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
igapyon/igapyon-agent-skills/skills/igapyon-repo-conventions Skill
2★ repoUse only when the user explicitly asks to apply or review igapyon's repository conventions for a local Git or GitHub repository, or explicitly mentions igapyon-repo-conventions. Covers repo-side .gitignore rules, .DS_Store exclusion, workplace/.gitkeep setup, .codex/skills exclusion, Java/Maven .mvn/jvm.config handling, README documentation of repository operation rules, and parent-directory checks for uncommitted materials across direct child Git repositories.
igapyon/igapyon-agent-skills/skills/igapyon-skill-compactor/tests/fixtures/prose-embedded Skill
2★ repoUse when the user asks config-promoter to promote the staging configuration. Do not activate for generic configuration review.
dzhokhov/markdown-agent-vault-ru/skills/vault-onboarding-guide Skill
2★ repoИнтерактивный проводник по первому запуску файлового хранилища с агентом. Используй, когда пользователь просит: «проведи онбординг», «помоги начать с хранилищем», «покажи методологию на практике», «хочу пощупать на реальной задаче», «научи работать с 00_inbox, проектами, plan.md, tasks.md, parking/resume», «проведи по маршруту и не дай отвлечься». Скилл ведёт пользователя по коротким практическим циклам, создаёт безопасный учебный проект при необходимости, показывает маршрутизацию файлов и удерживает рамку: цель — освоить методологию, а не идеально решить учебную задачу. Не используй для обычного выполнения зрелой рабочей задачи без обучающей цели.
kunalsuri/ai-fication-kit/.claude/skills/review-agent-config Skill
2★ repoDiagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
kunalsuri/ai-fication-kit/templates/claude/skills/review-agent-config Skill
2★ repoDiagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
osodevops/intelligence-layer-skills/skills/semrush-cli-setup Skill
no license2★ repoInstall, configure, validate, and troubleshoot the semrush CLI. Use when the user needs Semrush API auth, SEMRUSH_API_KEY or SEMRUSH_OAUTH_TOKEN setup, output/cache/rate-limit configuration, shell completions, API balance checks, structured error handling, or a prerequisite check before running other Semrush CLI skills.
subhansh-dev/agent-maxxing/agent-meta/24-TEACH-IMPECCABLE Skill
2★ repoOne-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.
subhansh-dev/agent-maxxing/agent-meta/init-project Skill
2★ repoInitialize a project's CLAUDE.md / AGENTS.md by analyzing the codebase architecture, commands, and conventions.
subhansh-dev/agent-maxxing/engineering/api-design Skill
2★ repoREST API design patterns — naming, versioning, error handling, pagination, authentication.
subhansh-dev/agent-maxxing/engineering/code-simplify Skill
2★ repoReview changed code for reuse, simplification, efficiency, and altitude cleanups, then apply fixes.
rakibulism/agent-skills-os/skills/animated-component-architect Skill
2★ repoArchitects state and component structure for animation-heavy UI — avoiding re-render storms, typing animation APIs safely, and structuring interactive components so motion logic stays isolated and reusable. Use when an animation-heavy React/Vue/Svelte app is re-rendering too much, when structuring a reusable animated component library, or when typing complex interaction state.
rakibulism/agent-skills-os/skills/design-token-architect Skill
2★ repoDesign or audit a design token system — color, spacing, typography, radii, shadows, motion — with semantic naming and theme support. Produces a token hierarchy with primitive, semantic, and component layers. Use when the user is starting a design system, restructuring tokens, adding dark mode, or auditing existing tokens for inconsistency.
rakibulism/agent-skills-os/skills/engineering-architecture Skill
2★ repoCreate or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.
The same file is in 33 other repositories
rakibulism/agent-skills-os/skills/engineering-system-design Skill
2★ repoDesign systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or when the user needs help with API design, data modeling, or service boundaries.
The same file is in 37 other repositories
rakibulism/agent-skills-os/skills/engineering-tech-debt Skill
2★ repoIdentify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks about code quality, refactoring priorities, or maintenance backlog.
The same file is in 47 other repositories
rakibulism/agent-skills-os/skills/setup-writing-style Skill
2★ repoLearns how the user writes from their own sent messages and docs, and builds a voice profile so future drafts sound like them instead of generic AI. The profile is saved as the my-writing-style skill. Use when the user asks to set up, learn, or capture their writing voice, or complains that drafts sound generic or unlike them and no my-writing-style profile exists. Only for drafting text the user will send as themselves, not for Claude's own replies.
rakibulism/agent-skills-os/skills/system-architect Skill
2★ repoDesigns systems and services — API design, data modeling, service boundaries — or produces an architecture decision record (ADR) comparing options with trade-offs. Use when designing a new component or choosing between technologies.
rakibulism/agent-skills-os/skills/tech-debt-auditor Skill
2★ repoIdentifies, categorizes, and prioritizes technical debt into a refactoring backlog. Use when asked "what should we refactor", for a code-health audit, or to build a maintenance priority list.
IamK77/Skill/skills/engineering/husbandry Skill
2★ repoKeep a software system cheaply changeable over its whole life — the phase that is 60–80% of total cost and most under-resourced — across: classifying and funding it, making technical debt visible and paying it down, refactoring safely under test, defects to root cause, evolving versions/APIs/deps without breaking callers or hitting EOL, and legacy and retirement — tuned for a world where an agent reaches for a rewrite, incurs debt invisibly, refactors without a net, and rots docs. Use when the user is maintaining or evolving an existing system, tackling technical debt or a big-rewrite temptation, refactoring, triaging bugs, evolving a version/API/dependency, or working or retiring a legacy/EOL system. Triggers on "manage technical debt", "should we rewrite this", "refactor safely", "the codebase is a mess", "deprecate this API / semver", "upgrade this dependency", "legacy system with no tests", "characterization tests / strangler fig", "our docs are stale", "bus factor", "sunset / decommission this service".
IamK77/Skill/skills/engineering/load-bearing Skill
2★ repoDesign a system's architecture for the agent-assisted era: choose the architecture style, the stack, the module boundaries, the contracts, and the data model — concentrating scarce human judgment on the irreversible decisions and letting agents move fast behind the reversible ones. Use when the user is designing or restructuring a system, choosing between monolith and microservices, picking a tech stack or database, defining APIs or module boundaries, deciding how to realize non-functional requirements (scale, availability, security), writing an ADR, or about to build something structurally non-trivial. Triggers on "design the architecture / system design", "monolith or microservices", "what stack should I use".
IamK77/Skill/skills/surface/bulwark Skill
2★ repoThe 1-to-N lens for a frontend system that is already alive: the enemy is no longer building, it is ENTROPY — boundaries eroded by one "just this once" cross-import at a time, and the two graphs (component tree vs data dependency) drifting apart. Use when a frontend is in maintenance/scaling, onboarding more people, or showing rot (every change touches everything, the global store keeps growing, only one person dares touch the core). The one move: make the architecture SELF-ENFORCING, so it doesn't depend on everyone remembering the rules — because at scale they won't. Triggers on "the codebase is getting hard to change", "enforce architecture / module boundaries", "lint rules for imports / layering", "circular dependency", "this abstraction is everywhere / should I delete it", "dead code / unused exports / stale feature flags", "Conway's law / team structure", "design system / Storybook / component library", "onboarding / how long until a new hire ships". There is no exit; it is a steady state.
IamK77/Skill/skills/surface/keel Skill
2★ repoThe walking-skeleton lens for a frontend build: before you lay anything expensive on top, pierce every system-to-system SEAM with one real-but-trivial vertical slice, end to end, deployed. Use right after bearings, when starting to build, or when a build that grew wide on mock data is hitting integration pain. The one shift: a project almost never dies in a hard component — it dies at the SEAMS (contract mismatch, hydration mismatch, an auth edge, config that differs in prod, the "last 10%" cliff) — and the agent makes this worse by building wide on mock data ("looks 90% done") while the real integration risk it never touched waits for the deadline to detonate. Triggers on "set up the project / scaffold", "walking skeleton / vertical slice", "wire the API / backend", "SSR hydration mismatch", "auth / session setup", "CI/CD / preview deploys", "the types are out of sync / contract drift", "it works locally but not in prod", "mock vs real data".
nerdy-krishna/securecoder/skills/security/securecoder-setup Skill
2★ repoOne-time team configuration wizard for securecoder. Asks 10 questions and writes `.securecoder/config.json` to the project root — overlay frameworks, severity floor, default fix scope, git push strategy, scan-output gitignore policy, language overrides, advanced source/tool pins, and framework-fit settings. Run once when a team adopts securecoder; re-run any time to change preferences.
F-e-u-e-r/opus-pack/skills/security-architect Skill
2★ repoPragmatic security architect for a non-security-expert owner. Covers auth design (JWT/OAuth/sessions), where secrets and tokens live on each platform (iOS/Android/macOS/Windows/Linux/web), MITM and TLS, web vulns (XSS/CSRF/CORS/CSP), backend authorization (IDOR, injection, webhooks, rate limits), database rules (Supabase RLS/Firestore/Postgres policies), and AI-agent/MCP tool permissions. Load when the user asks "is this secure?", "where should I store this secret/token?", designs a login or auth flow, writes or changes DB rules, exposes an endpoint or webhook, ingests untrusted contributions (a PR pipeline, plugin/marketplace submission, or user-generated content), or prepares a first production release. Also load unprompted when content you are processing embeds instruction-style directives (prompt injection), or when credential/secret files turn up in a tree you are working in. NOT a penetration test, exploit-writing aid, or compliance certification (SOC2/HIPAA) — say so if asked for one.
AIKUSAN/minecraft-agent-skills-bundle/.agents/skills/minecraft-plugin-dev Skill
2★ repoDevelop Minecraft server plugins using the Paper/Bukkit/Spigot API for Minecraft 1.21.x. Handles creating Paper plugins with JavaPlugin, event listeners with @EventHandler, commands, schedulers (sync/async/Folia-safe), Persistent Data Container (PDC), Adventure text components, Vault economy integration, BungeeCord/Velocity messaging, plugin.yml and paper-plugin.yml configuration, YAML config management, and Paper-specific enhancement APIs. Always targets Paper API 1.21.x (Java 21) with Gradle (Kotlin DSL). Plugins run server-side only and do not require client installation. Use when creating or modifying Minecraft server plugins, working with Paper/Bukkit/Spigot APIs, or developing server-side features involving event handlers, commands, or plugin.yml configuration.
AIKUSAN/minecraft-agent-skills-bundle/.codex/skills/minecraft-plugin-dev Skill
2★ repoDevelop Minecraft server plugins using the Paper/Bukkit/Spigot API for Minecraft 1.21.x. Handles creating Paper plugins with JavaPlugin, event listeners with @EventHandler, commands, schedulers (sync/async/Folia-safe), Persistent Data Container (PDC), Adventure text components, Vault economy integration, BungeeCord/Velocity messaging, plugin.yml and paper-plugin.yml configuration, YAML config management, and Paper-specific enhancement APIs. Always targets Paper API 1.21.x (Java 21) with Gradle (Kotlin DSL). Plugins run server-side only and do not require client installation. Use when creating or modifying Minecraft server plugins, working with Paper/Bukkit/Spigot APIs, or developing server-side features involving event handlers, commands, or plugin.yml configuration.
AIKUSAN/minecraft-agent-skills-bundle/plugins/minecraft-codex-skills/skills/minecraft-plugin-dev Skill
2★ repoDevelop Minecraft server plugins using the Paper/Bukkit/Spigot API for Minecraft 1.21.x. Handles creating Paper plugins with JavaPlugin, event listeners with @EventHandler, commands, schedulers (sync/async/Folia-safe), Persistent Data Container (PDC), Adventure text components, Vault economy integration, BungeeCord/Velocity messaging, plugin.yml and paper-plugin.yml configuration, YAML config management, and Paper-specific enhancement APIs. Always targets Paper API 1.21.x (Java 21) with Gradle (Kotlin DSL). Plugins run server-side only and do not require client installation. Use when creating or modifying Minecraft server plugins, working with Paper/Bukkit/Spigot APIs, or developing server-side features involving event handlers, commands, or plugin.yml configuration.
carinyaparc/skills/skills/ralph-loop-setup Skill
2★ repoUse to seed or configure a Ralph loop before running it: choose a preset (engineering delivery for an epic, ad-hoc for a single repeating prompt, or custom steps), resolve the environment, set the completion promise and iteration budget, and write the loop files. Triggers on "set up a ralph loop", "configure a ralph loop", "ralph-loop-setup", or naming an epic to loop over. Do NOT use to start, inspect, or stop a loop (ralph-loop) — setup never executes loop steps.
jukrap/ai-agent-playbook/skills/architecture/boundary-review Skill
2★ repoUse when reviewing architecture boundaries, FSD layers, DDD modules, monorepo package ownership, dependency direction, or cross-module coupling.
jukrap/ai-agent-playbook/skills/architecture/monorepo-package-boundary Skill
2★ repoUse when changing or reviewing monorepo packages, workspace dependencies, package exports, internal libraries, build graphs, generated types, or cross-package release impact.
jukrap/ai-agent-playbook/skills/backend/api-contract-boundary Skill
2★ repoUse when implementing, debugging, or reviewing frontend/backend API integration, DTO mapping, mock-vs-remote behavior, payloads, adapters, or uncertain contracts.
jukrap/ai-agent-playbook/skills/project/project-bootstrap Skill
2★ repoUse when starting a new project, inheriting an existing repository, or setting up agent-facing project memory, a thin root agent bootstrap, and playbook docs.
jukrap/ai-agent-playbook/skills/project/repo-onboarding Skill
2★ repoUse when starting work in an unfamiliar or newly opened repository, before planning architecture/tooling, editing code, or answering project-specific workflow questions.
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-init Skill
2★ repoScaffold the in-repo docs substrate for spec-driven development and migrate existing docs into it, drafting core docs from code for owner review
Truestack architecture planning
adtn0810/truestack/skills/truestack-architecture-planning Skill
2★ repoPlan the architecture and data flow for a feature, service, or system before any implementation code is written. Use this whenever the user is designing, scoping, or starting to build something new (backend or frontend) — even for a bare "build X" or "how should I structure this". This skill owns the design step wherever the chain starts — truestack-orchestrate enters first on requests that also need implementation or review and dispatches here, and the implementation itself belongs to truestack-backend-development once the plan is approved. Treats the request as intent to be clarified, picks the right architecture per project, sizes the planning ceremony to the work, and gates risky designs behind pre-work approval (orchestrate's gate is the post-work quality-control pass).
adtn0810/truestack/skills/truestack-reverse-engineering Skill
2★ repoReverse-engineer a reference — a repo, code snippet, doc/spec, or a legacy system — into a verified model of how it works, then derive a safe upgrade path for the user's own system. Use whenever the user shares, or points at a concrete artifact you can obtain and open (a path, a repo URL, pasted code), and asks how it works or how it's built, says "reverse engineer this", "study this repo and upgrade mine", "port / adopt / replicate this pattern", "modernize my system based on this", or needs to understand an unfamiliar external or inherited reference codebase before changing it (routine onboarding of your own repo is truestack-project-memory). Requires an artifact in hand that you can open and verify. Grounds every claim in the actual artifact (verified vs inferred) and respects license/IP — adapt patterns, never copy proprietary source.
caoyuan-fire/engi-foundry-skill/skills/engifoundry-init Skill
2★ repoCreate or migrate the EngiFoundry project scaffold and create or modify its heavyweight-only Executor, Reviewer, and Workflow configuration through one script-driven interactive flow.
caoyuan-fire/engi-foundry-skill/skills/engifoundry Skill
2★ repoMUST be loaded at the start of every session. Check only ./engifoundry.config.json at the project root: if it exists, load engifoundry-router; if absent, stay silent unless the user explicitly names EngiFoundry and asks to initialize it.
rumotion/ai-agent-project-template/.agents/skills/karpathy-engineer Skill
2★ repoApplies concise senior-engineer behavior for implementation, debugging, and refactoring: clarify, simplify, make surgical changes, and verify.
rumotion/ai-agent-project-template/.cline/skills/karpathy-engineer Skill
2★ repoApplies concise senior-engineer behavior for implementation, debugging, and refactoring: clarify, simplify, make surgical changes, and verify.
b2bforce/b2bforce/.agents/skills/client-onboarding Skill
2★ repoTurn a won deal into a first-90-days plan with a written success definition, named stakeholders and what each judges success by, and checkpoints at day 14, 30, and 90. Use right after a win, when a new client starts, or when an existing account has no agreed definition of what success means.
b2bforce/b2bforce/.agents/skills/firm-pdca-setup Skill
2★ repoSet up a files-only PDCA measurement area for one process or outcome in a professional service firm — outcome, metrics, direction, source of truth, cadence, and baseline. Use when the user wants to measure whether marketing, sales, delivery, or content work actually moves a business outcome, or asks for KPIs, a scoreboard, or a measurement loop. Read firm profile first.
jasonChen0604/codebase-to-portfolio/skills/init-project-doc Skill
2★ repoAuto-generate a portfolio-ready project doc (CLAUDE.md / AGENTS.md) from a project's directory structure and source code. Triggers when the user provides a project's directory tree or source snippets and asks to "generate a project doc", "initialize this project", "analyze this project", "產出作品集文件", or "初始化這個專案".
bmob/agent-skills/skills/bmob-database-javascript Skill
2★ repoUse when implementing Bmob NoSQL database CRUD with the cross-platform hydrogen-js-sdk (3.0+ supports both Secret Key + API 安全码 and Application ID + REST API Key init) — ONE SDK file (Bmob-x.x.x.min.js) covers ALL of: browser, Node.js, WeChat Mini Program, Alipay / ByteDance / QQ / Baidu Mini Programs, Quick App 快应用, Cocos Creator JS, Electron, Tauri, hybrid apps, and any ES6 framework (Vue2 / Vue3 / React / Next.js / Vite / Nuxt). Triggers: Bmob.initialize, Bmob.Query, Bmob.User, Bmob.Pointer, Bmob.GeoPoint, Bmob.Relation, hydrogen-js-sdk, npm install hydrogen-js-sdk, import Bmob from 'hydrogen-js-sdk', 微信小程序 Bmob, Cocos Creator Bmob, query.find, query.set, query.save, query.destroy, query.equalTo. NOT for Android native (use bmob-database-android), iOS native (use bmob-database-ios), Flutter / Dart (use bmob-database-flutter), curl / Python / Go / PHP / C# (use bmob-database-restful), or C++ Cocos2d-x (separate skill). If Bmob MCP is configured in the project, call get_project_tables first via bmob-mcp before writing code.
m-binimran/dev-pack/skills/api-design Skill
2★ repoDesign Next.js route handlers and server actions with input validation, correct status codes, error handling, and rate limiting. Use when building an API endpoint, server action, or webhook receiver.
m-binimran/dev-pack/skills/component-scaffold Skill
2★ repoBuild a production React component on shadcn/ui + Tailwind — variants, compound pattern, accessible states, and a clean prop API. Use when creating a new UI component or refactoring a messy one.
m-binimran/dev-pack/skills/state-architect Skill
2★ repoDecide where each piece of state lives — server, client, URL, or form — and avoid duplicating server state into client stores. Use when wiring data flow, adding a store, or when state feels tangled.
r-irbe/proof-skills/skills/_overrides/lean-setup Skill
2★ repoUSE FOR: bootstrapping a fresh leanprover/lean4 clone, repairing elan toolchains, linking stage0/stage1 builds, verifying that `lean` and `lake env lean` agree, cleaning up linked toolchains when done. DO NOT USE FOR: building Mathlib or downstream Lake projects (use @lean-build), bisecting a behavioural regression (use @lean-bisect), authoring a reproducer (use @lean-mwe), writing proofs (use @lean-proof), creating new lakefiles for downstream projects (use @lean-blueprint). TRIGGERS: elan, lean-toolchain, cmake preset, stage0, stage1.
john-data-chen/hermes-agent-backup/skills/creative/architecture-diagram Skill
2★ repoDark-themed SVG architecture/cloud/infra diagrams as HTML.
The same file is in 2 other repositories
john-data-chen/hermes-agent-backup/skills/devops/hermes-config-backup Skill
2★ repoBackup Hermes config, skills, memories, and cron jobs. Exclude secrets. Check for info leakage before compressing.
john-data-chen/hermes-agent-backup/skills/github/codebase-inspection Skill
2★ repoInspect codebases w/ pygount: LOC, languages, ratios.
The same file is in 2 other repositories
john-data-chen/hermes-agent-backup/skills/software-development/simplify-code Skill
2★ repoParallel 3-agent cleanup of recent code changes.
The same file is in 1 other repository
kimgoetzke/coding-agent-configs/skills/improve-codebase Skill
2★ repoFind deepening opportunities in a codebase, informed by the domain language in context.md and the decisions in .ai/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.
maurigre/mgr-method/skills/spec-init Skill
no license2★ repoInitializes a project's SDD (Specification-Driven Development) structure. On an EXISTING project, runs a phased deep analysis with chunking and generates /docs/sdd/ (00-overview to 08-glossary), CONSTITUTION.md and the review rules guide. On an EMPTY project (greenfield), conducts a guided interview about stack/architecture/domain and generates the same artifacts from the choices. Use whenever the user asks to analyze, document or map a project, generate SDD, extract contracts, onboard a repository, start a project from scratch with SDD, or generate instructions for Copilot/Cursor. Prerequisite of the spec-create skill.
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/super-init Skill
no license2★ repoInitialize or audit a project's CLAUDE.md against best-practice criteria. Use on first-time setup ('init', 'set up project', 'first time in this repo'), when scanning a project to create CLAUDE.md, or when refreshing an existing CLAUDE.md against the current state of the codebase. Replaces Claude Code's default /init.
jjw013/tech-debt-skill/skills/tech-debt-audit Skill
2★ repoAudits a codebase for technical debt across 10 categories (dependencies, documentation, bugs-and-logic, performance, security, test-coverage, dead-code, accessibility, todo-fixme, licensing) and produces a structured findings.md report. Use when a user wants a holistic debt assessment before deciding whether to file tickets or start fixing.
jjw013/tech-debt-skill/skills/tech-debt-fix Skill
2★ repoApplies fixes from a findings.md by grouping findings into non-overlapping file sets and dispatching work in parallel when the harness supports it. One branch per group; never auto-merges; always asks whether to modify directly or produce patches. Respects hard guardrails for high-risk paths.
jjw013/tech-debt-skill/skills/tech-debt-tickets Skill
2★ repoConverts a findings.md (produced by tech-debt-audit) into one ticket markdown file per finding. Supports a user-supplied ticket-template.md override at the project root. After writing files, offers to push tickets to a ticketing API (Jira, GitHub, GitLab, Linear) — but never pushes without explicit consent.
jjw013/tech-debt-skill/skills/using-tech-debt-skills Skill
2★ repoEntry point and router for the tech-debt skill pack. Routes the user to the right workflow (audit, tickets, fix) based on intent. Use when a user mentions technical debt, debt audit, debt review, or debt cleanup — this skill decides which of the three workflow skills applies.
vignesh2027/AI-AGENT-SKILLS/skills/architecture-design Skill
2★ repoDesign systems at the right scale with explicit trade-off documentation