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

  • System design review

    sandev/engineering-os/skills/design-and-architecture/system-design-review Skill

    0★ repo

    Run a structured review of a system or service design across scalability, reliability, security, cost, and operability. Use when the user shares an architecture, asks to review a system design, evaluate a proposed service, or pressure-test a design before build.

  • Using agent stack skills

    barry166/agent-stack-skills/skills/using-agent-stack-skills Skill

    0★ repo

    Use when a software-engineering request may match an Agent Stack Skills workflow, especially prompt refinement, unfamiliar or legacy project discovery, environment setup, safe refactoring preparation, complete legacy change delivery, or requests to find, list, recommend, or execute matching skills.

  • Seoauditor

    hannsxpeter/auditor-suite/plugins/seoauditor/skills/seoauditor Skill

    0★ repo

    Audit how the codebase makes a website visible to search engines and AI answer engines end to end (crawlability and indexation, rendering and content-in-HTML, on-page content and semantics, canonicalization, structured data, AI/generative-engine visibility, URL architecture and technical config, Core Web Vitals code signals, social metadata, internationalization, feeds and syndication, and SEO observability), write seoaudit.md (a scored, prioritized, self-contained report), then display the results in chat. Read-only: never crawls the live site, never runs Lighthouse, never calls Search Console or a model. Invoke with /seoauditor in Claude Code or $seoauditor in Codex.

  • Uiauditor

    hannsxpeter/auditor-suite/plugins/uiauditor/skills/uiauditor Skill

    0★ repo

    Audit how the codebase implements its user interface end to end (accessibility, semantic markup, styling architecture, component and UI-state correctness, responsive layout, frontend performance, design-system consistency, assets and media, internationalization readiness, and native/cross-platform UI), write uiaudit.md (a scored, prioritized, self-contained report), then display the results in chat. Read-only: never runs the app, never opens a browser, never takes screenshots, never mutates source. Invoke with /uiauditor in Claude Code or $uiauditor in Codex.

  • Seoauditor

    hannsxpeter/auditor-suite/skills/seoauditor Skill

    0★ repo

    Audit how the codebase makes a website visible to search engines and AI answer engines end to end (crawlability and indexation, rendering and content-in-HTML, on-page content and semantics, canonicalization, structured data, AI/generative-engine visibility, URL architecture and technical config, Core Web Vitals code signals, social metadata, internationalization, feeds and syndication, and SEO observability), write seoaudit.md (a scored, prioritized, self-contained report), then display the results in chat. Read-only: never crawls the live site, never runs Lighthouse, never calls Search Console or a model. Invoke with /seoauditor in Claude Code or $seoauditor in Codex.

  • Uiauditor

    hannsxpeter/auditor-suite/skills/uiauditor Skill

    0★ repo

    Audit how the codebase implements its user interface end to end (accessibility, semantic markup, styling architecture, component and UI-state correctness, responsive layout, frontend performance, design-system consistency, assets and media, internationalization readiness, and native/cross-platform UI), write uiaudit.md (a scored, prioritized, self-contained report), then display the results in chat. Read-only: never runs the app, never opens a browser, never takes screenshots, never mutates source. Invoke with /uiauditor in Claude Code or $uiauditor in Codex.

  • Gateway init

    gio-del/skills/skills/engineering/gateway-init Skill

    0★ repo

    Bootstrap the Gateway pattern in a root folder holding multiple independent project repos — creates GATEWAY.md, its CONTEXT.md vocabulary, and supporting ADRs, so /update-gateway and /new-project have something to operate on. Manual invocation only.

  • New project

    gio-del/skills/skills/engineering/new-project Skill

    0★ repo

    Scaffold a new Project folder at the Gateway root — git init it, register it in GATEWAY.md, and optionally link a remote (GitHub/Bitbucket/GitLab) with guided metadata. Manual invocation only.

  • Suno prompt architect

    frankxai/creator-skills/skills/music/suno-prompt-architect Skill

    0★ repo

    Expert Suno AI prompt engineering for professional music creation. Use this skill when creating Suno prompts for any AI-generated music that needs commercial quality.

  • Setup

    warpdotdev/client-release-agent-oss/.warp/skills/setup Skill

    0★ repo

    Set up the Client Release Agent end to end — clone the repo (or reuse an existing clone), verify required tools, create and fill in .env, and validate credentials. Use when the user asks to run the setup skill, or to set up, install, configure, or deploy the client release agent.

  • Loop system architect

    m1nga/skill-builder/skills/loop-system-architect Skill

    0★ repo

    Design, audit, repair, and operationalize reliable agent loops with explicit goals, triggers, persistent state, orchestration, independent verification, failure recovery, open skill discovery or creation, experience distillation, controlled self-improvement, and retirement conditions. Use when the user asks to build a loop, autonomous or recurring agent workflow, multi-agent operating system, self-improving process, knowledge/experience distillation pipeline, zero-context recovery flow, permanent update/replacement loop, or to turn a prose plan or repeated prompt into a genuinely executable loop.

  • Map product system

    m1nga/skill-builder/skills/map-product-system Skill

    0★ repo

    Turn rough product ideas, conversations, documents, or an existing codebase into an end-to-end product system map covering user journeys, capability boundaries, platform and customer mandates, data lifecycles, agent/service/human responsibilities, architecture, failure paths, governance, and delivery slices. Use when the user asks to understand the whole product, find missing functions or branches, establish product foundations, decide what belongs in code versus mandates or configuration, design multi-agent responsibilities, audit product completeness, or convert a product concept into an executable architecture. Trigger on phrases such as “看一下产品结构”, “梳理产品架构”, “检查用户旅程和功能分支”, “review the product structure”, or “map the whole product”.

  • Ai forge create

    robcsaszar/ai-forge/skills/ai-forge-create Skill

    0★ repo

    Claude Code skills covering the skill-authoring lifecycle — create, judge, eval with persisted regression suites, audit for ecosystem-wide coherence, review, and update

  • Architect

    yuri-semenenko/ai-engineering-workspace/codex/skills/architect Skill

    0★ repo

    Use for architectural decisions, RFCs, ADRs, system design, trade-off analysis, migration planning, and complex technical decisions that need Staff-level reasoning. Returns a structured recommendation rather than implementation code.

  • Codebase map

    yuri-semenenko/ai-engineering-workspace/codex/skills/codebase-map Skill

    0★ repo

    Use when orienting in an unfamiliar repo or subsystem, reviewing code you don't own, or preparing to work safely in a codebase you don't know yet. Produces a short, high-signal map: what it is, entry points, architecture, domain glossary, key seams, risky areas, and how to run and test — evidence over guesses.

  • Project onboarding

    yuri-semenenko/ai-engineering-workspace/codex/skills/project-onboarding Skill

    0★ repo

    Use when initializing, auditing, or updating a project's AGENTS.md, onboarding Codex to a repository, capturing repo-specific commands, or turning sparse project context into high-signal agent instructions.

  • Find docs

    DrOlu/agent-skills/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

  • Himalaya

    DrOlu/agent-skills/skills/himalaya Skill

    no license0★ repo

    CLI email client for IMAP and SMTP. Use when reading, searching, composing, sending, or managing email via terminal. Covers account setup, envelope listing, message reading, sending raw RFC 5322 messages, folder management, attachments, flags, and multi-account configuration.

  • Hyperframes cli

    DrOlu/agent-skills/skills/hyperframes-cli Skill

    no license0★ repo

    HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.

    The same file is in 1 other repository

  • Inngest cli

    DrOlu/agent-skills/skills/inngest-cli Skill

    no license0★ repo

    Use when installing or running the Inngest CLI and Dev Server for local development, local testing, serve endpoint debugging, Docker or Docker Compose setup, MCP configuration, self-hosted `inngest start`, or deployment workflow checks. Covers `inngest dev`, `inngest start`, auto-discovery, config files, environment variables, `@inngest/test`, local event sending, platform gotchas, and production/self-hosted server flags.

    The same file is in 1 other repository

  • Inngest setup

    DrOlu/agent-skills/skills/inngest-setup Skill

    no license0★ repo

    Use when adding durable execution to a TypeScript project — building retry-safe webhook handlers, background jobs that survive crashes, scheduled tasks, or long-running workflows that outlive a single request. Covers Inngest SDK installation, client config, environment variables, serve endpoints (Next.js, Express, Hono, Fastify), connect-as-worker mode, and the local dev server.

    The same file is in 1 other repository

  • Tailwind

    DrOlu/agent-skills/skills/tailwind Skill

    no license0★ repo

    Tailwind CSS v4.2 browser-runtime patterns for HyperFrames compositions. Use when scaffolding or editing projects created with `hyperframes init --tailwind`, writing Tailwind utility classes in composition HTML, adding CSS-first Tailwind v4 theme tokens, debugging v3 vs v4 syntax, or deciding when to compile Tailwind to CSS instead of using the browser runtime.

    The same file is in 3 other repositories

  • Codebase apprentice

    aoli0919/learn-anything-skills/skills/codebase-apprentice Skill

    0★ repo

    Use when a beginner wants to learn from a GitHub repository or codebase by turning it into a guided course, map, reading path, exercises, and project tasks.

  • Environment setup doctor

    aoli0919/learn-anything-skills/skills/environment-setup-doctor Skill

    0★ repo

    Diagnose setup problems, separate environment issues from concept issues, and provide fallback learning paths.

  • Robot sim starter

    aoli0919/learn-anything-skills/skills/robot-sim-starter Skill

    0★ repo

    Help beginners start with simulation before hardware by choosing tiny environments, fallback paths, and first motion demos.

  • Cloudflare email service

    K95M65/AI_ONBOARD/skills/cloudflare/cloudflare-email-service Skill

    0★ repo

    Send and receive transactional emails with Cloudflare Email Service (Email Sending + Email Routing). Use when building email sending (Workers binding or REST API), email routing, Agents SDK email handling, or integrating email into any app — Workers, Node.js, Python, Go, etc. Also use for email deliverability, SPF/DKIM/DMARC, wrangler email setup, MCP email tools, or when a coding agent needs to send emails. Even for simple requests like "add email to my Worker" — this skill has critical config details.

    The same file is in 1 other repository

  • Component scaffold

    K95M65/AI_ONBOARD/skills/component-scaffold Skill

    0★ repo

    Scaffolds a new React/TypeScript UI component (component + test + index) from a consistent template. Use when creating a new frontend component and you want the standard file layout without hand-copying boilerplate.

  • Develop test first

    K95M65/AI_ONBOARD/skills/develop-test-first Skill

    0★ repo

    Implements a known behavior change through a focused failing test, the smallest passing production change, and a verified refactor. Use when the user requests test-driven development, a known-cause regression-first bug fix, or new testable domain logic; do not use for unknown-cause diagnosis, behavior-preserving legacy characterization or refactoring, documentation-only work, generated artifacts, exploratory spikes, or UI polish whose value cannot be expressed as stable behavior.

  • Simplify code safely

    K95M65/AI_ONBOARD/skills/simplify-code-safely Skill

    0★ repo

    Simplifies existing code while preserving externally observable behavior, public contracts, and required performance. Use when reducing accidental complexity, removing dead or duplicated logic, clarifying control flow, shrinking an over-engineered change, or performing a focused behavior-preserving refactor; do not use for feature development, architecture replacement, or read-only code review.

  • Swift api design guidelines

    K95M65/AI_ONBOARD/skills/swift-api-design-guidelines Skill

    0★ repo

    Write, review, or improve Swift APIs using Swift API Design Guidelines for naming, argument labels, documentation comments, terminology, and general conventions. Use when designing new APIs, refactoring existing interfaces, or reviewing API clarity and fluency while preserving source compatibility requirements.

  • Swift architecture

    K95M65/AI_ONBOARD/skills/swift-architecture Skill

    0★ repo

    Evaluate MVVM, MVI, TCA, Clean Architecture, VIPER, MVP, Coordinator, and reactive patterns for SwiftUI or UIKit codebases. Use when designing, refactoring, or reviewing architecture; preserve the project's existing conventions and recommend a pattern only when its tradeoffs fit the scope, team, dependencies, and deployment targets.

  • Comvenio club onboarding

    Comvenio/comvenio-skills/skills/comvenio-club-onboarding Skill

    0★ repo

    Begleitet die strukturierte Ersteinrichtung eines Vereins mit dem Comvenio CLI: Profil, Einstellungen, Abteilungen, Mitgliedsstatus, Mitgliederimport, Teams, Gebäude, Objekte, Dateien und öffentliche Homepage. Verwende diesen Skill bei einem neuen Verein, Ersteinrichtung, Datenübernahme oder Onboarding.

  • Vibe design bootstrap

    nick3/vibe-design-skills/skills/vibe-design-bootstrap Skill

    0★ repo

    Coordinate the creation or reconstruction of a complete, reusable Vibe Design documentation foundation for a product. Use this skill whenever a team wants to standardize design work, bootstrap design documentation, rebuild standards from existing UI, start a design system for a new product, or prepare a project for Agent-assisted product and UI design. Do not use it for a routine single-screen design task when approved foundation documents already exist.

  • Mission init

    hashorva/purrfect-harness/.agents/skills/mission-init Skill

    no license0★ repo

    Bootstrap an orchestrated mission: create a dated folder under docs/missions/ with GOAL.md, features.json, PROGRESS.md, and the first WORKER_TASK from the repo's templates. MUST be used whenever the user says "start a mission", "new goal", "bootstrap the loop", "let's run the orchestration on X", or asks to begin orchestrated work of any kind. Also use to re-scope an existing mission. Produces files mechanically from docs/missions/templates/ — never freestyle the formats. Runs fleet-inventory at GATE 0 and always shows the seat→model map for human confirm/swap. Default chair is Opus (Cursor intake plans briefly; Opus weighs and orchestrates) unless the human names otherwise.

  • Refactor code

    JoaoAlavarse/cursor-config/skills/refactor-code Skill

    0★ repo

    Improves the internal structure, readability and maintainability of existing code while preserving its external behavior. Use when refactoring, cleaning up code, or reducing technical debt.

  • Architecture design

    ahtishamshahzad/agent_dev_flow/.ai/skills/architecture-design Skill

    0★ repo

    Use after the stack is approved to define module boundaries, data flow, integration points, and cross-cutting concerns (auth, config, error handling). Produces the architecture that phases and tasks are generated from. Proportional to the request.

  • Api contracts

    ahtishamshahzad/agent_dev_flow/.ai/skills/backend/api-contracts Skill

    0★ repo

    Use to define and maintain the API contract between backend and clients — OpenAPI/GraphQL schema as source of truth, shared/generated types, breaking-change policy, and contract-first workflow for new endpoints.

  • Backend api architecture

    ahtishamshahzad/agent_dev_flow/.ai/skills/backend/backend-api-architecture Skill

    0★ repo

    Use to define the internal architecture of a backend API — layering (transport/controllers/services/data), domain boundaries, where cross-cutting concerns live, and how modules communicate. Framework-agnostic; foundations apply it per framework.

  • Graphql api design

    ahtishamshahzad/agent_dev_flow/.ai/skills/backend/graphql-api-design Skill

    0★ repo

    Use to decide whether GraphQL fits and to design a GraphQL API — schema/type design, resolvers, N+1 protection (dataloaders), pagination (connections), mutations/errors, query cost limits, and field-level authorization.

  • Rest api design

    ahtishamshahzad/agent_dev_flow/.ai/skills/backend/rest-api-design Skill

    0★ repo

    Use to design a REST API surface — resource naming, HTTP methods and status codes, pagination, filtering, versioning, idempotency, and consistent response shapes. Produces an endpoint design, not code.

  • Environment management

    ahtishamshahzad/agent_dev_flow/.ai/skills/devops/environment-management Skill

    0★ repo

    Use to plan environment configuration across dev/staging/production — one immutable artifact configured by environment, validated typed env vars (fail fast at boot), no secrets in client bundles, and parity so behavior differs only by config. Secret storage itself is secrets-management.

  • Monorepo selection

    ahtishamshahzad/agent_dev_flow/.ai/skills/devops/monorepo-selection Skill

    0★ repo

    Use when a monorepo is chosen to pick the workspace/tooling — pnpm/npm workspaces alone vs adding Turborepo for task orchestration and caching — based on app count, build complexity, and CI needs. Evaluates rather than defaulting to the heaviest option.

  • Pnpm workspaces

    ahtishamshahzad/agent_dev_flow/.ai/skills/devops/pnpm-workspaces Skill

    0★ repo

    Use to plan a pnpm-workspaces monorepo — workspace layout, internal package linking (workspace protocol), dependency hoisting/isolation policy, versioning of shared packages, and lockfile/CI discipline. Configuration planning; does not scaffold apps.

  • Turborepo foundation

    ahtishamshahzad/agent_dev_flow/.ai/skills/devops/turborepo-foundation Skill

    0★ repo

    Use to plan a Turborepo setup after it's chosen — task pipeline definition (dependsOn), input/output declarations for correct caching, affected-only execution, and CI integration. Plans configuration; does not scaffold apps.

  • Environment audit

    ahtishamshahzad/agent_dev_flow/.ai/skills/environment-audit Skill

    0★ repo

    Use to assess environment and configuration health — env-var usage and fail-fast, config/secrets handling, build/runtime settings, and parity across dev/staging/prod. Flags exposure and missing validation without printing secret values.

  • Mobile environment config

    ahtishamshahzad/agent_dev_flow/.ai/skills/mobile/mobile-environment-config Skill

    0★ repo

    Use to plan mobile environment configuration — dev/staging/prod separation, env-var handling, base URLs and keys via config (not hard-coded), and safe client exposure. No secrets in the client bundle.

  • Refactor planning

    ahtishamshahzad/agent_dev_flow/.ai/skills/refactor-planning Skill

    0★ repo

    Use to plan a behavior-preserving structural improvement — audit the target, ensure test coverage exists, plan small reversible steps, and verify behavior is unchanged. Any intended behavior change is a feature, not a refactor.

  • Repository architecture

    ahtishamshahzad/agent_dev_flow/.ai/skills/repository-architecture Skill

    0★ repo

    Use after architecture design to define the on-disk repository layout — single-repo vs monorepo, app/package boundaries, directory conventions, and shared-code placement. Translates the logical architecture into a concrete, navigable structure. No application code.

  • Dashboard architecture

    ahtishamshahzad/agent_dev_flow/.ai/skills/web/dashboard-architecture Skill

    0★ repo

    Use to decide where an admin dashboard lives — inside the customer web app, as a route group, as a separate application, or in a separate repository — weighing user roles, deployment boundaries, security boundaries, team ownership, UI system sharing, and release cadence. Placement is a decision, not a default.

  • Architecture decisions

    lzx-Bill/Project-Factory-Core/.agents/skills/architecture-decisions Skill

    0★ repo

    Use when choosing architecture, comparing tech stack options, defining module boundaries, writing ADRs, documenting system design, or explaining major technical tradeoffs. Trigger when user says "architecture", "tech stack", "module", "ADR", "system design", "technical decision", "choose between A and B", "microservices vs monolith", or when moving from requirements to implementation design. Coordinate with research-spikes for unverified technical assumptions.

  • Data api design

    lzx-Bill/Project-Factory-Core/.agents/skills/data-api-design Skill

    0★ repo

    Use when modeling entities, writing schema docs, designing APIs, defining state machines, or keeping data and API contracts consistent. Trigger when user says "data model", "schema", "API design", "state machine", "entity relationship", "database schema", "API contract", "endpoint", or when moving from architecture to implementation-ready data contracts. Coordinate with architecture-decisions for module boundaries and with prompt-authoring for API consistency.

  • Incubation discovery

    lzx-Bill/Project-Factory-Core/.agents/skills/incubation-discovery Skill

    0★ repo

    Use when exploring a new project idea from many angles before writing formal requirements. Trigger when user says "brainstorm", "explore directions", "generate ideas", "opportunity map", "scenario options", "feature ideas", "creative direction", or when they want to "see what's possible" before committing to a specific scope. Only use after a project folder exists; for initial setup use project-bootstrap first.

  • Project bootstrap

    lzx-Bill/Project-Factory-Core/.agents/skills/project-bootstrap Skill

    0★ repo

    Use when starting a new Project Factory project. Trigger when user says "new project", "create project", "initialize", "start a new wiki", or mentions setting up a fresh project folder with HOME.md and wiki structure. Also use when scaffolding prompts/, acceptance/, tasks/, reports/ directories for an existing project.

  • Project setup

    Zwin-ux/kit/skills/project-setup Skill

    0★ repo

    Set up a clean project baseline for agents and humans.

  • Workspace setup

    Zwin-ux/kit/skills/workspace-setup Skill

    0★ repo

    Set up monorepo and multi-package workspaces for agents and humans.

  • Camoufox setup

    Paldom/stealth-browser-skills/skills/camoufox-setup Skill

    0★ repo

    Installs and verifies the Camoufox stealth-browser toolchain — the camoufox[geoip] pip package, its Firefox browser binary via `camoufox fetch`, and the playwright-cli agent skills. Use when Camoufox is missing or setup fails, e.g. 'set up camoufox', 'install the stealth browser', 'camoufox fetch failed'. Not for launching, resuming, serving, or detection-testing a browser.

  • Azpg config tuning

    lestermarch/postgres-ai-experts/skills/azpg-config-tuning Skill

    no license0★ repo

    Tune server parameters on Azure Database for PostgreSQL Flexible Server — memory (work_mem, maintenance_work_mem, shared_buffers, effective_cache_size), autovacuum aggressiveness, max_connections, statement/lock timeouts, and connection pooling with the built-in PgBouncer. Use this skill whenever the task involves changing a Postgres server parameter, "work_mem", "shared_buffers", "max_connections", autovacuum tuning, connection pooling / PgBouncer, statement_timeout, "az postgres flexible-server parameter set", a parameter that needs a restart, or "how do I make my server use more memory / handle more connections?" on Flexible Server. For finding WHICH query or table needs tuning first hand off to azpg-stat-diagnostics or azpg-explain-analyze; this skill changes the knobs.

  • Ic onboarding

    Immersive-commons/ic-skills/skills/ic-onboarding Skill

    0★ repo

    Set an agent's human user up on Immersive Commons end-to-end, explaining every step to them in plain English — mint a token, install + verify the MCP server, set their profile, EDUCATE them on everything IC offers, and file a quality tier-upgrade request. Use when the human says "set me up on IC", "connect me to immersive commons", "register my agent", "onboard me", "finish my IC setup", or hands you the verify URL. RFC 8628 device-code; two-phase because tiers are operator-approved. Official immersivecommons.com skill.

  • Dead code elimination

    dgabreuu/react-skill-pack/skills/dead-code-elimination Skill

    0★ repo

    Use when a React + Vite project needs an advisory scan for unreachable modules, unused imports or unreferenced dependencies before a manually reviewed cleanup.

  • Vite advanced config

    dgabreuu/react-skill-pack/skills/vite-advanced-config Skill

    0★ repo

    Use when auditing React Vite configurations for conservative static signals, development-server security, and Vite 7/Rollup versus Vite 8/Rolldown compatibility.