Architecture & codebase
12,717 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
grimoire-rs/grimoire/.claude/skills/swarm-plan Skill
7★ repoUse for feature planning, task decomposition, multi-perspective research, or ADR scaffolding. Tier (`low | auto | high | max`) scales research depth, architect model, and review breadth. Canonical research primitive for AI config / ADR work.
grimoire-rs/grimoire/catalog/skills/ai-config-authoring Skill
7★ repoCraft effective AI agent configuration — skills, rules, agents, and instructions — for any AI coding client. Use when writing or reviewing a SKILL.md, rule file, or agent definition; when deciding between a skill, rule, hook, or always-on instruction; when a config file grows past its context budget; or when a skill description fails to trigger.
grimoire-rs/grimoire/catalog/skills/grim-usage Skill
7★ repoDrive the grim CLI — the OCI package manager for AI skills, rules, agents, and bundles. Use when installing, updating, searching, or publishing AI-config artifacts with grim; when composing grim init, config, add, lock, install, update, status, context, fetch, describe, search, tui, mcp, build, release, publish, login, logout, or completions commands; when configuring settings, multiple registries, or qualified alias/repo references; or when resolving registries, project vs global scope, client targets, or offline mode.
grimoire-rs/grimoire/test/manual/catalog/skills/architecture-guide Skill
7★ repoSketch a module layout and pick design patterns for a new feature. Use when asked to plan an architecture, choose between approaches, or document a design decision before implementation. The walkthrough starts from the feature's user-visible behaviour and works inward, mapping each responsibility onto a module with a single reason to change, then weighs candidate patterns against the codebase's existing conventions rather than introducing novelty for its own sake. It covers strategy traits for swappable behaviour, facade seams that keep business logic out of the CLI layer, and three-layer error chains so batch operations diagnose failures per item. Every recommendation closes with the rejected trade-offs, so the design note doubles as an auditable decision record. This deliberately verbose description gives the manual rig one artifact whose detail pane overflows a small terminal — open it in grim tui and scroll with the arrow keys or j/k.
figueroaignacio/ignaciofigueroa.dev/.agents/skills/improve-codebase-architecture Skill
7★ 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 10 other repositories
Marketplace integration helper
WesleySmits/agent-skills/.agent/skills/marketplace-integration-helper Skill
no license7★ repoGenerates boilerplate for e-commerce API integrations. Use when the user asks about WooCommerce, Shopify, Bol.com, or Etsy APIs, webhooks, product sync, or order handling.
WesleySmits/agent-skills/.agent/skills/react-component-architect Skill
no license7★ repoScaffolds React/Next.js components with TypeScript, CSS modules, tests, and Storybook stories. Use when the user asks to create a React component, generate component boilerplate, or mentions component architecture.
WesleySmits/agent-skills/.agent/skills/vue-component-architect Skill
no license7★ repoScaffolds Vue/Nuxt components with Composition API, CSS modules, Vitest tests, and Storybook stories. Use when the user asks to create a Vue component, generate component boilerplate, or mentions Vue 3 architecture.
WolframResearch/system-modeler-ai-toolkit/modelica-model-architecture Skill
7★ repoArchitecture and structuring guidance for Wolfram System Modeler / Modelica (.mo) models and libraries. Use this skill BEFORE writing equations whenever creating, implementing, structuring, or refactoring a model or library, to decide component decomposition, connectors, component reuse, file/folder layout, units, and naming. Triggers on phrases like 'create/build a Modelica model', 'implement this model/paper in Modelica', 'make a WSM model', 'write a Modelica library', 'structure/architect this model', 'single .mo file vs directory', 'split this into components', 'refactor this model/library', or any decomposition / connector / component-reuse / file-layout decision. Whenever you are about to write a multi-class library, consult this skill first to choose directory-form (one class per file) storage rather than a single monolithic .mo. Complements the validate/simulate/diagnose/annotate Modelica skills; for assembling a specific component library (e.g. create-hydraulic-model) defer to that domain skill.
OdinMB/ops-workflow/skills/scaffold Skill
6★ repoSet up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
martin1847/evolab/skills/repo-governance-bootstrap Skill
6★ repo一次性初始化适合 AI 协作开发的轻量工程治理骨架(docs/INDEX、ADR、module、roadmap、ACTIVE_CONTEXT、AGENTS.md / CLAUDE.md)。新仓库 / 文档结构混乱 / 项目内文档治理初始化时调用。【定位】独立可用、不需要多 agent 编排;也是 cto-orchestration 新项目接入的第一步,但小项目只做文档治理时单独用即可。一次性建结构,区别于循环跑的 cto-orchestration。
JasonCodeMaker/Agentic-Research-Control-Panel/skills/research-init Skill
no license6★ repoUse when installing, attaching, initializing, repairing, or validating ARC in a research workspace.
ndisisnd/msg/.claude/skills/msg Skill
6★ repoRoot menu for msg skills, plus harness modes. `--init` is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo (scaffolds devkit/ and root files via a batched interview; idempotent, never overwrites). Other modes: `--init-staging` (add a staging branch + flip release flow to staged), `--update` (re-scan an already-bootstrapped repo for new init components and unclassified PRDs, with a warning gate before any full reinit), `--gui` (local PRD board), `--help` (guided skill picker).
konglong87/methodology-skills/skills/mvp-first Skill
6★ repoUse when user requests complex systems involving multiple modules or subsystems - like 'build a XX system', 'design XX architecture', or 'implement XX with multiple features'. Triggers to prevent over-engineering before validating core assumptions.
Aysnc-Labs/angora/.claude/skills/angora-design-system-init Skill
6★ repoInitialize a brand-new Angora design system from scratch — run the creative-direction interview (audience, feel, domain vocabulary, signature element, dark-mode opt-in), translate into OKLCH tokens (palette, type scale, spacing, shadows, radii), and build the foundational design-system pages (buttons, icons, grid, cards, forms). Trigger when the project is uninitialized — `system.md` has `[TBD]` or `[Placeholder]` values, or `global.css` tokens are unset — or when the user explicitly wants to start, restart, or kick off the design system. Phrases like 'initialize the design system', 'our tokens are still placeholder', 'start Angora from scratch', 'set up the tokens and type scale', 'where do we begin on this project' all trigger this.
thettwe/nyann/skills/check-prereqs Skill
6★ repoSurvey the machine and report which nyann features are usable right now. TRIGGER when the user says "is my machine ready for nyann", "what do I need to install", "check my setup", "do I have the right tools", "check prereqs", "audit my environment", "new machine, what's missing", "I'm on a new machine", "install nyann prereqs", "/nyann:check-prereqs". Do NOT trigger on general "what is nyann" questions — those want a docs pointer, not a machine survey. Do NOT trigger when the user is already mid-bootstrap — let the bootstrap-project skill handle that case and emit its own skip records for missing stack tools.
thettwe/nyann/skills/explain-state Skill
6★ repoSummarize what nyann currently sees in this repo: stack detection, active profile, branching strategy, hook status, CLAUDE.md, and recent commits. TRIGGER when the user says "what does nyann think is set up here", "show nyann state", "explain the setup", "what's the current config", "what's the active profile", "describe this repo's nyann setup", "what's wired up", "show me the repo state", "/nyann:explain-state". Do NOT trigger on "what does this repo do" (that's a docs intent — route to CLAUDE.md / README), "is this repo healthy" (that's the `doctor` skill), or "what's in the X profile" (that's `inspect-profile`).
thettwe/nyann/skills/gen-claudemd Skill
6★ repoRegenerate the nyann-managed block in CLAUDE.md from the current profile, stack detection, and doc plan — without re-running a full bootstrap or retrofit. TRIGGER when the user says "regenerate CLAUDE.md", "update CLAUDE.md", "refresh CLAUDE.md", "rebuild CLAUDE.md", "re-gen CLAUDE.md", "my CLAUDE.md is stale", "CLAUDE.md doesn't match my profile", "sync CLAUDE.md with the profile", "/nyann:gen-claudemd". Do NOT trigger on "optimize CLAUDE.md" / "trim CLAUDE.md" / "what's unused" — that's the `optimize-claudemd` skill (usage-analytics-driven). Do NOT trigger on "explain CLAUDE.md" / "what's in CLAUDE.md" — that's `explain-state`. Do NOT trigger on initial project setup — that's `bootstrap-project`.
thettwe/nyann/skills/gen-dependency-updater Skill
6★ repoGenerate a Dependabot or Renovate config (`.github/dependabot.yml` or `renovate.json`) for the active stack with sensible defaults (weekly schedule, minor+patch grouping, open-PR cap at 5). Preview- before-mutate: prints the rendered config and exits without writing unless `--apply` is passed. Idempotent: same content is a no-op, different content shows a diff and refuses to overwrite without `--force-overwrite`. TRIGGER when the user says "add dependabot", "enable dependabot", "add renovate", "set up renovate", "configure dependency updates", "automate dependency updates", "scaffold dependabot.yml", "create renovate.json", "add automated dependency PRs", "wire dependency bot", "turn on dependency updates", "/nyann:gen-dependency-updater". Do NOT trigger on "update my dependencies" / "run npm update" — that's a one-off package-manager invocation, not config scaffolding. Do NOT trigger on "fix this dependabot PR" — that's a workflow inside a specific PR, not config generation.
thettwe/nyann/skills/gen-devcontainer Skill
6★ repoGenerate a `.devcontainer/devcontainer.json` keyed to the project's primary language so `gh codespace create` (or VS Code's "Reopen in Container") gives anyone on the team a ready-to-go env with the right runtime, GH CLI, git-lfs, and language-tier VS Code extensions pre-installed. Preview-by-default; idempotent on apply (no-op on identical bytes, diff-and-refuse on divergence unless `--force-overwrite`). TRIGGER when the user says "add a devcontainer", "set up codespaces", "scaffold devcontainer.json", "reopen in container", "configure dev environment", "containerized dev env", "make this work in codespaces", "add VS Code container", "wire up devcontainer", "/nyann:gen-devcontainer". Also trigger when a user asks "how do I run this in Codespaces" and there's no `.devcontainer/` directory yet. Do NOT trigger on "build a Docker image for production" — that's a Dockerfile concern outside devcontainer scope. Do NOT trigger on "fix my devcontainer build" — that's debugging an existing setup, not generating one (read the file with the user instead).
thettwe/nyann/skills/inspect-profile Skill
6★ repoExplain in plain English what a nyann profile enables — stack, branching, hooks, extras, conventions, documentation. TRIGGER when the user says "what does the nextjs-prototype profile do", "explain the python-cli profile", "show me what <name> enables", "what's in profile X", "describe the <name> profile", "inspect profile X", "/nyann:inspect-profile". Do NOT trigger on "show this repo's setup" — that's the `explain-state` skill (reads the repo, not a profile file). Do NOT trigger on "apply profile X to this repo" — that's `bootstrap-project`. Do NOT trigger on "save this setup as a profile" — that's `learn-profile`.
thettwe/nyann/skills/learn-profile Skill
6★ repoInspect a reference repo and save its nyann-relevant setup (stack, hooks, branching, commit convention, extras) as a reusable profile. TRIGGER when the user says "save this setup as a profile called X", "learn a profile from ~/projects/foo", "capture this repo's setup as my-profile", "make a profile from this repo", "turn this repo into a profile", "extract a profile from <path>", "remember this setup as <name>", "/nyann:learn-profile". Do NOT trigger on "what does this profile do?" — that's `inspect-profile`. Do NOT trigger on "apply profile X to this repo" — that's `bootstrap-project`. Do NOT trigger on "fix drift" — that's `retrofit`.
thettwe/nyann/skills/migrate-profile Skill
6★ repoSwitch this repository from one nyann profile to another. TRIGGER ON: 'switch profile', 'migrate profile', 'change this repo profile', 'switch from X to Y', 'change profile to', 'migrate from', 'use a different profile', 'switch to nextjs', 'switch to python'. Computes a diff between source and target profiles, previews all hook/config/convention changes, and applies via bootstrap.
thettwe/nyann/skills/route-docs Skill
6★ repoChange where project documentation is stored — local files, Obsidian vault, Notion workspace, or a per-type split — and regenerate the doc scaffold to match. TRIGGER when the user says "change doc routing", "switch docs to Obsidian", "move docs to Notion", "route docs locally", "change documentation storage", "reroute docs", "switch from local to Obsidian", "set up doc routing", "change where docs are stored", "/nyann:route-docs". Do NOT trigger on "bootstrap this project" — bootstrap runs doc routing as one step of the full pipeline. Do NOT trigger on "generate CLAUDE.md" — that's `gen-claudemd`. Do NOT trigger on "optimize CLAUDE.md" — that's `optimize-claudemd`.
thettwe/nyann/skills/settings Skill
6★ repoInteractive settings menu for nyann preferences. View current values in a table, then pick one setting to change at a time via AskUserQuestion. Re-runnable anytime — does not require a full setup wizard. TRIGGER when the user says "change nyann settings", "nyann preferences", "configure nyann settings", "update my preferences", "toggle triage", "disable sentinel", "enable session triage", "/nyann:settings", "show nyann settings", "nyann config". ALSO trigger on direct shortcut: "/nyann:settings <key> <value>" — skip the menu and write the value directly. Do NOT trigger on "/nyann:setup" — that is the first-run wizard. Do NOT trigger on "/nyann:check-prereqs" — that inspects host tools, not nyann config.
thettwe/nyann/skills/setup Skill
6★ repoFirst-run onboarding for nyann. Creates the user config directory, collects preferences through AskUserQuestion interactive pickers, and writes ~/.claude/nyann/preferences.json. TRIGGER when the user says "set up nyann", "configure nyann", "nyann setup", "onboard me", "first time using nyann", "initialize nyann", "nyann first run", "get nyann ready", "/nyann:setup". ALSO trigger when: the user runs any nyann command for the first time and ~/.claude/nyann/preferences.json does not exist — suggest running setup first, but don't block them. Do NOT trigger on "set up this project" or "bootstrap this repo" — those are bootstrap-project. Do NOT trigger on "check prereqs" — that is check-prereqs. This skill configures nyann itself, not a repo.
thettwe/nyann/skills/undo-bootstrap Skill
6★ repoReverse a bootstrap or retrofit run by walking its BootRecord manifest: restore pre-state files, drop branches that were created, surface anything that couldn't be safely undone. TRIGGER when the user says "undo the bootstrap", "undo nyann setup", "revert nyann setup", "uninstall nyann from this repo", "back out the bootstrap", "undo the retrofit", "I regret running bootstrap", "rip out nyann", "/nyann:undo-bootstrap". ALSO trigger when the user wants to roll back a /nyann:retrofit run that drifted things they didn't expect — retrofit remediation goes through bootstrap.sh, so its boot record is in the same place. DISAMBIGUATION: this is NOT `/nyann:undo` — that one rewinds git commits on a feature branch via `git reset`, completely separate from filesystem mutations bootstrap made. If the user just said "undo my last commit", route to `/nyann:undo` instead. Do NOT trigger on "uninstall the plugin" — that's a Claude Code plugin manager concern, not a per-repo undo. Do NOT trigger on "remove .git" / "delete the repo" — undo-bootstrap explicitly refuses to remove .git/ because doing so destroys all of the user's git state, not just bootstrap's.
KraitDev/skiLL.Md/skills/backend/api-design-rest Skill
6★ repoWhen creating or extending an HTTP API for client consumption.
KraitDev/skiLL.Md/skills/backend/error-handling-architecture Skill
6★ repoWhen designing how a system recovers from and reports failures.
KraitDev/skiLL.Md/skills/dev-tools/ci-cd-pipeline-architecture Skill
6★ repoWhen configuring automated build, test, and deployment workflows for a repository.
vignesh2027/Claude-Agentic-Skills2.0-version/onboarding-designer Skill
6★ repoActivates OnboardingDesigner for user and customer onboarding experience design. Use when you need to design a product onboarding flow that minimizes time-to-value, create an in-app onboarding checklist or tour, design a customer onboarding sequence for B2B SaaS, build an email onboarding drip campaign, or analyze onboarding funnel drop-off and recommend improvements.
vignesh2027/Claude-Agentic-Skills2.0-version/rag-architect Skill
6★ repoActivates the RAG-Architect agent for designing and building Retrieval-Augmented Generation systems. Use this skill when you need to build a document Q&A system, design a knowledge base with semantic search, set up vector stores (Chroma, Pinecone, pgvector), implement hybrid retrieval (dense + BM25 sparse), add re-ranking, or generate grounded answers with source citations and hallucination detection. Outputs complete Python code for the full RAG pipeline.
vignesh2027/Claude-Agentic-Skills2.0-version/system-architect Skill
6★ repoActivates SystemArchitect for high-level software system design and architecture review. Use when you need to design a new system from scratch (define components, APIs, data flows), review an existing architecture for scalability or reliability issues, choose between architectural patterns (monolith vs microservices, event-driven vs request-response), design for high availability and disaster recovery, or create a technical architecture document.
Minara-AI/media-agent/skills/media-setup Skill
6★ repoInteractive wizard to configure platform connections, API keys, and dependencies for media-agent. Detects available tools, walks through setup for each platform, tests connections, and writes config files. Run this before any other media-agent skill.
yeaight7/agent-powerups/plugins/codebase-intelligence/skills/managed-codebase-context Skill
6★ repoUse when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
yeaight7/agent-powerups/plugins/codebase-maintenance/skills/architecture-simplification Skill
6★ repoUse when a codebase carries over-engineered abstractions, unnecessary layers, or redundant logic that should be collapsed without changing behavior.
yeaight7/agent-powerups/plugins/codebase-maintenance/skills/context-retrieval-loop Skill
6★ repoUse when about to refactor, rename, or remove code, assessing dead code before deletion, or unsure of the blast radius of a change.
yeaight7/agent-powerups/plugins/codebase-maintenance/skills/dead-code-removal Skill
6★ repoUse when unused functions, classes, exports, or files need to be identified and safely deleted.
yeaight7/agent-powerups/plugins/codebase-maintenance/skills/safe-refactor Skill
6★ repoUse when code needs restructuring without changing observable behavior.
yeaight7/agent-powerups/plugins/codebase-maintenance/skills/test-preserving-refactor Skill
6★ repoUse when code needs restructuring and observable behavior must stay unchanged, with existing tests kept green at every step.
yeaight7/agent-powerups/plugins/dev-vitals/skills/repo-map Skill
6★ repoUse when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.
yeaight7/agent-powerups/plugins/documentation-systems/skills/architecture-decision-records Skill
6★ repoUse when a significant architectural choice is being finalized, revisited, or reversed -- technology selection, structural patterns, or trade-offs that future maintainers or agents might unknowingly undo.
yeaight7/agent-powerups/plugins/documentation-systems/skills/readme-hardening Skill
6★ repoUse when a README cannot be followed verbatim -- setup or test commands fail or are vague, environment requirements are unstated, or a new engineer or agent cannot bootstrap the project quickly.
yeaight7/agent-powerups/plugins/security-guardrails/skills/agent-config-security-audit Skill
6★ repoUse when modifying agent config files, committing configuration changes, onboarding a repository with existing agent configs, or running a periodic config hygiene check.
yeaight7/agent-powerups/plugins/software-engineering/skills/codebase-migration-batches Skill
6★ repoUse when a wide refactor or migration is too large to ship as one change — API renames across many files, framework or config migrations, or mechanical codemod-backed refactors that need reviewable batches.
yeaight7/agent-powerups/plugins/tool-integrations/skills/managed-codebase-context Skill
6★ repoUse when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
yeaight7/agent-powerups/skills/agent-config-security-audit Skill
6★ repoUse when modifying agent config files, committing configuration changes, onboarding a repository with existing agent configs, or running a periodic config hygiene check.
yeaight7/agent-powerups/skills/architecture-decision-records Skill
6★ repoUse when a significant architectural choice is being finalized, revisited, or reversed -- technology selection, structural patterns, or trade-offs that future maintainers or agents might unknowingly undo.
yeaight7/agent-powerups/skills/architecture-simplification Skill
6★ repoUse when a codebase carries over-engineered abstractions, unnecessary layers, or redundant logic that should be collapsed without changing behavior.
yeaight7/agent-powerups/skills/codebase-migration-batches Skill
6★ repoUse when a wide refactor or migration is too large to ship as one change — API renames across many files, framework or config migrations, or mechanical codemod-backed refactors that need reviewable batches.
yeaight7/agent-powerups/skills/dead-code-removal Skill
6★ repoUse when unused functions, classes, exports, or files need to be identified and safely deleted.
yeaight7/agent-powerups/skills/managed-codebase-context Skill
6★ repoUse when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
yeaight7/agent-powerups/skills/readme-hardening Skill
6★ repoUse when a README cannot be followed verbatim -- setup or test commands fail or are vague, environment requirements are unstated, or a new engineer or agent cannot bootstrap the project quickly.
yeaight7/agent-powerups/skills/repo-map Skill
6★ repoUse when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.
yeaight7/agent-powerups/skills/safe-refactor Skill
6★ repoUse when code needs restructuring without changing observable behavior.
yeaight7/agent-powerups/skills/test-preserving-refactor Skill
6★ repoUse when code needs restructuring and observable behavior must stay unchanged, with existing tests kept green at every step.
DYAI2025/Plumbline/config/claude/skills/ai-native-prd-architect Skill
no license6★ repoUse when turning a feature idea into an implementation-ready PRD with traceable REQ IDs, acceptance criteria, NFRs, risks, data model, and task slices for /agileteam Phase 0.
AhmedHabiba/architor/.claude/skills/challenge-assumptions Skill
6★ repoAdversarial reviewer personality for architecture discussions. Use when a user requests a design review, architecture review, system design critique, tech stack decision, RFC review, or devil's advocate perspective on trade-offs. Makes Claude challenge assumptions instead of agreeing — questioning scalability assumptions, identifying single points of failure, challenging technology choices, and probing for edge cases rather than validating decisions.
AhmedHabiba/architor/templates/claude/skills/architecture-methodology Skill
6★ repoEnforces 4-phase architecture design workflow. Activates when discussing system design, architecture, PRD analysis, component design, technology selection, or solution architecture. Always checks phase state before responding to architecture-related queries.
AhmedHabiba/architor/templates/claude/skills/architecture-patterns Skill
6★ repoKnowledge base for architecture patterns, trade-offs, and selection criteria. Activates when recommending or evaluating architecture patterns like microservices, monolith, serverless, event-driven, CQRS, or hybrid approaches.