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
dineshrevunuru/SuperSkills/setup-deep-modules Skill
1★ repoWire dependency-cruiser to ENFORCE deep-module boundaries in one of Dinesh's React/Next/TypeScript apps — so the seams `codebase-design` designs can't erode into shallow cross-layer imports. Use when asked to 'enforce module boundaries', 'stop imports reaching into a feature's internals', 'add a boundary/architecture lint', 'set up dependency-cruiser', 'enforce layering', 'block deep imports past the public interface', or when agents/teammates keep bypassing a designed seam. Low-priority infra: reach for it only when a codebase is big enough (multi-feature, seams eroding) that discipline alone stops holding — NOT on prototypes or a small single-file app. The linter is a CONTROL, not a code-review reminder.
dineshrevunuru/SuperSkills/setup-pre-commit Skill
1★ repoSet up a Husky pre-commit hygiene GATE — lint-staged + Prettier on staged files, plus optional typecheck and fast tests — in one of Dinesh's shipped React/Next/TypeScript repos. Use when asked to 'add pre-commit hooks', 'set up Husky', 'configure lint-staged', 'add a format/typecheck gate before commit', 'stop unformatted or broken code getting committed', or when a client repo needs a hygiene floor. Low-priority infra: reach for it only when a maintained/client repo needs the gate — NOT on prototypes. The hook is a CONTROL, not a reminder to run the linter.
dineshrevunuru/SuperSkills/setup-skill-project Skill
1★ repoConfigure a repo ONCE for the engineering/SHIP skills — decide where work items and specs live (issue tracker) and where domain/decision docs live (doc layout), then record it in one block the downstream skills read. Use before first use of the work-pipeline or SHIP skills on a repo, or when asked 'set up this project for the skills', 'where do tickets/issues live here', 'configure the issue tracker', 'set up CONTEXT.md / doc layout', 'wire up the engineering workflow', 'new repo before I start shipping', or 'run the project setup'. Run-once infra. SOLO DEFAULT = local markdown files; it mode-switches UP to a team tracker only when a team actually uses one — never assume an enterprise setup. The config is a CONTROL that stops each downstream skill from guessing where work lives.
Structure information architecture
dineshrevunuru/SuperSkills/structure-information-architecture Skill
1★ repoDesigns and validates information architecture — organization schemes, hierarchy, labels, polyhierarchy — then proves it with card sorts and tree tests as one generate→evaluate loop. Use when organizing content or features into categories, naming navigation labels, building a sitemap, planning or analyzing a card sort or tree test, reading a dendrogram or similarity matrix, or when users 'can't find' things ('users can't find X', 'how should we organize the nav', 'run a card sort', 'is this hierarchy right', 'interpret these tree test results', 'fix our IA').
NSBen/skillfoundry/src/skillfoundry/data/starter_skills/explain-codebase Skill
1★ repoUse when you need to understand an unfamiliar repository or module and produce a structured walkthrough of how it works and where to change it.
NSBen/skillfoundry/src/skillfoundry/data/starter_skills/refactor-smell Skill
1★ repoUse when code shows duplication, long functions, or confusing control flow and you want safe refactors that preserve behaviour.
mblauberg/provenant/skills/refactor Skill
1★ repoUse for authorised, behaviour-preserving structural simplification backed by characterisation and equivalence evidence. Not for new behaviour, read-only review, or unknown root cause; use tdd, code-review, or diagnose.
mblauberg/provenant/skills/setup-repo Skill
1★ repoUse when asked to set up or scaffold a repository's process, labels, tracker, branch ruleset, issue forms, docs layout, work-item runbook, or board. Not for this repo's own day-to-day GitHub mechanics; use its runbook.
furkangonel/cowrangler/bundled_skills/creative/architecture-diagram Skill
1★ repoGenerate dark-themed SVG architecture diagrams as self-contained HTML.
furkangonel/cowrangler/bundled_skills/refactoring Skill
1★ repoSafe, incremental refactoring techniques — improve structure without changing behavior
furkangonel/cowrangler/bundled_skills/setup-cowork Skill
1★ repoGuided Cowork setup — install role-matched plugins, connect your tools, try a skill. Trigger for: - [TODO: Add specific triggers for when to use this skill] Don't trigger for: - [TODO: Add anti-triggers for when NOT to use this skill]
furkangonel/cowrangler/bundled_skills/simplify Skill
1★ repoAudit recently changed code for reuse, quality, and efficiency issues using parallel sub-agents, then fix all findings
Dangerous config file protection
vishuwa2004/cskill-agents/agents/claude-code/skills/dangerous-config-file-protection Skill
1★ repoKeep writes out of sensitive dotfiles and claude folders by checking canonicalized basenames before granting permission.
The same file is in 1 other repository
Privacy redacted repl bridge system init
vishuwa2004/cskill-agents/agents/claude-code/skills/privacy-redacted-repl-bridge-system-init Skill
1★ repoReuse one system init payload shape across trusted and remote transports, but redact tool, MCP, and plugin metadata when the bridge path would leak local integrations or filesystem paths.
The same file is in 1 other repository
Shared system init shape parity
vishuwa2004/cskill-agents/agents/claude-code/skills/shared-system-init-shape-parity Skill
1★ repoCentralize system init or capability payload construction in one builder so multiple transports emit identical schemas and only vary inputs or delivery.
The same file is in 1 other repository
Dangerous config file protection
vishuwa2004/cskill-agents/agents/codex/skills/dangerous-config-file-protection Skill
1★ repoKeep writes out of sensitive dotfiles and claude folders by checking canonicalized basenames before granting permission.
The same file is in 1 other repository
Privacy redacted repl bridge system init
vishuwa2004/cskill-agents/agents/codex/skills/privacy-redacted-repl-bridge-system-init Skill
1★ repoReuse one system init payload shape across trusted and remote transports, but redact tool, MCP, and plugin metadata when the bridge path would leak local integrations or filesystem paths.
The same file is in 1 other repository
Shared system init shape parity
vishuwa2004/cskill-agents/agents/codex/skills/shared-system-init-shape-parity Skill
1★ repoCentralize system init or capability payload construction in one builder so multiple transports emit identical schemas and only vary inputs or delivery.
The same file is in 1 other repository
Dangerous config file protection
vishuwa2004/cskill-agents/skills/dangerous-config-file-protection Skill
1★ repoKeep writes out of sensitive dotfiles and claude folders by checking canonicalized basenames before granting permission.
The same file is in 1 other repository
Privacy redacted repl bridge system init
vishuwa2004/cskill-agents/skills/privacy-redacted-repl-bridge-system-init Skill
1★ repoReuse one system init payload shape across trusted and remote transports, but redact tool, MCP, and plugin metadata when the bridge path would leak local integrations or filesystem paths.
The same file is in 1 other repository
Shared system init shape parity
vishuwa2004/cskill-agents/skills/shared-system-init-shape-parity Skill
1★ repoCentralize system init or capability payload construction in one builder so multiple transports emit identical schemas and only vary inputs or delivery.
The same file is in 1 other repository
NDDev-it-com/rldyour-antigravity-cli/.gemini/skills/ry-init Skill
1★ repoИнициализируй Antigravity CLI adapter scope без изменений. EN: initialize Antigravity CLI adapter scope read-only.
NDDev-it-com/rldyour-antigravity-cli/skills/ry-init Skill
1★ repoИнициализируй Antigravity CLI adapter scope без изменений. EN: initialize Antigravity CLI adapter scope read-only.
rrpauls/hermes-esra/optional-skills/evolutionary-self-dev/hermes-codebase-engineer Skill
1★ repoActivate hermes-codebase-engineer for any programming, code analysis, integration, refactoring or development tasks related to Hermes Agent fork, skill integration, OODA implementation, or building ESRA features. Use when the task involves reading/writing code, creating integration scripts, adapting skills to Hermes format, building orchestrators, or modifying agent logic. Combines with ooda-framework, self-improver, experimenter and loop-auditor. Triggered by programming, code, integrate Hermes, refactor, script, Python agent development or similar.
erenisci/acta/skills/init Skill
0★ repoStart a new project — create <PROJECT>_BRIEF.md for you to fill (? = suggest, - = skip); asks the doc language. Writes no docs itself. Trigger on /acta:init, "start a project", "create a project brief".
aneebbaig/app-starter-skills/plugins/app-starter/skills/nextjs-app Skill
0★ repoBootstrap a new Next.js (App Router, TypeScript) web app, or audit and retrofit an existing one, with current packages and no deprecated APIs. Use when the user wants to start, scaffold, or set up a new Next.js project, a React web app, a SaaS or dashboard or landing page on Next.js, or asks to "create a new nextjs app". ALSO use on an existing Next.js or React codebase when the user asks to audit, review, fix, clean up, refactor, modernize, upgrade, harden, or "bring up to standard" the app, remove deprecated APIs, improve the structure, or apply house rules. Handles private, open-source, and private-plus-open-source variants, Prisma and Postgres, better-auth, Tailwind, and shadcn or Mantine.
mnox/mnox-ai/plugins/config-chunks/skills/ai-setup Skill
0★ repoFirst-run guided onboarding that sets up an agent for a less-technical user — leads with a one-shot recommended set of guidance "chunks" (or 2–3 plain-language questions to tailor), confirms, applies them by driving the config-chunks engine into CLAUDE.md / AGENTS.md, then offers safe permission setup. Use when the user says "/ai-setup", "set up my agent", "set up my agent guidance", "onboard me to chunks", "configure my CLAUDE.md guidance", "first-run setup", "recommend chunks for me", "help me get started with config-chunks", "which chunks should I use", or otherwise wants a guided walkthrough to subscribe to guidance chunks. Re-runnable any time; for piecemeal management afterward use /chunks, for permissions use /permission-setup, and to author new chunks use /chunk-review.
mnox/mnox-ai/plugins/config-chunks/skills/permission-setup Skill
0★ repoRecommend safe, conservative agent permission settings for a less-technical user, then delegate the write — never mutate security config directly. Detects the provider (Claude Code / Codex / Cursor / others) and surface (CLI / Desktop-IDE / Cloud), explains permissions in plain language, recommends the "Cautious" least-privilege posture as behavior then concrete config, names that provider's bypass footgun by name, and shows the exact config + location for the user (or a platform config skill) to apply. Use when the user says "/permission-setup", "set up permissions", "set up my agent permissions", "is my agent safe", "make my agent safe", "what permissions should I use", "lock down my agent", "are my settings secure", "review my agent permissions", or finishes /ai-setup. Re-runnable any time; reads references/permission-profiles.md live.
giovicordova/skills-gc/skills/perspective Skill
no license0★ repoStrategic reality check for any project. Researches whether the solution already exists, whether there are better approaches, and whether the codebase follows current best practices — using live documentation, not stale training data. Use this skill when the user says 'perspective', 'am I on the right track?', 'is there a better way?', 'has someone already built this?', 'reality check', or any request to evaluate whether the current project direction is optimal. Also use when the user questions whether they are reinventing the wheel, wonders about alternatives, or wants to validate architecture against what exists in the ecosystem.
Ajeesh25353646/claude-skills/visual-architecture-explainer Skill
0★ repoUse when the user wants a visual, beautifully explained architecture document for any system they've built, combining mermaid.js diagrams, visual companion mockups, dark-themed HTML, and narrative walkthroughs. Best for when they say 'I can't understand what I built, explain it visually', 'create a visual architecture doc', or 'make me a diagram of my system'.
thinkyou0714/claude-lab-skills/lab-automation-architecture/skills/retry-idempotency-check Skill
0★ repo自動化フロー・API 呼び出しのリトライ設計とべき等性を確認する。同じ処理が複数回実行された場合に、データ破損・二重決済・重複挿入が起きないかを検証する。リトライ・再実行を伴う処理の設計時に使う。
thinkyou0714/claude-lab-skills/lab-communication-translation/skills/onboarding-readability Skill
0★ repoドキュメント・README・設計記録が、初めて読む人(人間またはAI)にとって理解可能かを評価する。前提知識・用語定義・構造・導線の欠落を検出し、改善点を提示する。ドキュメントを公開・共有する前に使う。
thinkyou0714/claude-lab-skills/lab-data-auth-ops/skills/auth-system-design Skill
0★ repo認証・アイデンティティの仕組み(認証方式・セッション/トークン・本人確認・回復)をゼロから設計する。新規プロダクト・新規認証導入の設計初動で使う。
withqwerty/ship/skills/init Skill
no license0★ repoUse this skill when the user wants to set up, configure, or initialize the ship plugin, create or update their ship profile, change their review mode, update their product brief, or edit .claude/ship.local.md. Trigger on "ship init", "set up ship", "configure ship", "create my profile", "update my profile", "change review mode to brutal/kind", or when any other ship skill detects that .claude/ship.local.md does not exist. Also use when the user says they've changed roles, shifted priorities, or moved to a new project stage.
alexe-ev/product-plugins/marketing-growth/skills/design-onboarding-flow Skill
0★ repoDesign a user onboarding flow that gets new users to the activation moment as quickly as possible. Use this skill when onboarding is too long, confusing, or failing to deliver early value.
Manage technical debt tradeoffs
alexe-ev/product-plugins/technical-product/skills/manage-technical-debt-tradeoffs Skill
0★ repoStructure the trade-off decision between addressing technical debt and delivering new product value. Use this skill when a team needs to make explicit, principled decisions about when and how to invest in technical debt reduction.
alexe-ev/product-plugins/technical-product/skills/prioritize-architecture-aware Skill
0★ repoIncorporate architectural constraints and technical debt into product prioritization decisions. Use this skill when a team needs to balance feature work with technical investment.
maskar/cc-plugins/sawkit/skills/project-structure Skill
0★ repoThis skill should be used when the user is scaffolding a new project, reorganizing file structure, or discussing directory layout conventions. It provides language-specific best practices for Python, Node/TypeScript, Go, and general projects. Enforces the ./tmp/ intermediary workflow and .claude/CLAUDE.md convention. Triggers on: project init, directory layout, file organization, scaffolding, repo structure, creating new projects, setting up a Python/Node/Go project, or organizing code. Also available as /sawkit:project-structure.
clever-cc-plugins/cc-concept/plugins/cc-concept/skills/cc-concept-onboarding Skill
0★ repoUse this skill to set up or extend the strategic context a marketing project needs before positioning, competitive, or go-to-market work. Invoke when the user asks to "onboard for strategy", "set up strategy context", "add competitive context", or when a cc-concept skill reports a missing strategic need. Runs standalone and also recognises context an existing cc-content project already provides.
azadmotala/claude-code-team-builder/skill Skill
0★ repoBuilds a complete AI development environment for a software project — agents, custom skills, CLAUDE.md project context, orchestration layer, and routing rules. Triggers when someone says 'set up a new project', 'build a team for [project]', 'create project setup', 'scaffold my AI team', or describes a client project and wants Claude Code configured for it. Produces a full .claude/ configuration with project context, agent routing, autonomous execution support, and slash commands tailored to the project's domain and workflow.
telefrek/vallorcine/skills/feature-refactor Skill
0★ repoReview and refactor implemented code with quality checklist
telefrek/vallorcine/skills/setup-vallorcine Skill
0★ repoOne-time project setup — KB, decisions, feature pipeline, and project profile
telefrek/vallorcine/skills/spec-init Skill
0★ repoBootstrap the spec corpus for this project
bokuwalily/claude-code-skills/skills/codebase-to-course Skill
0★ repo75 battle-tested Claude Code skills from shipping 20+ apps solo — macOS, Next.js, Vercel, iOS/Expo, Cloudflare, Phaser, local AI media & more
bokuwalily/claude-code-skills/skills/codex-cli-setup Skill
0★ repoOpenAI Codex CLIをインストールし認証して、Claudeのbashツールや自動化スクリプトからノンインタラクティブで呼び出せるようにするときに使う
bokuwalily/claude-code-skills/skills/gcal-oauth-desktop-setup Skill
0★ repo個人GCPプロジェクトでGoogle Calendar APIのOAuth 2.0 Desktop App認証を新規セットアップするとき(既存GCPプロジェクトへの権限がない場合を含む)。
bokuwalily/claude-code-skills/skills/openclaw-ollama-setup Skill
0★ repoOpenClaw(2026.5+)をローカルOllamaのLLMで動かす設定をしたい時。プロバイダ登録・デフォルトモデル設定・動作検証まで。旧OpenAI互換ハックは不要
cskwork/claude-minimal-plugin/skills/taste-skill Skill
0★ repoSenior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
specdd/plugin-claude/skills/specdd-refactor Skill
0★ repoUse when Claude Code needs to refactor code, tests, docs, specs, or project structure while preserving active SpecDD behavior.
Saturate/skills/codebase-audit Skill
no license0★ repoPerforms comprehensive codebase audit checking architecture, tech debt, security vulnerabilities, test coverage, documentation, dependencies, and maintainability. Use when auditing a project, assessing codebase health, running security scans, checking for vulnerabilities, reviewing code quality, analyzing tech debt, or asked to audit/analyze the entire codebase.
Saturate/skills/node-package-management Skill
no license0★ repoReference guide for npm, pnpm, yarn, and bun package managers. Covers workspace configuration, security audits, troubleshooting, and migration between package managers. Use for complex monorepo setup, debugging package issues, or deep package manager reference.
deltafly/doom-cheats-for-claude-code/plugins/doom-cheats/skills/iddt Skill
0★ repoIDDT — "full automap reveal." A recon mode: for an unfamiliar or long-unseen project it reveals the whole map — architecture, entry points, key folders and files, data flow, tech stack, where things live. It runs Glob + Grep + Explore subagents and caches a compact "MAP REVEALED" overview. Use when the user types /iddt, or asks to "map this out", "show the project structure", "what's in this repo", "where do I start", "give me an overview of the codebase", "recon", or in Hungarian "térképezd fel", "mutasd a projekt szerkezetét", "mi van ebben a repóban", "hol kezdjek hozzá", "adj áttekintést a kódbázisról" — and proactively when starting work in an unknown codebase where you need to get oriented first.
burythehammer/claude-code-plugins/plugins/terraform-migration/skills/migrate-to-plugin-framework Skill
0★ repoThis skill should be used when migrating Terraform provider data sources or resources from hashicorp/terraform-plugin-sdk/v2 to hashicorp/terraform-plugin-framework. Trigger phrases include "migrate to plugin framework", "SDK v2 to plugin framework", "convert to plugin framework", "migrate data source", "migrate resource", "plugin framework migration", "move to framework", or "upgrade from SDK v2". Provides step-by-step migration workflow, code patterns, schema mapping, and common gotchas.
The same file is in 2 other repositories
uplift-technology-company-limited/uplift-plugins/plugins/vercel-gha-deploy/skills/vercel-gha-deploy Skill
0★ repoSet up (or fix) deploying a Next.js / frontend repo to Vercel from a GitHub Actions workflow — with an org-level VERCEL_TOKEN, a main-only branch gate, and an auto-bumped vX.Y.Z version tag baked into the build and shown in the UI. Use this WHENEVER the user wants to add a Vercel deploy pipeline via GitHub Actions, move a repo from manual `vercel --prod` to CI deploy, run the build on a self-hosted runner, wire auto-versioning onto Vercel deploys, or bootstrap a not-yet-set-up repo (git init → GitHub → vercel link → deploy) — even if they don't name this skill. NOT for: fixing app/code bugs that happen to surface in a Vercel build, one-off manual `vercel --prod` runs, Vercel dashboard settings (env vars, domains, rollbacks), Vercel's native git integration (this skill uses GitHub Actions instead), or deploys to other targets (AWS ECS, Docker, a VPS).
kennyolofsson23-netizen/claude-code-config/skills/ddd/setup-code-formating Skill
no license0★ repoSets up code formatting rules and style guidelines in CLAUDE.md
kennyolofsson23-netizen/claude-code-config/skills/ddd/software-architecture Skill
no license0★ repoGuide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
The same file is in 1 other repository
kennyolofsson23-netizen/claude-code-config/skills/onboarding-cro Skill
no license0★ repoWhen the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," "new user experience," "users aren't activating," "nobody completes setup," "low activation rate," "users sign up but don't use the product," "time to value," or "first session experience." Use this whenever users are signing up but not sticking around. For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence.
The same file is in 4 other repositories
kennyolofsson23-netizen/claude-code-config/skills/project-init Skill
no license0★ repoInitialize a new project with Kenny's universal conventions and stack-appropriate infrastructure. Use this skill whenever: setting up a new project, creating a new repo, scaffolding a new app, starting fresh on a new idea, 'init project', 'new project', 'set up a new app', 'create a project for X', or any variant of starting a new codebase from scratch. Also trigger when the user says 'bootstrap', 'scaffold', or 'kickstart'. This skill ensures every project gets the same quality gates and conventions while adapting infrastructure to the chosen stack.
kennyolofsson23-netizen/claude-code-config/skills/security-threat-model Skill
no license0★ repoRepository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
The same file is in 8 other repositories
Zrzzzz/agent-codebase-skills/init-session-notes Skill
0★ repo为项目初始化「会话归档」自动化基础设施: 1. SessionEnd hook:每次会话结束自动用 claude -p 提炼对话要点追加到 docs/session-notes.md, 含超阈值自动压缩(默认 45KB)。 2. docs/session-notes.md:长期决策与踩坑沉淀(hook 维护,模板由本 skill 初始化)。 本 skill 只管「会话归档」:不写 CLAUDE.md / AGENTS.md 分层约定——那些归 [`init-agents-md`](../init-agents-md/SKILL.md);不初始化 docs/TASKS.md 任务管理—— 那些归 [`init-agent-task-md`](../init-agent-task-md/SKILL.md)。 使用:/init-session-notes;或当用户说「给项目装会话归档」「我想要自动整理对话要点」时也命中本 skill。