Coding & Development
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
$ npx skills add rpulid/skillsdesign-forge
Use when the user wants a product interface discovered, compared across real visual directions, decided with them, specified, built in the project, and checked against the approved look. Triggers include /design-forge, design forge, DESIGN FORGE, 디자인 포지, 시안 비교, 디자인 방향, a new screen, a redesign, or visual QA of an implemented UI. Skip a one-line copy fix, backend-only work, and an architecture design document.
$ npx skills add oth54477/design-forgetest-feature
Generate, run, and verify production-grade tests for a Python feature in any repository. Use when the user asks for tests for a feature, coverage of edge cases, regression tests, or robustness before deploying: "write tests for this feature", "hazme tests para esta feature", "test this endpoint", "cubre los edge cases", "tests antes de producción". Discovers the project stack from the repo, designs risk-based coverage, writes executable pytest/unittest code, runs it, and proves the suite catches regressions with a mutation gate. Not for non-Python projects, not for explaining testing theory, and never fixes production code.
$ npx skills add fer-prieto/opencode-skill-test-featuremicro-project-tutor
Teaches any programming language, framework, or tool through micro-projects instead of quizzes. Assesses the student's level by reading code they write, designs a short curriculum where each micro-project teaches exactly one concept and builds a real piece of a real end goal, then gives code-review style feedback. Use whenever the user asks to learn or practice a language, framework, or tool ("teach me Python", "CSS session", "let's do some JS", "I want to get better at React"), or pastes code from something they are building in order to learn. Never uses Q&A blocks or multiple-choice questions.
$ npx skills add dbdg64/micro-project-tutorstm32-firmware
STM32 firmware development with STM32CubeMX / STM32CubeIDE + HAL/LL and with PlatformIO — project structure and USER CODE rules, peripherals (UART/I2C/SPI/ADC/timers/DMA), clocks, low power, flash/option bytes, building from the command line, flashing and debugging with ST-Link (STM32CubeProgrammer CLI, OpenOCD, GDB, SWV), and HardFault analysis. Use this skill whenever the user works on any STM32 / Nucleo / Discovery / Blue Pill board, a `.ioc` file, CubeMX/CubeIDE, HAL_ functions, ST-Link, or sees a HardFault — even if they just say "o meu STM32 não arranca" or paste a HAL call. Use together with embedded-c-cpp for general C/C++ quality, testing and architecture.
$ npx skills add budenga/firmware-skillskit:web-frameworks
Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching strategies, shared dependencies.
$ npx skills add darrenak403/kit-skillsesp32-firmware
ESP32 firmware with PlatformIO — Arduino framework (primary) and ESP-IDF (also inside PlatformIO, or Arduino as an IDF component) — for ESP32, S2, S3, C3, C6. Covers platformio.ini setup, Arduino core 2.x vs 3.x API differences, safe pin selection (strapping/flash/PSRAM/ADC2 pins), FreeRTOS tasks and ISRs, memory/PSRAM, Wi-Fi/BLE, NVS/Preferences, OTA, deep sleep, partitions, flashing over USB/serial, decoding Guru Meditation panics and boot loops. Use this skill whenever the user works on any ESP32 / ESP32-S3 / C3 / C6 board, platformio.ini with espressif32, Arduino sketches for ESP32, idf.py/sdkconfig, or pastes ESP32 serial output (rst:, Guru Meditation, Brownout, watchdog) — even if they only say "a placa reinicia" or "o upload falha". Use together with embedded-c-cpp for general C/C++ quality, testing and architecture.
$ npx skills add budenga/firmware-skillsqa-audit
Evidence-first QA audit of a web app or API. Maps what to test, tests it with isolated agents against a coverage ledger (functional, design and UI/UX, accessibility, performance, code quality and non-invasive security hygiene), independently reproduces every bug, fixes each one behind a failing regression test, verifies fixes with a separate agent, and reports a release verdict. Use for "QA this app", "find and fix bugs", "check it matches the design", "make sure X works before launch", "run a QA pass", or a single broken flow.
$ npx skills add TGod-Ajayi/qa-audit-skillsecure-app-scaffolder
Use when starting, scaffolding or re-architecting a web application that must be secure-by-design (ANSSI/CIS/FBI/OWASP ASVS), or when adding auth, authorization, uploads, audit logging, admin features, Docker/Podman deployment or MCP endpoints. Produces a rootless TypeScript frontend + Python backend + hardened PostgreSQL stack with zero-trust input, object-level authorization, column-level encryption, idempotent writes, OIDC/LDAPS/WebAuthn, tamper-evident audit logs, honeytokens, signed images, dual scanning (Trivy + OpenSCAP) and a pre-production cleanup procedure.
$ npx skills add SkouedLabs/SkouedSkillsdotnet-8-to-10-migration
Plan and carry out a .NET 8 → .NET 10 migration of a repository or monorepo, safely and in reviewable steps. Analysis mode: environment preflight, project graph, migration groups, shared libraries to multi-target, baseline build/test, a reversible net10.0 experiment in a throwaway git worktree, and an ordered plan (JSON + Markdown report). Implementation mode: migrates ONE approved group in a disposable worktree with at most three recipe-defined repairs and a final gate, and returns a patch for human review (or rolls back). Use this whenever someone wants to plan, assess, scope, de-risk or perform an upgrade of .NET 8 projects to .NET 10 (or "the latest LTS"), asks what will break, which projects to migrate first, how to split a big solution into batches, or wants a group migrated — even if they just say "upgrade our dotnet repo". It never edits the repository itself, commits, pushes or opens pull requests. Not for .NET Framework → .NET migrations or vulnerability/package-...
$ npx skills add DmytroFlakac/dotnet-migration-skillhtml-to-pptx
Convert an HTML slide deck (one `.slide` div per slide, 1280x720) into a NATIVE, fully editable PowerPoint — real rectangles, rounded boxes, pills, circles, lines, arrows, freeform shapes, bullets, curved text and text boxes, NOT slide images. Use whenever the user says "make a PowerPoint of this HTML", "convert the deck to ppt", "I need it editable in PowerPoint", "don't just put images in PowerPoint", or hands over an HTML deck / HTML slideshow that must become a .pptx. Works on any brand.
$ npx skills add ImperaBusinessServices/html-to-pptxastro-ui-patterns
Implement Astro interaction patterns such as navigation, dialogs, tabs, filters, cards and theme switching. Reuse framework primitives while preserving each pattern’s behaviour contract.
$ npx skills add gdcrosbie/agent-skillsRobTF9/sql-helper
Write and explain SQL queries for a Postgres database.
$ npx skills add RobTF9/skill-grouping-demo-2RobTF9/code-review
Review a pull request for correctness, safety, speed and readability.
$ npx skills add RobTF9/skill-grouping-demo-2ko-system/forms-validation
Accessible forms with react-hook-form, zod and shadcn/ui Form, covering inline errors, pending and disabled states, success feedback and server-side validation with shared schemas.
$ npx skills add ko-system/kodra-skillsaliagenttucuman-byte/dev-kit-react-testing
Testing profesional de aplicaciones React: Vitest para unidades y hooks, React Testing Library para componentes con criterio de queries por rol, MSW para mockear red a nivel de API, Playwright para end-to-end, cobertura de interacciones reales, cobertura de componentes y los limites de cada nivel. CARGAR cuando hay que escribir tests de una interfaz, decidir que mockear, configurar Vitest o Testing Library, montar un componente o escribir un flujo end-to-end.
$ npx skills add aliagenttucuman-byte/dev-agent-skillssuper-xman/light-aaa-web-game
Build and verify lightweight, visually ambitious 3D Web games using Three.js/WebGL2, procedural geometry and materials, synthesized audio, and compact gameplay systems. Use when the user requests a small single-file browser game, an offline HTML 3D game, AAA-style Web graphics, procedural game assets, or size/performance optimization of such a game. Includes rendered visual validation, gameplay checks, and honest hardware performance gates. Not a promise of commercial AAA content scale.
$ npx skills add super-xman/skill-labaagzamov-dev/engineering-review
Review software changes, diagnose bugs with evidence, and assess regressions, lifecycle failures, permissions, feature flags, performance, and test coverage. Use for requested code reviews, difficult bug investigations, and the final review of substantial implementation work. Scale to the changed behavior; do not turn routine edits into whole-project audits or edit during a review-only request.
$ npx skills add aagzamov-dev/agent-workflow-skillsShortArrow/library-design
Designing a library — a published package, or an in-app module from the moment it has a second consumer. The implementation stays editable forever, while the public API, the dependency set, the performance characteristics and every observable behaviour freeze at first external use (Hyrum's law). Five duties to the caller: take no control, add no hidden cost (zero-cost abstraction as the bar), hold no hidden state, hide no failure, block no escape. Use when designing or reviewing a public API, when extracting shared code into a module, when asked to "make this reusable", when a signature-compatible change alters an observable behaviour, and when an application is being shaped around a framework's types and lifecycle.
$ npx skills add ShortArrow/skillskhiyarusa/performance-optimization
Finds and fixes game frame-rate problems by measurement in Godot, Unity, Unreal or Roblox: CPU- vs GPU-bound, then the biggest fix (draw calls, pooling, GC spikes). Use for low FPS, stutter, a first-use hitch, or requests to optimize or profile. Not for build size (`unity-build-size`), physics jitter (`physics-tuning`) or network lag (`roblox-networking`, `godot-multiplayer`).
$ npx skills add khiyarusa/farmanShortArrow/test-design
Deriving test cases, triggered by the moments that produce weak ones: about to write a test list that is the happy path restated, about to derive tests by reading the implementation they check, about to test the bound the specification names and not the other one, about to enumerate the roles the specification lists and skip the caller it forgot, about to vary one condition at a time from the happy path, about to draw a state or decision table without tying each row to a test, about to write an expected result with "or" in it, about to skip the error paths as unlikely, about to leave a path unimplemented and untested, or about to grade a suite as adequate by reading it. A test derived from the implementation passes by construction; coverage counts classes, not tests. Use when writing a test plan or list, when a use case is the specification in hand, when adding tests to existing code, when reviewing a suite for gaps, and when a suite is all green and proves little.
$ npx skills add ShortArrow/skillslokeshrana9999/llm-scan
Find every place a repo calls an LLM and write a route map (routes.json). Use when the user says "audit my LLM usage", "why is my LLM bill high", "make my LLM calls faster", "where do we call the model", "map our LLM calls", or starts any LLM cost or latency review. Run this first; llm-capture and llm-diagnose need its output.
$ npx skills add lokeshrana9999/llm-cost-skillsRIJUDEVx/interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "second opinion", "second look", "2nd opinion", "what could this break", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles; only findings a run proves survive.
$ npx skills add RIJUDEVx/agent-skillsdanielsegg/code-review-checklist
Revisar diffs, commits, branches, Pull Requests e alterações locais com foco em defeitos, regressões, segurança, desempenho, testes e manutenibilidade. Usar quando Codex precisar realizar revisão ou auditoria de código, avaliar a qualidade de uma mudança, fornecer feedback técnico ou definir critérios de aprovação, especialmente em projetos PHP/CakePHP e aplicações web.
$ npx skills add danielsegg/minhas-skills