Loading...
Loading...
Found 388 Skills
Use when you need to execute R3 (Prototype Generation) in the product requirement Spec process of sdlc-dev, generate requirements/prototype.md based on requirements/prd.md (including task flow + page structure + ASCII wireframe + AC mapping + walkthrough script), and avoid proceeding with generation without context/PRD, using Open Questions instead of verification checklists, or using non-ASCII formats that make the prototype untraceable and unreviewable.
Use this skill when diagnosing, configuring, or monitoring NICs for AF_XDP / XDP workloads. Covers driver detection, hardware queue configuration, offload control (GSO/GRO/TSO/LRO), VLAN offloads, Flow Director (FDIR) rules, CPU core pinning and NUMA awareness, hardware queue and drop monitoring, BPF program inspection with bpftool, kernel tracing via ftrace, perf profiling and flamegraphs, IRQ-to-queue-to-core mapping, and a quick diagnostic checklist.
Privacy-first planning-only statement export for banks, cards, brokerages, and payment platforms. The LLM builds a manual download checklist with official URLs, suggested date ranges, export formats, and staging directory, but does not use browser tools or browser automation. Use when account files are not on disk yet and the user wants more privacy. CLEAR step: C (Capture)
Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: "production checklist", "harden agent", "production ready", "secure agent", "inbound auth", "going live", "cold start optimization", "session lifecycle", "StopRuntimeSession", "quota", "throttling", "maxVms", "rate limit", "security audit of outbound API calls", "gateway target audit for production", "restrict who can call", "lock down endpoint", "only our app can call". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.
Designing lead magnets that earn the email. The discipline of building gated content (ebooks, templates, checklists, swipe files, mini-courses, free tools) that delivers genuine standalone value while qualifying the lead and warming them for what comes next. Honest about thin-bait (overpromises, underdelivers), kitchen-sink-resource (everything, helps with nothing), and earned-value-magnet (delivers standalone value while qualifying the lead). Triggers on lead magnet, gated content, opt-in offer, ebook, checklist, template, swipe file, mini-course, free tool, content upgrade, freebie, opt-in, list-building offer. Also triggers when an audience is being asked for an email and the offer attached to that ask needs design discipline, when previous lead magnets converted but did not produce qualified leads, or when a lead magnet is being scoped for the first time.
Use this skill when diagnosing, configuring, or monitoring NICs for AF_XDP / XDP workloads. Covers driver detection, hardware queue configuration, ring buffer sizing, RSS indirection table management, interrupt coalesce tuning, offload control (GSO/GRO/TSO/LRO), VLAN offloads, Flow Director (FDIR) rules with loc pinning and ixgbe wipe bug workaround, RPS/XPS queue CPU mapping, sysctl network tuning, CPU core pinning and NUMA awareness, hardware queue and drop monitoring, softirq and rx_missed_errors analysis, BPF program inspection with bpftool (prog dump xlated, net show), kernel tracing via ftrace and dmesg, perf profiling and flamegraphs, IRQ-to-queue-to-core mapping, bonding interface diagnostics, socket inspection, and a quick diagnostic checklist.
This skill should be used when the user asks to "add a Lottie animation", "play a .lottie or .json animation", "integrate a Bodymovin/After Effects animation on web or mobile", "control Lottie playback / segments", "make a scroll-driven Lottie", "recolor a Lottie at runtime", or "export an AE animation to Lottie". Covers dotLottie/lottie-web integration, playback control, interactivity, theming, and the AE export checklist.
Design audit checklist - motion gaps, accessibility, color consistency, responsive, performance.
Use quando o usuário pede progresso geral, status de todas as especificações, percentual concluído, quanto falta, bloqueios ou próximo trabalho do repositório Specsfy, ou quando uma transição automática pedir a projeção final ou o roteamento pelo estado observado. Produz uma visão somente leitura de specs, gates, tarefas e checklists; não use para alterar a especificação ou implementar tarefas.
Use quando o usuário pede para validar, revisar, auditar ou checar se `specs/{id}-{slug}/spec.md` segue o formato rígido Specsfy/2.0 e está pronto para planejar. Use também quando uma transição automática pedir prova do Definition Gate ou nova validação após correção. Use antes do Ato II. Registre gates na seção 13 do mesmo arquivo; não crie checklist, relatório, plan.md ou outro artefato.
Architecture-aware feature scaffolding for .NET 10 projects. Detects the project's architecture (VSA, Clean Architecture, DDD, Modular Monolith) and generates complete feature slices with all required layers: endpoint, handler, validator, DTOs, EF configuration, and integration tests — with the completeness checklist and per-architecture code templates every generated feature must satisfy. Use when: "scaffold", "create feature", "add feature", "new endpoint", "generate", "add entity", "scaffold a module", "add module", or when customizing generation templates or defining what a complete feature slice includes.
Move quality earlier in the development lifecycle. Covers dev/QA pairing patterns, Three Amigos sessions, TDD facilitation (Red-Green-Refactor), PR review checklists for testability, and Definition of Done with quality gates. Includes shift-left maturity model for team assessment. Use when: "shift left," "TDD," "dev-QA pairing," "definition of done," "testability," "quality culture," "QA in sprint planning." Not for: writing the unit tests themselves — use unit-testing; automated PR test-quality review at scale — use ai-qa-review; multi-quarter QA direction or roadmap — use test-strategy. Related: unit-testing, ai-qa-review, test-strategy.