the implementer, every repository consistent with the contract and with each other, every acceptance criterion covered. Read-only; writes a readiness report. Front door for /lld-readiness.
- ▌ Repo Scaffold · keyvaluesoftwaresystemsCreate the starting skeleton of new repositories from an approved high-level design — project layout, a passing build and test, lint, a README, CI, a container image when the design deploys one, and a codebase map — and report each repository's commands. Front door for /repo-scaffold.
- ▌ Java Review · keyvaluesoftwaresystemsJava (Spring Boot, Quarkus) review checklist — what to check in Java (Spring Boot, Quarkus) code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Rust Review · keyvaluesoftwaresystemsRust review checklist — what to check in Rust code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Feature Impact · keyvaluesoftwaresystemsAssess which repositories an approved feature changes, whether it changes an interface between repositories, stored data or infrastructure, and list everything it touches (domains, tables, jobs, queues, endpoints and their consumers, rules, change scenarios), from the PRD and the codebase maps. Read-only; writes a structured impact assessment. Front door for /feature-impact.
- ▌ Database Review · keyvaluesoftwaresystemsdatabase (PostgreSQL) review checklist — what to check in database (PostgreSQL) code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Maestro Discuss · keyvaluesoftwaresystemsSide-chat partner for Maestro interviews — discuss ONE open PRD/HLD/LLD interview question with the human in a separate session, then record the agreed outcome so the main run's context never sees the discussion. Front door for /maestro-discuss or $maestro-discuss with a slug, step and question id.
- ▌ Go Review · keyvaluesoftwaresystemsGo review checklist — what to check in Go code, by severity. A reference for writing and reviewing it; in a workflow run the review step records each problem as a finding and the engine decides what blocks.
- ▌ Quarkus Patterns 2 · keyvaluesoftwaresystemsQuarkus 3.x LTS architecture patterns with Camel for messaging, RESTful API design, CDI services, data access with Panache, and async processing. Use for Java Quarkus backend work with event-driven architectures.
- ▌ Quarkus Security 2 · keyvaluesoftwaresystemsQuarkus Security best practices for authentication, authorization, JWT/OIDC, RBAC, input validation, CSRF, secrets management, and dependency security.
- ▌ Kotlin Testing 2 · keyvaluesoftwaresystemsKotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.
- ▌ Python Testing 2 · keyvaluesoftwaresystemsPython testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
- ▌ Architecture Review 2 · keyvaluesoftwaresystemsReview the per-stack LLDs and the cross-repo contract — analyze architecture gaps, security, scaling, reliability, data model, and contract soundness. Read-only; writes a review artifact. Front door for /architecture-review.
- ▌ Database Migrations 2 · keyvaluesoftwaresystemsDatabase migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
- ▌ Kotlin Patterns 2 · keyvaluesoftwaresystemsIdiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.
- ▌ Django Patterns 2 · keyvaluesoftwaresystemsDjango architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
- ▌ Django Security 2 · keyvaluesoftwaresystemsDjango security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
- ▌ Python Patterns 2 · keyvaluesoftwaresystemsPythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
- ▌ Nextjs Turbopack · keyvaluesoftwaresystemsNext.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
- ▌ Build Knowledge 2 · keyvaluesoftwaresystemsScan the codebase and build a structured living-docs knowledge base (technical + functional per domain, plus an architecture diagram), and seed cross-cutting review lessons. Front door for /build-knowledge.
- ▌ Functional Testcases 2 · keyvaluesoftwaresystemsAuthor a FUNCTIONAL test-case catalog (human-readable, black-box) for a feature by deriving cases from the acceptance criteria, the HLD, and the cross-repo contract — one case per behavior a user or client can observe, positive + negative + edge, each traceable to the criterion/operation it verifies. Black-box QA source of truth, NOT automation code. Reads the design artifacts; writes the catalog; never edits app code. Front door for /functional-testcases.
- ▌ Fastapi Patterns 2 · keyvaluesoftwaresystemsFastAPI best practices covering project structure, Pydantic v2 schemas, dependency injection, async handlers, authentication, authorization, transactional service layers, and testing with httpx and pytest.
- ▌ Pytorch Patterns 2 · keyvaluesoftwaresystemsPyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
- ▌ React Performance 2 · keyvaluesoftwaresystemsReact and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.
- ▌ Springboot Patterns 2 · keyvaluesoftwaresystemsSpring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.
- ▌ Springboot Security 2 · keyvaluesoftwaresystemsSpring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services.
- ▌ Design Correction Fold 2 · keyvaluesoftwaresystemsApply human-approved corrections to final design-document copies with minimal, validated edits and no unrelated rewriting.
- ▌ Angular Developer 2 · keyvaluesoftwaresystemsGenerates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.
- ▌
- ▌
- ▌
- ▌ Kotlin Ktor Patterns 2 · keyvaluesoftwaresystemsKtor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing.
- ▌ React Native Patterns 2 · keyvaluesoftwaresystemsReact Native and Expo app patterns — Expo Router navigation, state separation (server/client/route/form), TanStack Query data fetching with Zod, performant lists, NativeWind/StyleSheet styling, native APIs, and secure storage. Use when building or editing React Native / Expo screens, components, navigation, or data layers.
- ▌
- ▌ Dart Flutter Patterns 2 · keyvaluesoftwaresystemsProduction-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture.
- ▌ Kotlin Coroutines Flows 2 · keyvaluesoftwaresystemsKotlin Coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, and testing.
- ▌ Kotlin Exposed Patterns 2 · keyvaluesoftwaresystemsJetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern.
- ▌ Flutter Dart Code Review 2 · keyvaluesoftwaresystemsLibrary-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture.
- ▌ Android Clean Architecture 2 · keyvaluesoftwaresystemsClean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns.
- ▌ Compose Multiplatform Patterns 2 · keyvaluesoftwaresystemsCompose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
- ▌ Maestro 2 · keyvaluesoftwaresystemsLead agent for Maestro workflows — drives a workflow.yaml end-to-end by carrying out engine-served lead actions, dispatching workers, and asking humans. Front door for /maestro or $maestro with a feature slug and optional workflow file. Use when the user wants to run, resume, or continue an orchestrated SDLC flow for a feature.
- ▌ Plan 2 · keyvaluesoftwaresystemsProduce a concise, decision-focused high-level design (HLD) for a feature. Ground the direction in requirements and the existing system, record only material trade-offs, and write a developer-readable hld.md. Read-only except for the HLD and open-question artifacts. Front door for /plan.
- ▌ Verify 2 · keyvaluesoftwaresystemsRun the project's deterministic checks and produce an evidence-backed proof report plus a machine-readable proof marker. Never modifies code (writes only its proof artifacts). Front door for /verify.
- ▌ Fix Loop 2 · keyvaluesoftwaresystemsMake ONE bounded fix attempt at failing deterministic checks — root-cause first, editing only files related to the failure — then report. Front door for /fix-loop.
- ▌ Repo Tasks 2 · keyvaluesoftwaresystemsBuild a validated, repo-specific parallel task DAG from an approved LLD and contract.
- ▌ Hld Writing 2 · keyvaluesoftwaresystemsWrite or narrowly repair one decision-focused HLD from an approved PRD, maintained architecture context, and confirmed technical decisions in plain, skimmable technical English.
- ▌ Lld Writing 2 · keyvaluesoftwaresystemsWrite or narrowly repair one buildable repository LLD from an approved HLD, confirmed repo decisions, and bounded code evidence, including an implementation-complete data model and a frontend-ready API/client contract in concise, skimmable technical English.
- ▌ Prd Writing 2 · keyvaluesoftwaresystemsWrite or repair one final PRD from fully confirmed structured context in plain, skimmable technical English. Use only after the PRD interview is complete; never invent missing product decisions.
- ▌ Repo Design 2 · keyvaluesoftwaresystemsProduce a concise, buildable low-level design (LLD) for one repository. Ground it in that repo's code, show the implementation seam, responsibilities, critical flows, interfaces, state, and verification without repeating the HLD or padding irrelevant sections. Writes only the LLD. Front door for /repo-design.
- ▌ Repo Review 2 · keyvaluesoftwaresystemsReview one repository's exact implementation worktree and commit against its LLD and contract.
- ▌ API Contract 2 · keyvaluesoftwaresystemsGenerate the cross-repo API/event CONTRACT (OpenAPI) by reconciling the per-stack LLDs — the backend LLD (what it exposes) and the frontend LLD (what it consumes) — into the single boundary both build against. Also derives acceptance criteria and the affected stacks. Reads the LLDs; writes the contract; never edits app code. Front door for /api-contract.
- ▌ Backend Tasks 2 · keyvaluesoftwaresystemsSplit an approved backend scope + contract into a small, ordered, test-first task list with a verification step per task and risk flags. Read-only planning — never edits code.
- ▌ Hld Interview 2 · keyvaluesoftwaresystemsClarify material architecture decisions before an HLD is finalized. Generate feature-specific technical Grill questions, audit prior answers and contradictions, and collect grouped answers without drafting design prose.
- ▌ Lld Interview 2 · keyvaluesoftwaresystemsClarify only material repository implementation decisions before one repo LLD is written. Audit existing answers, inspect the bounded implementation seam, and ask feature-specific questions in grouped native popups.
- ▌ Prd Interview 2 · keyvaluesoftwaresystemsClarify product intent before a PRD is written. Summarize maintained project context, confirm the feature goal, generate feature-specific Grill questions, and resolve material behaviour and edge cases without scanning application code or drafting the PRD.
- ▌ QA Automation 2 · keyvaluesoftwaresystemsAuthor critical-journey E2E / UI-automation tests from the acceptance criteria (not from the implementation), run them in a clean env, and report. Meets QA standards (risk-tiering, isolation, determinism, no weakened assertions). Edits test files only. Front door for /qa-automation.
- ▌ Clickhouse Io 2 · keyvaluesoftwaresystemsClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.