agentsclimarketplace

Architecture & codebase

12,711 rows, by stacks then stars

1,011 of these skill files have been read, by 858 distinct authors, and what they tell an agent counted. What Architecture & codebase authors agree on, and what they forbid

  • Setup pre commit

    kjuhwa/skills-hub/skills/cli/setup-pre-commit Skill

    0★ repo

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

  • Generated enum and config code from json schema

    kjuhwa/skills-hub/skills/codegen/generated-enum-and-config-code-from-json-schema Skill

    0★ repo

    Build-time code generator that reads a JSON content-type knowledge base and emits per-language type-safe enums + const TypeInfo structs (MIME type, group, extensions, is_text).

  • Strict pydantic config with suggestions

    kjuhwa/skills-hub/skills/configuration/strict-pydantic-config-with-suggestions Skill

    0★ repo

    Forbid unknown fields on every config model and reject misspellings with a "did you mean ..." suggestion drawn from difflib.get_close_matches, while stripping whitespace from all string values automatically.

  • Yaml config with templated dynamic paths

    kjuhwa/skills-hub/skills/configuration/yaml-config-with-templated-dynamic-paths Skill

    0★ repo

    Load experiment config from YAML, then auto-resolve dependent paths via templates like "{base}/{exp_name}/tokenizer/best_model" unless the user overrides.

  • Model config min json compact format

    kjuhwa/skills-hub/skills/data/model-config-min-json-compact-format Skill

    0★ repo

    Distribute model config as compact JSON (config.min.json) alongside the .onnx file so package size stays small and parsing is universal.

  • Hexagonal architecture visualization pattern

    kjuhwa/skills-hub/skills/design/hexagonal-architecture-visualization-pattern Skill

    0★ repo

    Render the hexagon with domain core centered and ports/adapters radiating outward through driving/driven lanes

  • Idempotency visualization pattern

    kjuhwa/skills-hub/skills/design/idempotency-visualization-pattern Skill

    0★ repo

    Visual patterns for demonstrating idempotency guarantees through request replay, key-based deduplication, and state convergence animations.

  • Claude code skill scaffold

    kjuhwa/skills-hub/skills/devops/claude-code-skill-scaffold Skill

    0★ repo

    [Tooling] Claude Code 스킬 표준 구조(SKILL.md + prompts/ + scripts/ + references/)를 자동 생성하는 스캐폴딩.

  • Launchd shell env bootstrap

    kjuhwa/skills-hub/skills/electron/launchd-shell-env-bootstrap Skill

    0★ repo

    Electron apps launched from Finder/Dock on macOS inherit a minimal launchd PATH — spawn the user's login+interactive shell, parse its env, merge it into process.env so brew/nvm/pyenv work for the agent.

  • Architecture decision

    kjuhwa/skills-hub/skills/engineering/architecture-decision Skill

    0★ repo

    Creates an Architecture Decision Record (ADR) documenting a significant technical decision, its context, alternatives considered, and consequences. Every major technical choice should have an ADR.

  • Architecture review

    kjuhwa/skills-hub/skills/engineering/architecture-review Skill

    0★ repo

    Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL verdict. The architecture equivalent of /design-review.

  • Create architecture

    kjuhwa/skills-hub/skills/engineering/create-architecture Skill

    0★ repo

    Guided, section-by-section authoring of the master architecture document for the game. Reads all GDDs, the systems index, existing ADRs, and the engine reference library to produce a complete architecture blueprint before any code is written. Engine-version-aware: flags knowledge gaps and validates decisions against the pinned engine version.

  • Setup engine

    kjuhwa/skills-hub/skills/engineering/setup-engine Skill

    0★ repo

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

  • Tech debt

    kjuhwa/skills-hub/skills/engineering/tech-debt Skill

    0★ repo

    Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.

  • Test setup

    kjuhwa/skills-hub/skills/engineering/test-setup Skill

    0★ repo

    Scaffold the test framework and CI/CD pipeline for the project's engine. Creates the tests/ directory structure, engine-specific test runner configuration, and GitHub Actions workflow. Run once during Technical Setup phase before the first sprint begins.

  • Tauri cors origins setup

    kjuhwa/skills-hub/skills/fastapi/tauri-cors-origins-setup Skill

    0★ repo

    Allow a FastAPI backend to accept requests from the full range of Tauri webview origins on macOS, Windows, and Linux, plus Vite dev.

  • Menu key config registry

    kjuhwa/skills-hub/skills/frontend/menu-key-config-registry Skill

    0★ repo

    Centralize sidebar/drawer menu keys as a union type + config object per domain, so menu rendering, drawer view switches, and default-expand state all reference the same source of truth. Eliminates string-key drift across the three places a menu key appears.

  • Ort crate onnx runtime session configuration

    kjuhwa/skills-hub/skills/inference/ort-crate-onnx-runtime-session-configuration Skill

    0★ repo

    Configure ONNX Runtime via the ort crate's session builder: inter/intra threads, optimization level, parallel execution, embedded model bytes.

  • Mcp multi transport config pydantic

    kjuhwa/skills-hub/skills/integration/mcp-multi-transport-config-pydantic Skill

    0★ repo

    Single Pydantic config that supports three MCP transports (stdio, sse, streamable-http) with per-transport required-field validation in a model_validator(after) so users get a clear error when the wrong combination is set.

  • First occurrence config print with set memo

    kjuhwa/skills-hub/skills/jit-compilation/first-occurrence-config-print-with-set-memo Skill

    0★ repo

    Print a JIT-selected config the first time a given shape/desc is encountered, memoizing with `std::unordered_set<std::string>` keyed on the stringified descriptor — so each unique workload prints exactly once.

  • Bubblewrap namespace sandbox config

    kjuhwa/skills-hub/skills/linux-sandbox/bubblewrap-namespace-sandbox-config Skill

    0★ repo

    Build a bwrap invocation with a JSON-driven mount config (RO binds, RW binds, disabled defaults). Validates paths, blocks forbidden mounts, and enforces that RW mounts stay under $HOME. Merges user config over the default arg list.

  • Sandbox backend pluggable architecture

    kjuhwa/skills-hub/skills/linux-sandbox/sandbox-backend-pluggable-architecture Skill

    0★ repo

    Three-backend dispatcher (Host/Bwrap/KVM) with auto-detection priority and env override. Abstract base class defines the interface; concrete implementations handle isolation. Used to run untrusted subprocess workloads on Linux with progressive isolation.

  • Scaffold exercises

    kjuhwa/skills-hub/skills/misc/scaffold-exercises Skill

    0★ repo

    Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

  • Huggingface hub mixin for custom torch model

    kjuhwa/skills-hub/skills/ml-ops/huggingface-hub-mixin-for-custom-torch-model Skill

    0★ repo

    Give a custom nn.Module save_pretrained/from_pretrained plus HF Hub push/pull by multiple-inheriting from PyTorchModelHubMixin, with no HuggingFace config boilerplate.

  • Torchrun ddp training scaffold

    kjuhwa/skills-hub/skills/ml-ops/torchrun-ddp-training-scaffold Skill

    0★ repo

    Minimal torchrun + DDP scaffold with init/cleanup, per-rank seeding, model-size print, all_reduce aggregation, and rank-0-only logging and checkpointing.

  • Config json architecture dispatch

    kjuhwa/skills-hub/skills/model-loading/config-json-architecture-dispatch Skill

    0★ repo

    Auto-detect model version from config.json architecture field and dispatch to the correct model class

  • Effect ts monorepo with turbo and subpath exports

    kjuhwa/skills-hub/skills/monorepo/effect-ts-monorepo-with-turbo-and-subpath-exports Skill

    0★ repo

    Organize effect-based services in a monorepo using Turbo task pipelines and explicit subpath exports instead of barrel indexes

  • Nix electron resource path copy

    kjuhwa/skills-hub/skills/nix/nix-electron-resource-path-copy Skill

    0★ repo

    Copy the Electron ELF binary (not symlink) into a custom derivation tree so /proc/self/exe resolves to your tree. Merge app resources and Electron resources into one resources/ directory. Preserve the stock Electron wrapper for environment setup.

  • Lazy static once init pattern

    kjuhwa/skills-hub/skills/patterns/lazy-static-once-init-pattern Skill

    0★ repo

    lazy_static! for one-time initialization of expensive resources (codec choices, audio devices).

  • Cuda home discovery without torch init

    kjuhwa/skills-hub/skills/pytorch-integration/cuda-home-discovery-without-torch-init Skill

    0★ repo

    Discover CUDA_HOME at module import time without touching PyTorch's internal cuda-home helper, because in some versions it initializes CUDA — which then breaks subsequent `multiprocessing` forks.

  • Improve codebase architecture

    kjuhwa/skills-hub/skills/refactor/improve-codebase-architecture Skill

    0★ repo

    Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

  • Migrate to shoehorn

    kjuhwa/skills-hub/skills/refactor/migrate-to-shoehorn Skill

    0★ repo

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

  • Request refactor plan

    kjuhwa/skills-hub/skills/refactor/request-refactor-plan Skill

    0★ repo

    Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

  • Serde json config serialization

    kjuhwa/skills-hub/skills/serialization/serde-json-config-serialization Skill

    0★ repo

    serde_json for dynamic configuration serialization with schema validation via protobuf.

  • Version aware lora config selection

    kjuhwa/skills-hub/skills/training/version-aware-lora-config-selection Skill

    0★ repo

    Select the correct LoRAConfig class based on detected model architecture version at runtime

  • Model config versioning and backwards compat

    kjuhwa/skills-hub/skills/versioning/model-config-versioning-and-backwards-compat Skill

    0★ repo

    Embed major/minor version in model config.min.json; validate at load time; ship multiple model versions side-by-side under assets/models/<version>/ with a CHANGELOG.

  • Windows registry config storage

    kjuhwa/skills-hub/skills/windows/windows-registry-config-storage Skill

    0★ repo

    WinReg integration for app config storage (desktop shortcuts, printer settings).

  • Hexagonal architecture data simulation

    kjuhwa/skills-hub/skills/workflow/hexagonal-architecture-data-simulation Skill

    0★ repo

    Seed realistic port traffic with paired driving/driven adapter pairs and domain invariants that make violations visible

  • Idempotency data simulation

    kjuhwa/skills-hub/skills/workflow/idempotency-data-simulation Skill

    0★ repo

    Generating realistic duplicate-request streams, key-collision scenarios, and retry storms to stress-test idempotency implementations.

  • Setup deploy

    kjuhwa/skills-hub/skills/workflow/setup-deploy Skill

    0★ repo

    Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

  • Skill repo bootstrap architecture

    kjuhwa/skills-hub/skills/workflow/skill-repo-bootstrap-architecture Skill

    0★ repo

    Lay out a shared skill/knowledge git repo so it is simultaneously a catalog and a self-installer — separate bootstrap (commands + umbrella skill + installers) from skills (category/name/SKILL.md). Covers repo layout, safety gates, registry pinning, and skill deprecation lifecycle.

  • Investigate

    kevinxo328/agent-skills/skills/investigate Skill

    0★ repo

    Research an open question with discipline: verify-don't-assume → evaluate → report → exhaustively question. Use whenever the user is making a solution / architecture / setup decision — technology selection, architectural design, third-party option evaluation, configuration choices, feasibility studies, or breaking into an unfamiliar codebase. Triggers include: "investigate", "evaluate", "research", "how should we design X", "what should we use for Y", "is X viable".

    The same file is in 1 other repository

  • Ref sp dev projects architecture

    swiftpostlabs/agentic-tools/.agents/skills/ref-sp-dev-projects-architecture Skill

    0★ repo

    Shareable skills and tools for AI agents

  • Ref sp dev repo conventions

    swiftpostlabs/agentic-tools/.agents/skills/ref-sp-dev-repo-conventions Skill

    0★ repo

    Repo-specific conventions for this Python project (agentic-tools): the feature-first src/agentic_tools layout, pyproject.toml configuration hub, Black + Pyright-strict + pytest tooling via Poe, typing rules, CLI and script placement, and translations. Use when: creating or moving features, tests, or CLI entrypoints; deciding which top-level or package folder a file belongs in; adjusting pyproject.toml, Poe tasks, or tool config; or explaining how this repo is wired.

  • Triz refactor

    christianmerkwirth/triz-skills/skills/triz-refactor Skill

    no license0★ repo

    Refactors a module by applying a chosen TRIZ principle or auditing for ideality gaps.

  • Git setup skill

    fxckcode/skills-kit/skills/git-setup-skill Skill

    0★ repo

    Prepares Git/GitHub repositories with .gitignore, .gitattributes, README files, licensing, metadata, tags, releases, and GitHub Actions. Use when the user wants to set up or professionalize a repository, add documentation or licensing, configure CI, or prepare releases and repo metadata.

  • Swarm forge skill

    fxckcode/skills-kit/skills/swarm-forge-skill Skill

    0★ repo

    Sets up or refines repository AI workflow context across multiple CLI targets and four development patterns: TDD, BDD, ATDD, and SDD. Use when the user says things like "set up this repo for Claude Code", "set up this repo for Codex", "prepare the agent workflow", "add a TDD setup", "make this BDD-friendly", "set up ATDD", "set up spec driven development", or "review this project and scaffold the context files". It inspects the repo, chooses or confirms suitable CLI targets, setup patterns, and one of the four supported development patterns, asks only missing setup questions, runs bundled scaffold scripts when needed, and safely merges into existing project context files.

  • Vibedevteam init

    floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/vibedevteam-init Skill

    0★ repo

    批量创建 beads 任务并关联 TASK 文档。当用户需要初始化 Epic 的 beads 任务时使用。

  • React pdf kit setup

    react-pdf-kit/agent-skills/skills/react-pdf-kit-setup Skill

    0★ repo

    Set up @react-pdf-kit/viewer in a generic React app (>=2.0.0 <3.0.0) using the canonical RPConfig, RPProvider, RPLayout, RPPages provider chain.

  • React pdf kit worker config

    react-pdf-kit/agent-skills/skills/react-pdf-kit-worker-config Skill

    0★ repo

    Override the pdfjs-dist version and configure the PDF.js worker URL for @react-pdf-kit/viewer (>=2.0.0 <3.0.0) via the RPConfig workerUrl prop, with Vite, Next.js Turbopack, and webpack recipes. The default needs no setup.

  • Api contract

    LuchoC-Dev/agent-kits/skills/api-contract Skill

    no license0★ repo

    Define el contrato de la API — recursos, endpoints, estilo (REST/GraphQL/RPC), versionado, formato de request/response y de errores, paginación y filtrado. Trigger cuando el usuario quiera "diseñar la API", "definir endpoints", "contrato de API", "REST o GraphQL", "estructura de la API" o esté por implementar un backend sin el contrato cerrado.

  • Contract first

    LuchoC-Dev/agent-kits/skills/contract-first Skill

    no license0★ repo

    Disciplina contract-first / API-first — congelar el contrato de la interfaz (OpenAPI, schema, tipos compartidos) como fuente de verdad antes de implementar cualquier lado. Trigger cuando el proyecto tiene `contract-first` en las disciplinas activas, o el usuario pide "API-first", "contrato primero", "definir el contrato antes", "OpenAPI antes de codear", o hay cliente y servidor que deben acordar una interfaz.

  • Environment setup

    LuchoC-Dev/agent-kits/skills/environment-setup Skill

    no license0★ repo

    Configure and manage development, staging, production, and test environments. Use when setting up environment variables, managing configurations, or separating environments. Handles .env files, .env.test, config management, and environment-specific settings. Always use this skill when the user mentions env files, environment variables, .env.test, test environment config, or wants to separate environments — even if they just ask to "add a test env" or "configure testing variables".

  • Find docs

    LuchoC-Dev/agent-kits/skills/find-docs Skill

    no license0★ repo

    Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service -- even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer -- do not rely on training data for API details, signatures, or configuration options as they are frequently outdated. Always verify against current docs. Prefer this over web search for library documentation and API details.

    The same file is in 1 other repository

  • Information architecture

    LuchoC-Dev/agent-kits/skills/information-architecture Skill

    no license0★ repo

    Pregunta al usuario el modelo de navegación y las secciones principales antes de proponer un sitemap. Define rutas, jerarquía de contenido y flujo de entrada. Trigger cuando el usuario quiera "definir el sitemap", "armar la estructura de la app", "planificar las rutas", "information architecture" o haya completado el discovery y necesite organizar la app antes de diseñar pantallas.

  • Sdd init

    LuchoC-Dev/agent-kits/skills/sdd-init Skill

    no license0★ repo

    Initialize Spec-Driven Development context in any project. Detects stack, conventions, and bootstraps the active persistence backend. Trigger: When user wants to initialize SDD in a project, or says "sdd init", "iniciar sdd", "openspec init".

  • Service architecture

    LuchoC-Dev/agent-kits/skills/service-architecture Skill

    no license0★ repo

    Define el estilo arquitectónico (capas, hexagonal, clean, DDD táctico, microservicios), los módulos o servicios y sus límites, la comunicación entre ellos y dónde vive la lógica de dominio y el enforcement de reglas de negocio. Trigger cuando el usuario quiera "arquitectura del backend", "monolito o microservicios", "hexagonal", "clean architecture", "DDD", "estructura de módulos" o necesite decidir cómo se organiza el sistema.

  • Taskfile setup

    LuchoC-Dev/agent-kits/skills/taskfile-setup Skill

    no license0★ repo

    Creates or updates a Taskfile.yml and a docs/tasks.md for any backend project that uses Docker Compose for infrastructure and any build tool (Maven, Gradle, npm, pnpm, Poetry, Go, etc.). Use this skill whenever the user wants to set up task automation, create a Taskfile, configure project tasks, or when starting any new project that needs a standard set of commands. Also trigger when the user says "crear taskfile", "setup taskfile", "configurar tasks", "crear tasks", "necesito un taskfile", or asks how to run the project with a task runner. When in doubt, offer to set this up — projects without a Taskfile benefit from having one.

  • Operon setup

    Try-Operon/skills/operon-setup Skill

    0★ repo

    Walk a user through installing Operon and publishing their first AI skill, end-to-end. Drives the `operon` CLI on the user's behalf.

  • Private context bootstrap

    ArthurZakirov/OpportunityOS/skills/private-context-bootstrap Skill

    0★ repo

    Bootstrap private, remote-backed user context onto a fresh machine for opportunity workflows without committing personal data to public repositories.