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
Architecture refactor guidance
motao123/dev-workflow-kit/architecture-refactor-guidance Skill
1★ repoUse when the core problem is structural change: boundaries, coupling, module seams, interface extraction, or safe refactor sequencing. This skill helps decide how to reshape code without turning implementation into guesswork.
motao123/dev-workflow-kit/environment-config-audit Skill
1★ repoUse when the main risk is environment parity, config drift, secrets wiring, flags, defaults, or deployment-time assumptions rather than code logic itself.
spacemata/codex-plugins-for-claude-code/plugins/financial-markets/skills/user-context Skill
1★ repoStart onboarding, initialize, inspect, save, update, forget, export, or explicitly reset the Public Equity Investing plugin's local user context, source setup, or optional automation setup. Use when the user explicitly asks to get started, orient, or manage Public Equity Investing saved preferences, source pointers, context storage, or recurring automation.
Aws solutions architect professional
toddkasper/expert-skills/aws/skills/aws-solutions-architect-professional Skill
1★ repoDesigning and evaluating complex AWS architectures — multi-account AWS Organizations, hybrid and cross-account networking (Transit Gateway, PrivateLink, Direct Connect), business-continuity and DR design, migration and modernization strategy (the 7 Rs), and cost/resilience/performance trade-offs at enterprise scale. Use when making or reviewing enterprise AWS design decisions across organizational complexity, new solutions, continuous improvement, or workload migration. Not hands-on pipeline/IaC delivery (see aws-devops-engineer-professional) or security-control depth (see aws-security-specialty). Scoped and benchmarked by the AWS Solutions Architect – Professional (SAP-C02) blueprint.
toddkasper/expert-skills/salesforce/skills/salesforce-administrator Skill
1★ repoDay-to-day Salesforce org configuration — profiles, permission sets, OWD, sharing rules, FLS, the object/field data model, Flow automation, data import (Data Import Wizard, Data Loader), validation rules, duplicate management, reports, dashboards, and Agentforce admin setup. Use when configuring or reviewing declarative org settings, security/sharing, automation, or analytics. Not Apex/triggers/SOQL (see salesforce-platform-developer-1), advanced sharing architecture, deployment pipelines or auditing (see salesforce-advanced-administrator), or building AI agents (see salesforce-agentforce-specialist). Scoped and benchmarked by the Platform Administrator (Plat-Admn-201) blueprint.
Salesforce advanced administrator
toddkasper/expert-skills/salesforce/skills/salesforce-advanced-administrator Skill
1★ repoAdvanced declarative Salesforce administration — the full sharing/security model (role hierarchy, owner/criteria sharing rules, muting and session-based permission sets), complex Flow automation and order-of-execution debugging, custom object and relationship design (master-detail, junctions, DLRS roll-ups), data management (Data Loader, duplicate/matching rules, External IDs), sandbox strategy, SFDX deployment, and auditing/monitoring (Setup Audit Trail, Field History, Event Monitoring). Use when designing or debugging org config beyond day-to-day admin. Not basic setup (see salesforce-administrator) or Apex/code (see salesforce-platform-developer-1). Scoped and benchmarked by the Advanced Administrator (Plat-Admn-301) blueprint.
Salesforce technical architect
toddkasper/expert-skills/salesforce/skills/salesforce-technical-architect Skill
1★ repoEnd-to-end Salesforce architecture and trade-off design — multi-org strategy, security and identity (SSO, OAuth, JWT Bearer, SAML, FLS), enterprise data modeling and LDV, solution architecture across clouds, integration patterns (Named Credentials, Platform Events, Bulk/REST API, middleware), governor-limit-aware design, and development-lifecycle/deployment governance. Use when designing or reviewing cross-cloud architecture, integration pipelines, access models, or org strategy. Not single-cloud config or hands-on coding (see the cloud-consultant and platform-developer skills). Scoped and benchmarked by the Certified Technical Architect (CTA) review-board blueprint.
LFTPadilla/agent-dev-kit/plugins/dev-skills/skills/knip Skill
1★ repoFind dead code, unused files, unused exports, and unused dependencies in a JavaScript/TypeScript project using knip. Use before a refactor, before a PR, or when the user asks to clean up bloat, remove unused deps, or shrink the codebase.
0xkangl/skills/skills/agents-scaffold Skill
no license1★ repoScaffolds a multi-repo (polyrepo) workspace, adds web / server / client / custom modules to an existing one, or initializes a standalone single-repo project in place from one template. Sets up the spec-center SSOT plus per-module repos (or a single repo's in-repo specs/contracts) with shared CLAUDE.md conventions via a zero-dependency Node script.
0xkangl/skills/skills/codebase-audit Skill
no license1★ repoMulti-agent codebase audit / 代码库审计 spanning architecture, performance/scalability, code quality, security, testing, dependencies/debt, maintainability/observability, build/deploy/infra, and conventions compliance (against the code-conventions skill), plus conditional dimensions — frontend a11y/i18n on web stacks, per-endpoint-group interface audit(接口审计)when an HTTP service is detected, and per-business-flow audit(业务流程审计)whenever important flows are identified (any project type): scopes the target, fans out parallel auditors, adversarially verifies every finding to cut false positives, then synthesizes two standalone documents — 审计报告 + 按严重度问题汇总。只发现与整理问题,不产出修复方案;issues-report 可交下游 remediate-suggest skill 补推荐方案(完成时提示、不自动调用)。
jimtin/production-ai/skills/codebase-prune-review Skill
1★ repoReview an existing codebase for redundant, legacy, dead, superseded, or attack-surface-increasing code paths and guide progressive removal with behavior mapping, test coverage, security review, and validation. Use when asked to remove old providers or integrations, clean redundant code paths, reduce tech debt, reduce attack surface, review dead code, retire obsolete routes, remove stale compatibility layers, or clean up after migrations such as Google Drive uploads to Vercel Blob.
jimtin/production-ai/skills/full-app-review Skill
1★ repoOrchestrate a full non-mutating app or repo review across architecture, live flows, frontend quality, testing and coverage, security, observability and error instrumentation, analytics, dependencies, deployment, validation readiness, and redundant code paths. The default outcome is an evidence-backed, severity-ordered report plus a prioritized remediation plan — no mutations. Use when the user asks to fully review an app or repo, perform a full app review, app audit, production readiness review, end-to-end review, comprehensive codebase review, or asks what should be fixed before implementation, push, merge, or production. Not for single-dimension requests — route those to the relevant specialist skill directly.
jimtin/production-ai/skills/repo-testing-setup Skill
1★ repoDesign-then-execute setup of a repository's complete testing and security validation foundation. Containerized lanes for every test layer, canonical verify command, declared hook/gate enforcement model, repo-scoped secret scanning, dependency and image audits, deterministic provider stubs, deployment branch policy, repo-tracked testing inventories, pinned tool policy, and flake handling. Use after $clarify-before-build and $feature-design-preflight when a new project needs its testing approach designed, when a repo has no canonical containerized gate, when tests run on the host, or when security scanning is missing or mis-scoped. Use the short path to audit an adopted repo without mutation. Produces a confirmed Repo Testing Design, executes it, records rules in AGENTS.md/CLAUDE.md, and proves it with a green canonical gate. Not for writing feature tests or fixing individual failures; use $test-readiness-preflight.
vecten/sdlc-toolkit/skills/generate-skill Skill
1★ repoScaffold a new skill for the sdlc-toolkit plugin with config awareness, proper structure, and consistency with existing skills. Use when the user says "create skill", "new skill", "generate skill", "add a skill to sdlc-toolkit", or wants to turn a workflow into a reusable skill.
vecten/sdlc-toolkit/skills/migrate-cursor Skill
1★ repoMigrate workspace configuration, local skills, and rules from Cursor to Claude Code. Two-phase workflow: export in Cursor, import in Claude Code. Use when the user says "migrate cursor", "migrate from cursor", "import cursor config", "export cursor skills", or "switch to claude code".
dor-rondel/agent-skills-mcp/resources/frontend/nextjs-project-init Skill
1★ repoUse this skill when initializing a brand new Next.js web application from scratch. Covers pnpm setup, boilerplate structure configuration, quality tool validation, and writing the wildcard PR validation GitHub Actions workflow.
dor-rondel/agent-skills-mcp/resources/langgraph/langgraph-project-init Skill
1★ repoUse this skill when initializing a brand new Python LangGraph project from scratch. Covers installing uv, bootstrapping directories, generating the Makefile, configuring LangGraph Studio, and setting up the GitHub Actions CI workflow.
dor-rondel/agent-skills-mcp/resources/solidity/foundry-project-init Skill
1★ repoUse this skill when initializing a brand new EVM Solidity smart contract project using Foundry from scratch. Covers forge setup, structure scaffolding, and configuring the exact path-filtered GitHub Actions CI workflow.
leonhoffmann86/team-sprint/skills/update Skill
1★ repoUpdates the vendored Sprint chain in bootstrapped repos from the plugin source. Refreshes scripts, subagents, MCP config, and git hooks. Use --all to update every registered repo. Leaves configuration and lifecycle files untouched.
SylphxAI/skills/skills/architecture-convergence Skill
1★ repoDrive a substantial one-or-many-repository architecture rewrite onto shared invariants, a migration path, compatibility rules, and acceptance evidence. Use for real architecture convergence work. Not a local refactor, ordinary feature delivery, or pure process/delivery theater.
SylphxAI/skills/skills/product-lifecycle-architect Skill
1★ repoOrchestrate multi-domain product programs via dependency, handoff, validation, and delivery graphs when ~3+ lifecycle domains must converge. Not one app/game blueprint, marketing OS, or single campaign.
SylphxAI/skills/skills/prompt-architecture Skill
1★ repoDesign or audit durable agent instructions, runtime constitutions, Skill metadata, agent-to-agent and subagent briefs, bootstrap/install prompts, and instruction hierarchy without duplicating source policy. Use when creating, reviewing, projecting, or restructuring agent prompt architecture. Do not use for ordinary user-facing copy or one task's content brief alone.
SylphxAI/skills/skills/provenance-system-design Skill
1★ repoDesign provenance for artifacts, claims, builds, or content—lineage, attestation, verification, and disclosure. Use when provenance is the product concern. Not generic logging and not a one-line changelog note.
fxckcode/chatwoot-skills/skills/chatwoot-setup Skill
1★ repoSet up a Chatwoot account, configure agents, teams, inboxes, labels, roles, SAML SSO, and notification preferences. Use when the user needs to create or configure a Chatwoot workspace.
jiayx01/PhysisAI/plugins/physisai/skills/aise-setup Skill
1★ repo安装或初始化 PhysisAI,配置个人与项目两层本地记忆,并连接 Codex 或 Claude Code。用户说要安装、初始化、接入已有项目、升级旧版本,或第一次使用 AI 自进化时使用。
dimsedra/moatcraft-skills/.agents/skills/backend-architect Skill
1★ repoConduct a probing backend architecture discovery conversation to establish system boundaries, data models, API paradigms, performance/reliability moats, and architectural guardrails. Synthesize backend-architecture-spec.md as a version-controlled technical spec. Use when designing backend infrastructure, APIs, data systems, or server-side architecture. Do NOT use for visual design (use front-end-designer) or brand identity (use brand-product-alignment).
dimsedra/moatcraft-skills/.agents/skills/brand-product-alignment Skill
1★ repoConduct an engaging brand and product discovery conversation to extract positioning, hard boundaries, anti-patterns, and experience moats. Synthesize brand-product-alignment-spec.md as a version-controlled spec. Use when defining, aligning, or locking down brand and product identity before front-end design or backend architecture. Do NOT use for visual styling (use front-end-designer) or technical architecture (use backend-architect).
dimsedra/moatcraft-skills/.agents/skills/moatcraft-onboarding Skill
1★ repoOnboard new users into the Moatcraft workflow. Two jobs: (1) explain how the workflow operates, (2) integrate the workflow environment into the user's project upon explicit user request. Adapts to project state (clean slate / mid-development / workflow migration). Strict security boundaries: never read secrets, treat scanned prose as untrusted, require explicit consent for every setup action. Use when user asks to set up Moatcraft, asks how it works, or asks for help getting started. Do NOT auto-fire — this skill is user-initiated only.
Paldom/github-skills/skills/issue-pr-templates Skill
1★ repoBuilds structured GitHub contribution intake - YAML issue forms with required fields and auto-labels, config.yml routing, a pull request template with a working checklist, and starter labels like good first issue. Use when the user asks for issue templates, bug report forms, a PR template, or to stop blank issues. Not for CONTRIBUTING or other prose community files, and not for issue triage.
IvanGomezMartinez/MatStudyLab/.agents/skills/codebase-design Skill
1★ repoShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
The same file is in 19 other repositories
IvanGomezMartinez/MatStudyLab/.agents/skills/improve-codebase-architecture Skill
1★ repoScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
The same file is in 6 other repositories
IvanGomezMartinez/MatStudyLab/.agents/skills/matstudylab-bootstrap Skill
1★ repoCheck-on-use skills sync before workflow commands — not user-facing.
IvanGomezMartinez/MatStudyLab/.agents/skills/setup-matt-pocock-skills Skill
1★ repoConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
iurysza/agent-skills/skills/setup-goal Skill
1★ repoTurns an idea into an approved goal package under ai-artifacts. Use when work needs clarified intent, scope, accepted facts, an implementation plan, and an explicit handoff.
ksed8/cc-loopkit/.claude/skills/refactor Skill
1★ repoClean up dead code, reduce duplication, and simplify structure without changing behavior. Use when refactoring, removing dead code, reducing duplication, or simplifying structure without changing behavior.
FrancoisChastel/sydonia-toolkit/skills/customs-schema-setup Skill
1★ repoSet up, install, load, bootstrap or reset the Sydonia Toolkit ASYCUDA / SYDONIA PostgreSQL reference schema in a database. Creates the database, loads the schema then the reference seed then (optionally) the end-to-end example in the correct order, and reports a clean or failed result. Use when the user wants to stand up a customs sandbox, load the customs data model, or reset it.
Prepare agent compatible repository
lilabrooks/lila-agent-skills/skills/prepare-agent-compatible-repository Skill
1★ repoAudit, create, and reconcile repository instructions and agent-facing configuration so a project works consistently with Codex and Claude Code. Use when asked to add or review AGENTS.md, AGENTS.override.md, CLAUDE.md, CLAUDE.local.md, .claude rules or settings, .codex project configuration, shared Agent Skills packages, nested instruction scope, setup and verification commands, or cross-agent repository readiness. Keep shared rules in one place, preserve intentional host differences, and distinguish behavioral guidance from enforced controls.
Deadlymind/nanolama/skills/architecture-decisions Skill
1★ repoRecords an architecture decision as a numbered, immutable ADR under docs/adr — Status, Date, Context, Decision, Consequences, and the alternatives that lost — so the reasoning outlives the people who held it. Use when a choice is expensive to reverse or cross-cutting (Celery versus a cron, cookie JWT versus bearer tokens, one shared DB with a tenant FK versus schema-per-tenant), when a settled trade-off is being re-litigated in review, when superseding an earlier ADR, or when a PR needs a link to the reasoning behind it. Not for the commit message that carries the change (see commit-message) or the user-facing release notes (see changelog).
Deadlymind/nanolama/skills/codebase-guide Skill
1★ repoThe master map for building a feature end to end on this Django 5.2 / DRF 3.16 + Next.js stack — the model to serializer to ViewSet to urls/router to tests pipeline, every step tenant-scoped by the entreprise FK and gated by {resource}_{action} RBAC. Use when starting a new feature, adding an endpoint or app, onboarding to the conventions, asking "how is a feature built here" or "where does this go", or reviewing that a change follows house rules. Points to specialist skills for depth. Not for the deep mechanics of one layer — see multi-tenancy, drf-api, rbac-permissions, migrations, or write-tests for that.
Deadlymind/nanolama/skills/nextjs-module Skill
1★ repoStructures a Next.js 16 App Router frontend feature as layered modules (lib/api typed fetchers, query-keys, TanStack Query hooks, React 19 pages) fed by one shared fetch client that sends the auth cookie with credentials include, attaches the tenant header, and normalizes errors. Use when scaffolding a new frontend feature or module, building a fetch/apiClient wrapper, wiring cookie-JWT calls to the DRF backend, deciding where fetchers vs hooks vs pages live, or fixing a feature whose data layer is tangled. Not for the cookie-JWT plus CSRF auth seam itself — cookie flags, credentialed CORS, refresh rotation and logout revocation (see cookie-auth-csrf) — query cache config and useMutation invalidation depth (see react-query), form state and validation (see zod-forms), or designing the workflow and screens a module implements (see product-ux-design and visual-ui-design).
yigityildiz0/universal-ai-skill-library/skills/archive-variants/setup-writing-style Skill
no license1★ repoBuild a private, evidence-based writing-style profile from text the user explicitly provides, then test it on drafts without copying distinctive passages or.
yigityildiz0/universal-ai-skill-library/skills/common/api-design Skill
no license1★ repoAPI design principles for REST, GraphQL, and gRPC including versioning, pagination, error handling, and documentation. Use when designing new APIs.
yigityildiz0/universal-ai-skill-library/skills/common/architecture-design Skill
no license1★ repoSystem architecture design including requirements analysis, trade-off evaluation, ADRs, and system decomposition. Use when designing new systems, evaluating architectures, or documenting design decisions.
yigityildiz0/universal-ai-skill-library/skills/common/cicd-architect Skill
no license1★ repoCI/CD pipeline expertise for automated build, test, and deployment workflows. Use when setting up GitHub Actions, GitLab CI, Jenkins, or other CI/CD.
yigityildiz0/universal-ai-skill-library/skills/common/cloud-architect Skill
no license1★ repoMulti-cloud architecture expertise for AWS, Azure, and GCP. Use when designing cloud infrastructure, implementing Well-Architected Framework principles.
yigityildiz0/universal-ai-skill-library/skills/common/code-smell-detector Skill
no license1★ repoDetect and categorize code smells using Martin Fowler's catalog with severity scoring and refactoring recommendations. Use when reviewing code quality.
yigityildiz0/universal-ai-skill-library/skills/common/config-consistency-checker Skill
no license1★ repoDetects configuration drift and inconsistencies across environments by comparing dev, staging, and production configs, validating schemas, and reporting.
yigityildiz0/universal-ai-skill-library/skills/common/dead-code-eliminator Skill
no license1★ repoFind and safely remove dead code including unreachable functions, unused imports, obsolete features, and stale feature flags using static analysis and call.
yigityildiz0/universal-ai-skill-library/skills/common/design-pattern-suggestor Skill
no license1★ repoAnalyze code structure and recommend applicable GoF and modern design patterns with implementation guides. Use when code has structural problems, excessive.
yigityildiz0/universal-ai-skill-library/skills/common/design-taste-frontend Skill
no license1★ repoSenior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware.
yigityildiz0/universal-ai-skill-library/skills/common/event-driven-architecture Skill
no license1★ repoEvent-driven architecture patterns including event sourcing, CQRS, message brokers, and event schema design. Use when designing asynchronous systems.
yigityildiz0/universal-ai-skill-library/skills/common/framework-migration-assistant Skill
no license1★ repoGuide framework and library migrations (Express to Fastify, Angular to React, Spring MVC to Spring Boot, Django to FastAPI) with migration assessment.
yigityildiz0/universal-ai-skill-library/skills/common/human-architect-mindset Skill
no license1★ repoSystematic architectural thinking for irreplaceable human capabilities - domain modeling, systems thinking, constraint navigation, and AI-aware problem.
yigityildiz0/universal-ai-skill-library/skills/common/init-csharp-project Skill
no license1★ repoInitialize a complete C#/.NET project with solution structure, testing framework, and configuration. Use when starting ASP.NET Core APIs, console.
yigityildiz0/universal-ai-skill-library/skills/common/init-java-project Skill
no license1★ repoInitialize a complete Java project with Maven/Gradle build, testing framework, and standard structure. Use when starting Spring Boot applications, Maven.
yigityildiz0/universal-ai-skill-library/skills/common/init-javascript-project Skill
no license1★ repoInitialize a complete JavaScript/TypeScript project with package.json, testing framework, bundler configuration, and documentation. Use when starting.
yigityildiz0/universal-ai-skill-library/skills/common/init-python-project Skill
no license1★ repoInitialize a complete Python project with standard structure, pyproject.toml, testing framework, and documentation. Use when starting a new Python project.
yigityildiz0/universal-ai-skill-library/skills/common/notebooklm-prompt-architect Skill
no license1★ repoCreate high-quality, source-grounded NotebookLM prompts. Use when the user asks for NotebookLM, Notebook LM, notebook eleme/elemi/kalem prompts, chat.
yigityildiz0/universal-ai-skill-library/skills/common/observability-setup Skill
no license1★ repoObservability implementation including structured logging, metrics collection, distributed tracing, and alerting. Use when setting up monitoring.
yigityildiz0/universal-ai-skill-library/skills/common/prisma-database-setup Skill
no license1★ repoGuides for configuring Prisma with different database providers (PostgreSQL, MySQL, SQLite, MongoDB, etc.). Use when setting up a new project, changing.