DevOps & Infra

robsonkades Bundle

Choose and review Kubernetes telemetry adapters when a legacy or vendor process emits incompatible metrics, logs or health signals, when deciding between per-pod translation and a node agent, or when an application upgrade silently changes parsed telemetry. Covers translation contracts, evidence-backed enrichment and failure behavior. Excludes in-process interface adaptation (gof-adapter), container mechanics (sidecar-pattern), probe configuration (kubernetes-service-lifecycle) and telemetry instrumentation design.

robsonkades Bundle

Operating a Kafka consumer from Java: the log-not-a-queue model where consumption removes nothing and position is an offset; the rebalance as the central operational event, with cooperative assignment as the mitigation and where duplicates enter; why slow processing trips max.poll.interval.ms, not the session timeout; pause/resume for slow work; commit strategies; auto.offset.reset as a data-loss-or-reprocessing decision; and lag as record, byte, time and catch-up signals. Use when a group rebalances repeatedly under load, when records are reprocessed after a deploy, when enable.auto.commit is left on, when a consumer starts from the wrong place after an outage. Not ordering scope (message-ordering-and-partitioning), guarantees (delivery-semantics), repeat-safe handlers (idempotency), the record that never succeeds (poison-messages-and-dlq), deserialisation cost (serialization-performance), in-flight bounds (concurrency-limiting-and-bulkheads), or drain (kubernetes-service-lifecycle).

robsonkades Bundle

The investigation process for performance work: defining an SLO, recording a baseline, characterising before diagnosing, falsifiability, fixed-work speedup bounds, experimental design, and validating by mechanism rather than by coincidence. Use when starting a performance investigation, when a fix is credited to a deploy that also restarted the process, when an optimisation is proposed without a measurement, when a benchmark result changes with the duration of the run, when an investigation has run for days without refuting a hypothesis, or when "it's fine in staging" is the explanation. Does not cover which tool to run (jfr-and-async-profiler), the statistics of the numbers (latency-statistics), or microbenchmark construction (jmh-microbenchmarks).

robsonkades Bundle

What happens to a message that cannot succeed: separating the permanently poison message that fails on its own content from the transiently blocked one whose dependency is down, and why an attempt counter cannot tell them apart; the dead-letter queue as a design with an owner, an alert and a redrive path; the record captured beside the payload; and the head-of-line decision in a partitioned log, where skipping a record trades a complete effect sequence for progress. Use when a consumer retries the same record forever, when a DLQ has grown and nobody owns it, when a DLQ record holds only the payload, when a deploy makes every message fail, when a partition stops advancing behind one record, or when dead-lettering is proposed for a dependency outage. Does not cover retry policy (retries-and-backoff), safe replay (idempotency), ordering scope (message-ordering-and-partitioning), the worker pool (task-queues-and-competing-consumers), guarantees (delivery-semantics), or alert thresholds (slo-and-alerting).

robsonkades Bundle

Cutting JVM startup and warm-up while staying on the JVM: CDS and AppCDS, the Leyden AOT cache (JEP 483/514/515), CRaC checkpoint and restore and its constraints, what each mechanism actually accelerates, verifying the cache is really in use, and measuring time-to-first-good-response instead of time-to-port-open. Use when cold start hurts a serverless or autoscaled deployment, when a CI pipeline pays for hundreds of JVM launches, when a CRaC flag fails with Unrecognized VM option, when an AppCDS archive is ignored after a JAR changes, when an outdated -XX:AOTCache is suspected after a rebuild, when -XX:AOTCacheOutput is in the production start command, when spring-boot:build-image is expected to yield a CRaC image, or when a startup speedup percentage is quoted without a source. Does not cover the warm-up curve and traffic gating (jit-compilation), loading, linking and initialisation (jvm-class-loading), or leaving the JVM behind (graalvm-native-image).

robsonkades Bundle

Placing the state that spans several requests of one conversation: client session state, server session state and database session state, plus signed tokens and external stores. Use when a multi-step wizard loses its data on the second replica, when HttpSession holds an object graph, when sticky sessions are added to keep an application working, when a rolling deploy logs everyone out, when a JWT carries mutable state or cannot be revoked, when session data is pushed into Redis without deciding what happens if Redis is down, or when "make it stateless" is proposed without saying where the state will go. Does not cover making an instance disposable in general (stateless-service-design), cache design (caching-strategies), or locks held across a conversation (offline-concurrency-control).

robsonkades Bundle

Making a service instance disposable so replicas are interchangeable: what stateless actually means — no correctness/routing dependency on one instance's volatile history; the in-process state inventory; and session state as a placement decision between sticky routing, an external store and a signed token. Use when replicas is raised above 1, when a @Scheduled job suddenly runs N times, when a local cache disagrees between instances, when an in-memory rate-limit counter or idempotency map is the source of truth, when HttpSession holds anything a user would miss, when a service writes to java.io.tmpdir, or when a rolling deploy loses sessions. Does not cover pod replacement and drain (kubernetes-service-lifecycle), reaching a replica (load-balancing-and-routing), cache design (caching-strategies), fleet-singleton work (leader-election), state split by key (sharding-and-partitioning), pool arithmetic (connection-pool-sizing), or what replicas may observe (consistency-models).

robsonkades Bundle

Designing trustworthy performance-regression gates: defining the decision and smallest important regression, preserving independent experimental units, calibrating noise and power, comparing compatible JMH results, handling multiplicity and drift, separating screening from confirmation, and operating secure baseline promotion. Use when performance results should influence merge, when a threshold or statistical test lacks an empirical error budget, when JMH scoreError is treated as a two-build test, when repeated iterations are mistaken for independent runs, when CI infrastructure changes contaminate comparisons, or when a pipeline can lose a comparator exit status. Does not teach benchmark construction (jmh-advanced), full-system workload design (load-testing), or general latency inference (latency-statistics).

robsonkades Bundle

Getting a request to a replica that can serve it: L4 versus L7 by capability rather than layer number, why an L4 balancer in front of long-lived HTTP/2 or gRPC connections balances connections instead of requests and pins a client to one replica, the balancing algorithms and what each optimises, power-of-two-choices, health checking and outlier ejection with the fleet-ejection hazard, and connection draining. Use when per-pod request rate is skewed while connection counts look even, when one replica is hot after a scale-up, when gRPC or HTTP/2 crosses a ClusterIP Service, when a dependency blip ejects the whole upstream, or when choosing between an ingress proxy, a mesh and client-side balancing. Does not cover why a replica is interchangeable (stateless-service-design), the in-pod proxy form (ambassador-pattern), what to do when every replica is busy (rate-limiting-and-load-shedding), readiness and drain mechanics (kubernetes-service-lifecycle), or routing a key to its owner (sharding-and-partitioning).

robsonkades Bundle

Generational ZGC internals: coloured pointers without multi-mapping, the load and store barriers, the young and old cycles and their STW phases, the remembered-set bitmap and its double buffering, relocation and page management, allocation stalls, and the generational log and JFR event names. Use when a deploy script still carries -XX:+ZGenerational, when jdk.ZAllocationStall events appear or allocation stalls cluster in traffic peaks, when a pause script greps only "Pause Mark" and reports a suspiciously good p99, when heap sizing was carried over unchanged from G1, when ZGC thread CPU is being read out of a thread dump, or when barrier overhead needs to be attributed to reads versus writes. Does not cover choosing between or operating the concurrent collectors (zgc-and-shenandoah), the introductory collector model (gc-fundamentals), or attributing an observed production pause across layers (pause-attribution).

robsonkades Bundle

Four things routinely conflated into one: a blocking API, a blocked OS thread, non-blocking I/O at the syscall, and an asynchronous programming model. Covers which JDK operations unmount a virtual thread and which capture the carrier, the difference between capture-with-compensation and pinning, the socket poller behind blocking socket calls, file I/O as the case Loom does not fix, and what blocking an event loop costs. Use when someone says virtual threads make I/O non-blocking, when a file-heavy workload on virtual threads grows the carrier pool, when a blocking call sits inside a Netty or Reactor pipeline, when jdk.virtualThreadScheduler.maxPoolSize is raised to fix a symptom, or when an argument turns on whether the model or the syscall is the bottleneck. Not choosing between the two models (reactive-and-virtual-thread-selection), continuation mechanics and pinning diagnosis (virtual-threads-internals), demand signalling (reactive-backpressure), or copy avoidance (io-uring-and-zero-copy).

robsonkades Bundle

Chain of Responsibility in modern Java, and the pipeline it is usually confused with: the classical first-accepting form versus middleware where stages may all process and forward conditionally. Covers choosing between them, the unhandled-request policy that silent chains get wrong, ordering discipline when handlers are contributed independently, error propagation and partial state when a stage throws mid-chain, and why servlet filters and interceptor chains are this pattern already implemented. Use when a request must be offered to several possible handlers, when @Order values are tuned to make a chain work, when a request falls off the end of a chain and nothing happens, or when a chain is proposed for three fixed cases. Does not cover the security framework's own filter configuration, the retry and timeout policies applied around a call (gof-decorator, circuit-breakers), or message processing across services (streaming-pipeline-topologies).

robsonkades Bundle

Engineering the full lifecycle of tasks accepted by Java executors: ownership, admission, queue/grow behavior, execution context, result/failure observation, rejection, cancellation, scheduled/periodic semantics, context cleanup, shutdown/drain and recovery. Covers ThreadPoolExecutor, scheduled pools and thread-per-task/virtual-thread executors without treating factory defaults as capacity policy. Use when work disappears, queues grow, rejection or deploy loses work, or a virtual-thread migration removes an implicit bound.

robsonkades Bundle

Java built-in serialization as an attack surface and a permanent API commitment: why readObject is an extra constructor that accepts arbitrary bytes, gadget chains and what deserialization filters (JEP 290/415) can and cannot do, the cost of implementing Serializable, serialVersionUID and the custom serialized form, validating and defensively copying in readObject, the serialization proxy pattern, why records are different, and the same risk in JSON polymorphic typing. Use when Serializable, readObject, readResolve or Externalizable appears, when ObjectInputStream reads bytes from a cache, queue, session store, RMI or JMX, when Jackson default typing is enabled, or when a mixed-version deploy breaks a serialized cache. Format cost is serialization-performance, contract evolution is rpc-and-api-contracts, and the reflective access underneath is java-reflection-and-method-handles.

robsonkades Bundle

A Java service at the edges of its life under Kubernetes: liveness, readiness and startup probes as three different questions, probe timing arithmetic, graceful shutdown as a sequence where endpoint removal races SIGTERM, terminationGracePeriodSeconds as a budget, draining non-HTTP work such as Kafka consumers and scheduled jobs, PodDisruptionBudgets, and limits as availability decisions. Use when 502s appear only during a rolling update, when a liveness probe checks a database and a blip restarts every healthy pod, when initialDelaySeconds was guessed instead of a startupProbe, when a pod exits 137 or loops in CrashLoopBackOff, when a node drain hangs, or when in-flight Kafka or scheduled work is lost on redeploy. Does not cover what the JVM detects in a cgroup (container-awareness), host kernel behaviour (linux-for-jvm), faster startup (startup-cds-crac-leyden), replica disposability (stateless-service-design), routing (load-balancing-and-routing), or API compatibility (rpc-and-api-contracts).

robsonkades Bundle

Reading what the JIT actually did: the columns of -XX:+PrintCompilation and its flag characters, -XX:+PrintInlining and its verdict strings, -XX:+LogCompilation with JITWatch, the -Xlog:jit+compilation and JFR forms, targeted compiler directives, and turning a refusal into a code change. Use when a hot method is suspected of not reaching tier 4, when a call site shows "too big" or another inlining refusal, when a method never appears in the compilation log at all, when someone prescribes -XX:CompileThreshold or -Xlog:jit, when a script greps the compilation log and returns nothing, when a directive added with jcmd changed nothing, when JFR shows no compilation events, or when raising FreqInlineSize globally is proposed to fix one method. Does not cover the tiered pipeline, warm-up and the code cache as concepts (jit-compilation), the design rules about inlining and escape (jit-inlining-and-escape-analysis), recompilation and uncommon traps (deoptimization), or C2's internal representation (c2-sea-of-nodes).

robsonkades Bundle

Define or review checks that preserve architectural qualities when a green pipeline misses incidents, inherited rules are skipped or unexplained, a characteristic lacks evidence, or a metric is being promoted to a blocking gate. Choose the measurement or rubric, threshold, execution site, owner and response policy; expose proxy limits and coverage gaps. Excludes selecting quality drivers (architecture-characteristics), implementing application tests (architecture-testing), pipeline composition (quality-gates), performance experiment thresholds (performance-regression-ci) and operational error-budget design (slo-and-alerting).

robsonkades Bundle

Inlining and escape analysis in C2: inlining as the multiplier, scalar replacement versus "stack allocation", flow-insensitivity, turning a PrintInlining verdict into a code change, and measuring with gc.alloc.rate.norm. Use when allocation rate is high on a hot path, when a hot call is refused inlining and the fix is unclear, when an object pool for small objects, @ForceInline on application code or a higher FreqInlineSize is proposed, when an interface gains a third implementation on a critical path, when "the JIT will handle it" or "allocation is expensive" is asserted without a measurement, when a rare branch makes an object escape, when Optional, a stream or a lambda capture is blamed or excused for allocation, or when a hot method never appears in PrintCompilation. Does not cover warm-up and the tiered pipeline (jit-compilation), benchmark construction (jmh-microbenchmarks) or GC cost (gc-fundamentals). The algorithm itself is escape-analysis-internals; byte attribution is allocation-profiling.

robsonkades Bundle

Whether a given schema change is safe, in which deploy order, and what breaks when it is not: the writer/reader pair, the compatibility levels and who upgrades first, the per-format rules for Avro, Protobuf and JSON Schema, registry configuration, and catching a break in CI. Use when AvroTypeException reports a missing required field, when "Can't get the number of an unknown enum value" is thrown, when UnrecognizedPropertyException exposes an unexpected mapper policy, when auto.register.schemas or specific.avro.reader is left at its default, when a proto field is deleted without reserved or its number reused, when BACKWARD leaves retained history unchecked, when a consumer group reset to earliest dies on old records, when an .avsc gains a field with no default, or when a typed property is added to an open JSON schema. Not wire size (serialization-performance), HTTP API versioning (rpc-and-api-contracts), offsets (kafka-consumers-in-java), or upcasters (event-sourcing).

robsonkades Bundle

Choosing between a reactive pipeline and thread-per-request on virtual threads, and deciding where they legitimately coexist: what each model actually gives you, where backpressure comes from in each, memory per in-flight request versus per idle connection, the diagnosability difference, and the framework configuration that decides which model a request runs under. Use when a team proposes migrating away from WebFlux or towards it, when virtual threads are described as making reactive obsolete, when a blocking call is about to be added to a reactive pipeline, when spring.threads.virtual.enabled is being turned on, when Quarkus RunOnVirtualThread is applied per endpoint, or when both models exist in one service and nobody can say which runs what. Not what blocks a carrier (blocking-and-nonblocking-io), demand and overflow (reactive-backpressure), the migration programme (virtual-thread-migration), or thread costs and sizing (thread-sizing-and-virtual-threads).

robsonkades Bundle

Operating Kafka Streams and Apache Flink for predictable throughput, state and recovery: separating their execution models, sizing partitions or operator parallelism, diagnosing backpressure, bounding native state, and relating commits or checkpoints to result visibility. Use when one partition or operator limits a pipeline, checkpoints grow or stall, RocksDB drives RSS outside the heap, exactly-once changes latency, or effective runtime configuration differs from declared settings. Generic topology and event-time semantics belong to streaming-pipeline-topologies; plain Kafka consumer loops to kafka-consumers-in-java.

robsonkades Bundle

Lambdas, method references and the functional interfaces they implement: what a lambda captures and what that costs, why its this differs from an anonymous class's, when a method reference is clearer, choosing among the standard java.util.function interfaces instead of inventing one, primitive specialisations that avoid boxing, checked exceptions inside lambdas, and the runtime shape (invokedynamic, capturing versus non-capturing, megamorphic call sites). Use when a lambda captures mutable state or a large object, when a codebase reinvents Function or Predicate, when checked exceptions force a try/catch inside a pipeline, or when a queued lambda outlives what it captured. Stream pipelines are java-streams, inlining is jit-inlining-and-escape-analysis, and per-request context a lambda must not capture is scoped-values.

melodic-software Bundle

Look up current library documentation, API references, and code examples via Context7 (ctx7 CLI or the Context7 MCP server, same backend). Use when: 'look up the docs for X', 'how do I migrate to X v2', or whenever a question names a library, framework, SDK, CLI tool, or cloud service, including API syntax, configuration, setup, and version-migration questions. Actions: lookup <library> <query> (default) | update (CLI upgrade + upstream drift check). For CLI/MCP setup, auth, and Windows gotchas, run /context7:setup.

melodic-software Bundle

Interview relentlessly to reach shared understanding on a plan, decision, or idea. Questions arrive in frontier rounds: every question whose prerequisites are settled asked together as one numbered set, each with a recommendation. Routes by context: an engineering task locks a task contract (goal, constraints, acceptance criteria, named assumptions) into a PLAN.md Brief that feeds the planning pipeline; a general decision drives to a shared understanding and stops. Synthesizes directly when intent is clear, runs the rounds loop when gaps remain, or interviews relentlessly on request. Use when: 'interview me', 'lock the brief', 'spec this task', 'grill me', 'this is underspecified', 'ask me questions first', 'what do you need to know', 'acceptance criteria', 'how will we know this is done', or proactively before behavior-changing work when intent is ambiguous or underspecified; skip for mechanical work (typo/lint/whitespace/rename) and casual conversation.

bg-szy Bundle

Store and retrieve unstructured objects, file uploads, and cache-like state on Netlify using the @netlify/blobs key/value API from Functions, Edge Functions, and Build Plugins. Use when a task involves saving user file or image uploads, persisting form or contact-form submissions, storing generated output from Background Functions (sitemaps/processed media/bulk-email results), building read-only asset stores, adding client-side blob expiration, or wiring file-based blob uploads at deploy time. Not for per-user, transactional, or relational data (counters/balances/sessions) — reach for Netlify DB there instead.

bg-szy Bundle

NVIDIA RAG Blueprint deployment, configuration, troubleshooting, and shutdown guidance for Docker, Helm, and library-based RAG stacks.

bg-szy Bundle

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

bg-szy Bundle

Git operations, shell scripting, CI/CD pipelines, and terminal automation. Use for conventional commits, PowerShell/Bash scripting, configuring GitHub Actions, or automating development tooling workflows.

bg-szy Bundle

Configure Netlify projects via netlify.toml and the _headers/_redirects files — covering build settings and deploy contexts alongside environment variables/scopes and the Secrets Controller plus redirect/rewrite/proxy and custom-header rules. Use when setting a build command or publish directory, adding redirect or rewrite or proxy rules, configuring custom headers or basic auth, setting or scoping environment variables and secrets, wiring up a monorepo or SPA fallback, or skipping unnecessary builds. Reach for this whenever you touch netlify.toml or ask "why is my env var undefined in a function" or "how do I redirect this path".

bg-szy Bundle

Create and manage Netlify deploys — Git continuous deployment, CLI manual/anonymous deploys, Deploy to Netlify buttons, drag-and-drop, and per-context netlify.toml build settings. Use when linking a repo, deploying from the CLI, setting up Deploy Previews or branch deploys, configuring deploy contexts, adding skew protection, fixing a failed or secrets-flagged deploy, or wiring build hooks and Deploy to Netlify buttons.

bg-szy Skill

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, WHY HOW WHAT papers, 3W literature scan, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 三段式文獻掃描, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題, 심층 연구, 문헌 조사, 체계적 문헌고찰, 메타분석, 사실 확인, 연구 방향을 잡아줘, 연구 주제 정하는 것을 도와줘.

bg-szy Bundle

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

bg-szy Bundle

Zero-config Postgres for Netlify apps via @netlify/database — querying data from Functions/Edge Functions, writing schema migrations, setting up Drizzle ORM, local dev with netlify dev, database branches for deploy previews, and migrating an existing Postgres project onto Netlify. Use when adding a database, building a contact form or CRUD API, writing SQL migrations, wiring up Drizzle, running netlify database commands, testing with a local Postgres, or switching from Neon/Supabase/RDS to Netlify Database.

bg-szy Skill

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, audit my rebuttal, check my response draft, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見, 評估回覆, 논문 작성, 초록 작성, 논문 수정, 논문 계획을 도와줘, 심사 의견 반영, 답변서 점검, AI 사용 고지.

bg-szy Bundle

Write, configure, and deploy Netlify serverless functions in TypeScript, JavaScript, or Go. Use this when adding an API endpoint or backend route, adding a contact form handler, wiring auth or Identity signup/login hooks, building streaming or AI-proxy responses, scheduling cron jobs, running long background jobs (batch processing/scraping), reacting to deploy or form events, setting up rate limiting or region/memory config, or reading environment variables and secrets inside a function. Covers file locations, the Request/Context/Response handler shape, path routing, config options, and local testing with netlify dev.

bg-szy Bundle

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.