Decompose firmware into RTOS tasks with deadline-derived priorities, queue-based communication, and priority-inversion defenses.
Match people and capacity to project needs over time, accounting for partial allocation, ramp-up, and the cost of splitting attention.
Coordinate agents through a shared written workspace they each read and update, instead of passing messages.
Move a file from the user's device to durable storage and a processed state, with validation, progress, and recovery at every stage.
Plan scalability from a load model and bottleneck math, designing for realistic growth without premature over-engineering.
You MUST use this when receiving feedback on any text-based work artifact — code, specs, design docs, PRDs, proposals, plans, or prose — before implementing suggestions,…
Operate as a solutions architect who turns a customer's constraints into a defensible reference design and a path to production.
Combine result sets with UNION, INTERSECT, and EXCEPT, and know when a join or an exists clause is the better tool.
Reason about DNS records, resolution, TTLs, and caching so name changes land predictably instead of mysteriously.
Split services along business capabilities with clear data ownership, avoiding the distributed monolith.
Make payment operations safe to retry so a network timeout never charges a customer twice. Use when calling a payment API, processing webhooks, or building any money-moving…
Hold a consistent standard across everything a company ships, with agents that review against written criteria and escalate disagreements rather than averaging them.
Choose a loss that matches the task and the metric you care about, and understand what each penalises. Use when a model optimises well and performs badly on the thing that matters.
Build small, fast, secure container images with layer caching, multi-stage builds, and a minimal base policy. Use when images are bloated, slow to build, or failing security scans.
Handle plurals, grammatical gender, and agreement using locale plural categories rather than an if-else on count.
Migrate workloads to the cloud with honest 6R triage, dependency mapping, and rehearsed cutovers with rollback.
Shape pull requests a reviewer can actually hold in their head, through small size, a why-first description, and a self-review pass.
Remove or blunt identifiers so a dataset can be analysed or shared without re-identifying people, and know when it is only pseudonymous.
Produce a short honest briefing across every desk on a fixed cadence, surfacing decisions needed rather than activity performed.
Choose media formats and codecs by compatibility, quality, and licensing, with fallbacks for what the client cannot play. Use when deciding what to store and deliver.
Enforce and revoke access on live connections so a permission change takes effect immediately rather than at the next page load.
Present results so a user can judge relevance without opening each one, with useful snippets, clear grouping, and honest metadata.
Direct and supervise a coding agent (Claude Code, Cursor, Antigravity) so it ships correct, verified work.
Write engineering resumes with quantified impact bullets, honest tailoring, and machine-readable formatting. Use when writing or reviewing a technical resume.
Keep agent usage within budget through context discipline, model selection, and caching, without degrading results. Use when agent costs are rising or long sessions are expensive.
Flatten nested conditionals into early returns that handle edge cases up front and keep the main path unindented. Use when logic marches rightward into deep nesting.
Keep Spring Boot apps explicit with constructor injection, typed configuration, test slices, and restrained magic.
Keep a retrieval corpus current as source documents change, with incremental updates, deletion propagation, and a stated staleness budget.
Detect input, prediction, and performance drift with reference windows and act through retrain or rollback triggers.
Match data to object, block, or file storage tiers by access pattern, consistency, and cost per operation.
Guide for building ASP.NET Core Minimal APIs with OpenAPI/Swagger integration in .NET 10
Run a standing finance function with agents that reconcile transactions, track runway, flag anomalies, and prepare reporting for a human to approve.
Work with the borrow checker through ownership-first design instead of fighting it with clones and unsafe.
Publish an npm package that installs and imports cleanly: correct exports map, dual formats, types, and semver.
Move new users to their first value moment fast by defining activation, instrumenting the funnel, and cutting time-to-value. Use when signups do not become engaged users.
Cut the CPU and bytes spent turning objects into wire or disk format by choosing the right format, reusing schemas and buffers, and avoiding copies.
Place assertions where invariants are established or must hold: constructors, public boundaries, and loop bodies.
Prepare, run, and close meetings with agents so each one produces decisions and owned actions instead of discussion.
Run translation as a pipeline with catalogs, context, review, and continuous updates rather than a one-off handoff.
Reason honestly about at-most-once, at-least-once, and effectively-once semantics end to end. Use when specifying messaging behavior or auditing where a pipeline can lose or…
Validate requests at the boundary with schemas, reject unknown fields, and return errors clients can act on.
Run an org-level board that grades incident postmortems against a quality bar, promotes cross-cutting fixes to owned work, and reads across incidents for trends.
Build a mobile app where the local database is the source of truth, the UI reads and writes it directly, and a background sync engine reconciles with the server.
Make a working local environment reachable in minutes from a clean machine, and keep it close to production.
Make absence explicit in the type and resolve it at the edges so the interior never dereferences a surprise null.
Bootstrap a Node.js backend with ESM, typed config, graceful shutdown, and structured logging from the start.
Use formatting rules to surface exceptions and patterns automatically, without turning the sheet into a colour chart. Use when readers need to spot outliers or status at a glance.
Treat any serialized bytes from outside the program as hostile, parsing them through schema-validated formats instead of native object reconstructors.
Simulate an interview panel as agents that design questions, score independently on anchored rubrics, and reconcile in a debrief.
Read research papers efficiently in passes, separating claims from evidence and assessing reproducibility.
Apply Microsoft's Security Development Lifecycle so threat modeling, tooling, and sign-off are built into each phase instead of bolted on before ship.
Configure rules that stop unreviewed or broken code reaching the default branch, without making routine work impossible.
Use Tailwind-style utilities with discipline, extracting components at the right threshold and keeping class lists readable.
Distinguish overfitting from underfitting, data leakage, and distribution shift, since all four present as poor validation performance.
Explain the failing code line by line in writing until the sentence you cannot finish exposes the false assumption.
Push work to the edge so requests never touch your origin, using cache headers, invalidation, and origin shielding.
Catch timing-dependent bugs that vanish under observation by amplifying the race and moving logging off the critical path.
Turn raw sensor readings into trustworthy data with correct sampling, filtering, calibration, and timestamped batching.
Understand how files, directories, and durability actually work, so data written is data that survives a crash.
Design interfaces that survive translated text growing or shrinking substantially, without truncation or broken layout.