Architecture & codebase
12,712 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
Pocock improve codebase architecture
steph-frtech/cdesign-expo/.claude/skills/pocock__improve-codebase-architecture Skill
no license1★ repoFind deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
The same file is in 2 other repositories
itsjavi/skills/skills/find-docs Skill
1★ repoRetrieves 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the answer -- do not rely on training data for API details, signatures, or configuration options as they are frequently outdated.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.
itsjavi/skills/skills/setup-specs-workflow Skill
1★ repoCoding agent skills to help projects adopt spec-driven development with durable product memory documents
metallurgical/ogre-runner/skills/config Skill
no license1★ repoShow every .ai/.ogre/config.json key Ogre actually reads (dot path, current value/source, CLI override), or reset config.json back to fresh-install defaults.
hlsitechio/claude-skills-security/appsec-stack-pack/clerk-security Skill
1★ repoSecurity audit for applications using Clerk authentication including session management, webhook signature verification, JWT template configuration, organization/role setup, publishable vs secret keys, allowed origins/redirect URLs, custom session claims, and Clerk-specific patterns. Use this skill whenever the user mentions Clerk, @clerk/nextjs, @clerk/clerk-sdk-node, ClerkProvider, useUser, useAuth, clerkClient, Clerk webhooks, svix, or asks "audit my Clerk setup", "Clerk security", "is my Clerk webhook safe". Trigger when the codebase contains `@clerk/*` packages or `CLERK_*` environment variables.
hlsitechio/claude-skills-security/appsec-stack-pack/nextauth-security Skill
1★ repoSecurity audit for NextAuth.js / Auth.js applications including provider configuration, JWT vs database session strategy, callback safety (jwt, session, signIn, redirect), CSRF, NEXTAUTH_SECRET handling, OAuth client secrets, custom adapters, and Auth.js-specific patterns. Use this skill whenever the user mentions NextAuth, NextAuth.js, Auth.js, next-auth, @auth/core, authjs, NEXTAUTH_SECRET, [...nextauth].ts, providers, callbacks, signIn/signOut, or asks "audit my NextAuth setup", "Auth.js security review". Trigger when the codebase contains `next-auth` or `@auth/*` packages.
hlsitechio/claude-skills-security/appsec-stack-pack/nodejs-express-security Skill
1★ repoSecurity audit for Node.js HTTP servers using Express, Koa, Hapi, or plain http/https — covering middleware ordering, body parser config, helmet usage, session management with express-session, CORS configuration, error handling, file upload patterns (multer/busboy), and common Node-specific vulnerabilities like prototype pollution, ReDoS, and event loop blocking. Use this skill whenever the user mentions Express, Koa, Hapi, express-session, helmet, multer, body-parser, Node.js server, npm packages with known CVEs, or asks "audit my Express app", "Node.js security review", "is my Express middleware safe", "Koa security". Trigger when the codebase contains `require('express')`, `from 'express'`, `express()`, `new Koa()`, or similar Node HTTP server patterns.
hlsitechio/claude-skills-security/appsec-stack-pack/redis-security Skill
1★ repoSecurity audit for Redis usage including ACL configuration, network exposure (bind, protected-mode), TLS, command restrictions, key namespacing across tenants, EVAL/Lua sandbox safety, pub/sub leakage, persistence file protection, and client library patterns (ioredis, node-redis, redis-py). Use this skill whenever the user mentions Redis, redis client, ioredis, node-redis, redis-py, Lettuce, redis-cli, redis.conf, Lua scripts, EVAL, or asks "audit my Redis setup", "Redis security", "Redis ACL". Trigger when the codebase contains Redis client libraries or `redis://` connection strings.
hlsitechio/claude-skills-security/appsec-stack-pack/spring-boot-security Skill
1★ repoSecurity audit for Spring Boot Java/Kotlin applications including Spring Security configuration, @PreAuthorize/@Secured, JPA queries (@Query, JPQL injection), CSRF setup, CORS, actuator endpoints exposure, application.yml secrets, Jackson deserialization, and Spring-specific CVE awareness (Spring4Shell). Use this skill whenever the user mentions Spring Boot, Spring Security, @PreAuthorize, JpaRepository, application.yml/properties, actuator, @SpringBootApplication, or asks "audit my Spring app", "Spring Boot security review". Trigger when the codebase contains `pom.xml` or `build.gradle` with `spring-boot-starter`, or Java/Kotlin files with `@SpringBootApplication`.
viktor-milev/claude-skills/prompt-architect-fable Skill
1★ repoFable-variant prompt architect — classifies a task against a 10-bucket taxonomy with an execution-mode overlay (interactive vs. agentic), decides output architecture (single-turn vs. chained multi-stage), and produces a technique-grounded v1 draft prompt calibrated for Claude Fable 5, with surface-aware run settings (chat app, Claude Code, Cowork, harness). Verdicts are SINGLE-TURN, SINGLE-TURN (CEILING), or CHAIN (README + Project orchestrator + per-stage prompts). Fires ONLY on explicit Fable invocation — trigger phrases include "architect this for Fable 5", "help me prompt this for Fable", "draft a Fable 5 prompt for". Do NOT trigger on unqualified requests ("help me prompt this", "draft a prompt for") — those route to prompt-architect (Opus sibling). Do NOT trigger when a draft prompt already exists — that's prompt-optimizer-fable. Do NOT trigger for tasks covered by a dedicated domain skill — route to that skill instead.
viktor-milev/claude-skills/prompt-architect Skill
1★ repoClassifies a task against a 10-bucket taxonomy, decides output architecture (single-turn vs. chained multi-stage), and produces a technique-grounded v1 draft prompt. Verdicts are SINGLE-TURN, SINGLE-TURN (CEILING) with a strain note, or CHAIN producing a README + Project orchestrator + per-stage prompts. Use when you describe a non-trivial task but have no prompt written yet. Trigger phrases include "help me prompt this", "set up a prompt for", "draft a prompt for", "how should I ask Claude to", "architect a prompt for", "I'm about to start work on X — help me frame it". Also trigger for multi-step analytical tasks (research, knowledge document, design, decision support) where no draft exists. Do NOT trigger when a draft prompt already exists — that's prompt-optimizer. Do NOT trigger for tasks already covered by a dedicated domain-specific skill — route to that skill instead.
Surfrrosa/claude-skills/coupling Skill
1★ repoOrthogonality / module-coupling audit. Asks the Pragmatic Programmer's central orthogonality question — "if I change feature X, how many modules light up?" — and surfaces the answer with mechanical evidence. Finds circular imports, cross-layer architecture violations, centralization magnets (large file × high fan-in), hidden coupling via git file-co-change patterns, and wildcard / dead imports. Use as a periodic full-codebase sweep (monthly, or before launches that grow surface area), or after a wholesale architectural refactor.
AnaCataVC/amiga-ia/skills/ami-project-architect Skill
1★ repoInteractively sets up the initial architecture of a new project. It gathers requirements, researches technologies, proposes a stack and folder structure with constant user interaction, and finally scaffolds the initial files and a comprehensive README.md.
AnaCataVC/amiga-ia/skills/ami-tech-debt-scanner Skill
1★ repoAnalyzes the repository for technical debt, including outdated dependencies, dead code, duplication, and architectural inconsistencies. Provides a classified report based on criticality, effort, and risk.
longyenkai83/personal-marketing-kit/skills/6-meta/subagent-architect Skill
no license1★ repoBuild (scaffold) hoặc audit (review) custom Claude Code subagents theo spec chính thức tại https://code.claude.com/docs/en/sub-agents. BUILD mode hỏi 6 câu trong 1 message rồi sinh file .md đúng spec, ghi vào ~/.claude/agents/ hoặc .claude/agents/. AUDIT mode review file có sẵn theo 10 best-practice gate. Vietnamese-first. Use when user says "tạo subagent", "build subagent", "audit subagent file", "review my subagent", "scaffold agent for X", "convert prompt to subagent", or invokes /subagent-architect.
Fantasymax/easy-build-skills/skill/user-research-for-ai-config Skill
no license1★ repoCRITICAL: If user says "design/make a skill for X" / "我想做一个 XX 的 skill" / "帮我做个 AI 写 XX 的 skill" — DO NOT write it yourself, USE THIS SKILL to interview them first. That IS the purpose. Use for personalized AI config or custom skill via structured self-interview, not copying templates. Two outputs: (A) Principles — CLAUDE.md / AGENTS.md / .cursorrules / system-prompt for Claude Code / Cursor / Codex / OpenCode / Aider etc. (B) Custom skill — design from scratch OR extract recurring task; works whether user has a clear task or needs AI to discover one. Trigger: 我的 principles / 自己的 skill / 个性化 AI / 帮我设计一个 skill / 我想做一个 XX 的 skill / 让 AI 写 XX 的 skill / 把我会的事教给 AI / build my own CLAUDE.md / make a custom skill / design a skill from scratch / build a skill for X / AI that understands me. Do NOT use for customer research, product discovery, market research.
redwoodmeridian/ranql-skills/plugins/ranql/skills/ranql-onboarding Skill
no license1★ repoUse when the user wants to SAVE their firm details to Ranql so they don't re-enter them — "set up my profile", "onboard me", "get me set up", "remember my firm/competitors". This is OPTIONAL and never a prerequisite — the other skills (teardown, creative, etc.) run fine on info collected in the chat. Onboarding just persists that info. Prefer pointing the user to the one-time web onboarding at ranql.com/platform/onboarding; you can also save fields via update_my_profile.
punkaze/skills/plugin/skills/worktree-setup Skill
1★ repoUse when starting an isolated task that needs a git worktree on a NEW branch — any project. Triggers — "set up a worktree for X", "start a worktree for this task", "isolate this work in a worktree", or before a subagent-driven / executing-plans run on a repo not already in a linked worktree. Reads a per-project config (in-repo .worktree.json or a registry under $CLAUDE_PLUGIN_DATA/projects) to decide single vs dual/multi-repo scope (identical branch names on coupled repos), cut from the right base branch, copy env files, and run the right install command. No-op when no config matches and you are not asked to init one.
bromso/metapowers/plugins/marketing/skills/ab-test-setup Skill
1★ repoDesign A/B tests with hypothesis, measurement, and statistical rigor
bromso/metapowers/plugins/marketing/skills/onboarding-cro Skill
1★ repoOptimize user onboarding for activation and retention
bromso/metapowers/plugins/marketing/skills/site-architecture Skill
1★ repoPlan information architecture, URL structure, and internal linking strategy
bromso/metapowers/plugins/metapowers/skills/init Skill
1★ repoInitialize a .metapowers/ directory and configure active domains for a project
bromso/metapowers/plugins/project-management/skills/team-setup Skill
1★ repoDefine team roles, responsibilities, skills matrix, and working agreements
bromso/metapowers/plugins/security/skills/logging-architecture Skill
1★ repoPlan centralized logging, retention, and audit trail design
bromso/metapowers/plugins/security/skills/siem-setup Skill
1★ repoDesign SIEM architecture, correlation rules, and dashboards
adaptocms/adapto-cms-agent-skills/plugin/skills/adapto-install Skill
1★ repoBootstrap entry point for Adapto CMS. Ensures the `adapto` CLI is installed and at the supported baseline (consent-gated), then hands off to adapto:scaffold to create a new project. Run this first to get started or to install/upgrade the CLI.
adaptocms/adapto-cms-agent-skills/plugin/skills/adapto-microcopy Skill
1★ repoManage UI micro copy (nav, buttons, labels, errors) as Adapto key/value/language entries. Two modes — init seeds a curated, on-brand starter set; extract scans your frontend for hardcoded strings and creates entries + a replacement guide (no source rewrite). Plan-then-apply.
adaptocms/adapto-cms-agent-skills/plugin/skills/adapto-scaffold Skill
1★ repoCreate a new Adapto-ready frontend by wrapping `npx create-adapto-app` — choose a framework (Next/Astro/SvelteKit), scaffold the project (the Adapto read-client is included), and wire up `.env`. Consent-gated — shows the exact command and runs it only after you approve. New projects only.
HarishDvs/Grizzly/skills/grizzly-init Skill
1★ repoSet up a new Grizzly writing project. Use when the user wants to start using Grizzly on a novel, when no NOVEL.md exists in the project, or when the user asks to onboard an existing manuscript. Creates NOVEL.md, VOICE.md, STANDARDS.md and the codex scaffold through a guided interview.
qiaeru/skills-github/skills/scaffolding-repos Skill
1★ repoScaffold or refresh the generic files of the owner's public GitHub repos. Use when starting or normalizing a repo: install the generic .gitignore, the LF .gitattributes, a Keep a Changelog / SemVer CHANGELOG.md, and the Repo profile marker the other github skills read.
wawoodwa/context-kit-skills/skills/context-kit-scaffold Skill
1★ repoScaffold a portable, name-agnostic starter kit for the next project -- any stack (Node.js, Python, PowerShell, ops/admin) -- by mining this project's accumulated docs, conventions, runbooks, agent-testing harness, and engineering strategies into a generic template tree under docs/genericcontext/. Produces a generic CLAUDE.md, stack-appropriate standards, five canonical runbook templates with empty lessons stubs, a sandboxed agent-smoke harness (restricted tester plus independent judge), an unattended-testing permission allowlist, a PORTING cheat-sheet, and a lessons-from-source-project.md that anonymizes and merges the portable strategies. Use whenever the operator wants to carry a project's hard-won patterns into a new one, or says 'generate generic context', 'scaffold next project from this one', 'extract docs as a starter kit', 'create a project template', or 'produce a generic CLAUDE.md'. Skip if the project has fewer than ~5 shipped changes, or back up first if docs/genericcontext/ already exists.
RashiD2801/Skills/startup-architecture-diagram Skill
no license1★ repoSystem architecture and data flow diagram for a startup — generates a clean inline HTML/CSS visual showing all components, services, data flows, and external integrations. Usable standalone or as Phase 3 of the startup-analyzer pipeline.
RashiD2801/Skills/system-architect Skill
no license1★ repoWhen the user describes an idea, concept, tool, or app they want to build — even casually ("I want to make a tool that...", "I have an idea for...", "help me think through...") — use this skill to interview them and generate a clean system architecture HTML file. Activate on any of these phrases or intents: "I want to build", "I have an idea", "help me think through", "what would the architecture look like", "how would I structure this", "I'm thinking of making".
jajupmochi/agent-harness/setup/init-agent-config Skill
1★ repoScaffold a new project with the relevant subset of agent-harness rules, hooks, skills, recommendations, and templates. Asks about project type, language preferences, and context tags, then composes a project-specific CLAUDE.md, .claude/settings.json, and starter files. Use in a fresh or existing project to apply agent-harness conventions.
jajupmochi/agent-harness/skills/agent-config-adapter Skill
1★ repoAdapt an existing agent configuration or plugin to a new agent or model route. Use when moving agent-harness or another agent setup between Claude Code, Codex, Gemini, Cursor, local models, or non-native model backends such as DeepSeek routed through another agent.
jajupmochi/agent-harness/skills/init-codex-config Skill
1★ repoScaffold or migrate a project to use agent-harness from Codex. Use when applying agent-harness in Codex, converting Claude Code setup to AGENTS.md/.codex/.agents, or making a project ready for Codex skills and hooks without changing the original Claude setup.
ninnettesudanese653/claude-plugins/plugins/hive/skills/setup Skill
1★ repoSet up Hive agent identity. Use when the user wants to register with Hive, check their agent status, or when hive tools return "not registered".
ninnettesudanese653/claude-plugins/plugins/socials/commands/setup Skill
1★ repoInteractive setup wizard for Socials browser extension
Marine-softdrink524/claude-skills/skills/tool-use-architect Skill
no license1★ repoDesign and implement Claude tool/function calling patterns with error handling, parallel execution, and validation. Based on Anthropic's Claude Cookbooks.
The same file is in 1 other repository
LaWebcapsule/d9-skills/skills/d9-fork-setup Skill
1★ repoComplete development environment setup for d9 (Directus 9 fork) — reduces onboarding from 2 days to 2 hours.
LaWebcapsule/d9-skills/skills/ses-eu-west3-setup Skill
1★ repoConfigure AWS SES in eu-west-3 (Paris) for EU-based Directus projects to ensure email delivery.
svyatov/agent-toolkit/plugins/improve-architecture/skills/improve-architecture Skill
1★ repoExplore a codebase to find architectural improvement opportunities with an assessment gate that stops if architecture is already healthy. Prevents god objects through cohesion checks and includes mandatory test writing for new module boundaries. Use when user wants to improve architecture, consolidate tightly-coupled modules, simplify module boundaries, deepen shallow modules, or improve testability. Also triggers on: 'clean up the architecture', 'too many small files', 'these modules are tangled', 'hard to test', 'refactor for testability'.
svyatov/agent-toolkit/plugins/refactor/skills/refactor Skill
1★ repoALWAYS use this skill before refactoring any code. It prevents over-refactoring and wrong refactoring by requiring an assessment first — catching code that is already clean, problems that are architectural rather than code-level, and missing test coverage that must exist before touching business logic. Trigger on: refactor, clean up, simplify, reduce complexity, code smells, messy code, break up function, reduce nesting, remove dead code, file too big, extract method, too many parameters, duplicated code, cognitive complexity, god class, magic numbers. Also trigger when a linter or static analysis tool flags complexity issues. Language-agnostic.
chf3198/megingjord-harness/skills/fleet-portable-config Skill
no license1★ repoAdapt the Megingjord harness to a new operator's fleet topology without hand-editing inventory files. Use when first activating the harness on a new host or onboarding a new fleet.
chf3198/megingjord-harness/skills/github-ruleset-architecture Skill
no license1★ repoDesign and audit repository and organization ruleset architecture, including layering, bypass controls, enforcement modes, and merge queue compatibility.
chf3198/megingjord-harness/skills/global-skills-bootstrap Skill
no license1★ repoInitialize a repository so global skills are always loaded first through repository instructions, local hooks, and governance presence checks.
chf3198/megingjord-harness/skills/repo-onboarding-standards Skill
no license1★ repoOnboard any repository into a standardized Copilot + CI governance baseline. Use for new repos and first-time sessions to ensure immediate standards adoption.
zhijunio/skills/codebase-audit Skill
1★ repoRead-only codebase health audit — MECE pillars architecture (A1–A6), code (C0–C3), security (S1), verification (V1–V2), dependencies (D1), operations (O1). Chat-only P0/P1/P2 roadmap; effort snapshot, standard, or deep; variants simplicity, anti-pattern, branch, direction, cicd, and pillar-scoped review. Use for codebase audit, architecture review, security hygiene, CI/CD review, over-engineering and anti-pattern scan; not article writing, topic learning, implementation edits, or plans/.
nanocodana/nanocodana/packages/cli/example-skills/scaffold-component Skill
1★ repoScaffold a new React component (tsx + test + index) from a name
shane9coy/katana-agent/agent/skills/agents/installer Skill
no license1★ repoKatana setup wizard. Use when user says /setup, 'set up katana', 'configure my agent', 'install features', or 'walk me through setup'. Guides user through API key configuration, skill enabling, and profile creation.
yyykf/spellbook-skills/skills/simplify Skill
1★ repoReview all changed files for reuse, quality, and efficiency, then fix any issues found. Spawns three parallel review agents and aggregates findings into actionable fixes.
SWEStash/swe-workflow-skills/plugins/architect/skills/api-design Skill
1★ repoDesign RESTful and GraphQL APIs — endpoint naming, request/response contracts, error handling, pagination, versioning, auth patterns, OpenAPI specs. Triggers: design the API, API contract, REST API, GraphQL schema, error response format, pagination, API versioning, OpenAPI, swagger, endpoints. Use architecture-design for REST-vs-GraphQL or monolith-vs-microservices decisions.
SWEStash/swe-workflow-skills/plugins/architect/skills/architecture-design Skill
1★ repoGuide architectural and structural decisions using Architecture Decision Records (ADRs) — new services, pattern choices, database selection, component boundaries, state management, costly-to-reverse decisions. Triggers: how should I architect, which pattern, design decision, should I use X or Y, system design, ADR, component design, architectural trade-off. Owns internal-structure decisions — build vs buy/adopt a vendor or OSS capability → build-vs-buy.
SWEStash/swe-workflow-skills/plugins/architect/skills/architecture-documentation Skill
1★ repoDesign and maintain architecture documentation with multi-level diagrams (C4) and docs-as-code. Triggers: architecture diagram, document the architecture, C4 diagram, system context, container diagram, component diagram, architecture docs, docs-as-code, PlantUML, Structurizr, D2, Mermaid architecture, infrastructure diagram, runtime flow. Use architecture-design for ADRs.
SWEStash/swe-workflow-skills/plugins/architect/skills/code-archaeology Skill
1★ repoUnderstand unfamiliar or legacy code before changing it — map entry points, mine git history (blame, churn, log -S), trace data flow, recover the why behind odd code, pin current behavior with characterization tests, find seams for safe change. Triggers: understand this codebase, legacy code, inherited this project, what does this code do, why is it written this way, nobody knows how this works, onboard to this repo, is it safe to change this. Prioritizing debt → technical-debt-review; improving code you already understand → refactoring.
SWEStash/swe-workflow-skills/plugins/architect/skills/configuration-strategy Skill
1★ repoDesign environment configuration, secrets management, and feature-flag hierarchy for a service or feature. Triggers: config strategy, environment variables, .env, secrets management, feature flag, config hierarchy, config precedence, twelve-factor config, environment-specific settings.
SWEStash/swe-workflow-skills/plugins/architect/skills/technical-debt-review Skill
1★ repoStrategic codebase health assessment — identify hotspots, categorize debt, produce remediation roadmap.
SWEStash/swe-workflow-skills/plugins/backend/skills/api-design Skill
1★ repoDesign RESTful and GraphQL APIs — endpoint naming, request/response contracts, error handling, pagination, versioning, auth patterns, OpenAPI specs. Triggers: design the API, API contract, REST API, GraphQL schema, error response format, pagination, API versioning, OpenAPI, swagger, endpoints. Use architecture-design for REST-vs-GraphQL or monolith-vs-microservices decisions.
SWEStash/swe-workflow-skills/plugins/backend/skills/architecture-design Skill
1★ repoGuide architectural and structural decisions using Architecture Decision Records (ADRs) — new services, pattern choices, database selection, component boundaries, state management, costly-to-reverse decisions. Triggers: how should I architect, which pattern, design decision, should I use X or Y, system design, ADR, component design, architectural trade-off. Owns internal-structure decisions — build vs buy/adopt a vendor or OSS capability → build-vs-buy.
SWEStash/swe-workflow-skills/plugins/backend/skills/code-slop-cleanup Skill
1★ repoStrip AI slop from a branch diff before PR — judge each hunk against the surrounding file's conventions, remove without changing behavior, re-run tests. Removal only: hunting bugs → code-reviewing; structural improvement → refactoring; repo-wide audit → technical-debt-review; pruning tests → test-suite-design.