Skills for making games: build a playable prototype and take it to a finished game, hold a frame budget on the hardware you are shipping to, choose a multiplayer authority model and make it survive latency, tune numbers against telemetry instead of taste, and keep an asset pipeline from eating the build.
39 skills · 2 commands · 2 agents
Skills for the defensive side of shipping software: review a change for the vulnerability classes that actually get exploited, reduce who can do what toward least privilege without breaking production, rotate or contain a credential, harden a container image and keep checking it, read a Terraform plan for what it destroys, preserve evidence and build an intrusion timeline after a compromise, respond to credential stuffing, write and test detection rules, prove tenant isolation, handle vulnerability reports from outside researchers, and reverse engineer the binaries, managed CIL assemblies, APK packages, packaged apps, firmware and WebAssembly you are authorised to examine — including de-bloating a smart-TV or streaming device you own.
31 skills · 2 commands · 5 agents
Skills for the daily loop of changing code: review a diff for the defects that actually break production, debug a failure down to a proven cause, decide what to test before writing tests, restructure code without changing behaviour, orient yourself in an unfamiliar codebase, review a regex for catastrophic backtracking, write documentation that stays true, scaffold new production-ready code, design an API you can still evolve, land a dependency upgrade, build a website, and author a skill that fires when it should.
29 skills · 1 command · 5 agents
Skills for keeping a running system alive: triage a red pipeline to its real cause, get a broken Kubernetes workload back before diagnosing it, design alerts where every page is actionable, instrument a service so the next incident is answerable, write the runbook a stranger can follow at 3am, rehearse failure on purpose, plan for load before it arrives, and find out why the bill grew.
19 skills · 2 commands · 7 agents
Skills for engineering leadership: take over a team and audit what you inherited, record decisions, write status updates, run postmortems and incident comms, read delivery health, review on-call load, design the team cadence, a reorganisation and goals, make the case for headcount or for paying down tech debt, map team skills and single points of knowledge, plan onboarding, hire, benchmark pay, evaluate vendors, handle retention, growth reviews, improvement plans and difficult conversations, and assess how a team uses AI. Also ships two subagents, for reading contracts and synthesising feedback, and two commands.
22 skills · 2 commands · 2 agents
Skills for code that runs on a user's browser or phone: field performance, hydration, memory, version skew, service workers, CSP and Safari bugs, dates and locales, crashes, hangs, startup, battery, bad networks, on-device migrations, deep links, pushes and app size.
22 skills · 1 agent
Skills for analytics data and classical machine learning: find why a number is wrong or a query costs too much, reconcile and decompose metrics, keep history, defend against upstream change, resolve duplicate entities, retire shadow spreadsheets, design and read experiments, and take models from leakage checks to production monitoring.
22 skills · 1 agent
Skills for cloud and platform engineering: Kubernetes control plane, networking and storage, Terraform estates, cloud networks, identity, databases, the edge and commitments, covering the painful recurring situations operations, delivery and security do not reach.
22 skills · 1 agent
Skills for evidence-led product management and go-to-market: switch interviews, cheap demand tests, design partners, premortems, pricing and discount control, metric diagnostics, activation, churn and dunning, win-loss, RFPs, proofs of concept and support-driven fixes.
22 skills · 1 agent
Skills for Linux and systems administration: systemd units, boot failures, kernel updates and crashes, disks and volumes, the OOM killer, load and resource limits, permissions (SELinux, AppArmor), cron and timers, DNS, firewalls, MTU, packet captures, TLS and private CAs, SSH and lockout recovery, and time sync.
21 skills · 1 agent
Skills for database engineering in depth: PostgreSQL and MySQL internals, locks, deadlocks and vacuum, connection storms and failover, partitioning, search engines, vector indexes, ClickHouse, time series, Redis and SQLite.
20 skills · 1 agent
Skills for embedded, IoT and hardware-adjacent software: safe firmware updates and fleet rollouts, provisioning and device trust, device clocks and telemetry, field-failure triage, firmware code review, hard faults, RTOS concurrency and watchdogs, brick recovery, power and sleep bugs, memory and flash budgets, and bus, radio and MQTT debugging.
20 skills · 1 agent
Skills for marketing, growth and content operations: content SEO and programmatic pages, email authentication, warm-up and deliverability, lifecycle sequences, campaign tagging and preflight, attribution and paid-search waste, lead quality, landing-page message match and low-traffic tests, customer stories, community health and moderation, and developer relations.
20 skills · 1 agent
Skills for recurring problems in language ecosystems: Python packaging, imports, memory and typing, Node modules and memory, TypeScript strictness, Go, the JVM, .NET, C and C++ sanitizers, linking and core dumps, and unsafe Rust.
20 skills · 1 agent
Skills for observability engineering: trace sampling and broken-trace hunts, latency histograms, cardinality and log cost, collector pipelines and backpressure, semantic-convention upgrades and migrations, telemetry redaction, continuous profiling, alert backtesting and business-metric alerts, dashboards and synthetic checks.
20 skills · 1 agent
Skills for freelancing and small-business operations: quoting work, scope control, invoicing and late payment, contract checklists, bookkeeping and tax-deadline preparation. Procedure, not professional advice.
20 skills · 1 agent
Skills for scientific and research engineering: reproducible analyses, numerical precision, HPC jobs, large datasets, benchmarking methodology and statistical review.
19 skills · 1 agent
Skills for the design of a product's interface: review a screen or flow against usability heuristics, audit a page against WCAG 2.2 Level AA, set up design tokens, themes and component states, plan a small usability test with real people, write and review interface copy, structure a site's navigation and taxonomy, spec a design for build, and set the visual hierarchy, the responsive layout and the forms a screen is built from.
16 skills · 1 command · 1 agent
One development workflow, from a vague request to a measured outcome: Frame, Architect, Make, Inspect, Launch and Yield, with a profile skill for a solo developer, a developer, a QA engineer or a whole team, and a subagent for each stage.
11 skills · 1 command · 6 agents
Skills for learning, teaching and knowledge work: ramping up on a domain or a technology, study and exam plans, workshops and exercises, mentoring and pairing, capturing tacit knowledge, measuring whether training worked, and reading, reproducing and scanning research.
16 skills · 1 agent
Skills for building features on language models: ground an answer in your own documents with retrieval, get structured output a program can trust, build and review an MCP server, migrate a feature to a new model without a silent regression, extract data from images and scans, choose between a single call, a workflow and an agent, design agent memory and context compaction, run bulk jobs in batch, build and measure classifiers, budget latency, survive provider outages, calibrate output filters and shape tool results.
15 skills · 1 agent
Skills for backend and distributed-systems correctness: webhooks, transaction races, timeout and retry budgets, overload protection, rate limiting, distributed locks, sagas, event schemas, consumer lag, hot partitions, scheduled jobs, GraphQL query cost and gRPC runtime failures, and search index sync.
14 skills · 1 agent
Skills for getting a change into production without a bad night: separate deploy from release so the worst case is one cohort and one flag, ship a schema change to a live database without a stuck lock, run a cutover that has a point of no return, plan a platform migration that changes one thing at a time, audit a CI/CD workflow's own definition for what an attacker can reach through it, and write release notes someone can act on.
12 skills · 1 agent
Skills for keeping public and developer documentation true: clean-room tutorials, tested samples, drift detection, stable URLs, error catalogues, API diff gates, search vocabulary, terminology, CLI reference and accessibility conformance reports.
12 skills · 1 agent
Skills for quality engineering and compliance procedure: order-dependent tests, mutation, property and fuzz testing, traffic replay, load tests, DPIAs, licence obligations, audit evidence, risk acceptance and audit trails, as procedure rather than legal advice.
11 skills · 1 agent
Skills for the working side of a career: tailor an application from a real history without embellishment, negotiate an offer you would actually accept, take a talk from idea to delivery, turn experience into a publishable article, and keep notes on what you read that are still useful in a year.
11 skills · 1 agent
Skills for developer tooling and build systems: recovering and purging git history, repairing rebases, dependency conflicts and phantom dependencies, build cache misses and slow builds, affected-only monorepo builds, partial-release recovery and benchmark methodology.
10 skills · 1 agent
Skills for the parts of life that are nobody's job: understand where the money actually goes and model a decision before making it, plan a trip around the constraints that break trips, get through a bureaucratic process without a second attempt, decide on a large purchase you will live with for years, change a habit in a way that survives a bad week, review the week honestly, trace a family through records rather than stories, and eat in a way that matches the goal.
8 skills · 2 agents
Infrastructure as code usage: evolve shared Terraform module contracts, build meaningful module regression tests, and promote reviewed plans through a controlled apply pipeline. Existing state repair, adoption, upgrades and security review stay with their specialist skills.
3 skills · 1 agent