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
Orfi/trackbed/claude/skills/trackbed-init Skill
3★ repoInternal one-time planning pipeline for Trackbed. Turns a Jira epic — or a standalone project — into an optional PRD, optional ADRs, an ordered roadmap, and (optionally) tickets, then locks the storage format in the manifest. Invoked by trackbed when no roadmap exists. Skippable when a roadmap already exists. Never user-invoked directly; never drives execution.
Orfi/trackbed/copilot/skills/trackbed-init Skill
3★ repoInternal one-time planning pipeline for Trackbed. Turns a Jira epic — or a standalone project — into an optional PRD, optional ADRs, an ordered roadmap, and (optionally) tickets, then locks the storage format in the manifest. Invoked by trackbed when no roadmap exists. Skippable when a roadmap already exists. Never user-invoked directly; never drives execution.
hec-ovi/agentickit/.pilot/skills/install-and-setup Skill
3★ repoInstall agentickit into an existing React app (Next.js App Router is the happy path; Bun / Cloudflare Workers / Hono also work). Wire the server route, the provider, and the sidebar. Use when a consumer says "add agentickit to my app" or "getting started".
hec-ovi/agentickit/.pilot/skills/write-a-consumer-skill Skill
3★ repoAuthor a SKILL.md inside a consumer app's own `.pilot/` folder. Covers the scaffold CLI (`agentickit init` / `agentickit add-skill`), the frontmatter shape (Anthropic + gbrain superset), the RESOLVER.md routing table, and the binding contract that ties each SKILL.md to a registered `usePilotAction`. Use when a consumer wants to expose capabilities as editable markdown.
Nembie/claude-code-skills/skills/auth-scaffold Skill
3★ repoScaffold authentication with Auth.js (NextAuth v5), including providers, session handling, middleware protection, and role-based access. Use when asked to set up auth, add login, protect routes, or implement authentication.
The same file is in 2 other repositories
Nembie/claude-code-skills/skills/env-config-validator Skill
3★ repoValidate environment configuration files, detect missing or misconfigured variables, and generate typed env schemas. Use when asked to validate env files, check environment config, generate .env.example, audit env variables, or create typed env validation.
Nembie/claude-code-skills/skills/typescript-refactorer Skill
3★ repoIdentify TypeScript code smells and suggest type-safe refactoring. Use when asked to refactor, improve types, clean up TypeScript code, tighten types, reduce any usage, or improve type safety.
The same file is in 2 other repositories
myksyut/pev-harness/skills/pev-bootstrap-codex Skill
3★ repoOpenAI Codex CLI を pev-harness の external reviewer (Verify phase) / external executor (Execute phase) として導入する one-time setup skill。 codex CLI install 確認 (npm i -g @openai/codex または brew install --cask codex)、 CODEX_API_KEY 環境変数の存在確認、 codex exec --json で sanity test、 settings.local.json の PEV_REVIEWER_MODE / PEV_EXECUTOR_MODE 雛形提案までを 1 操作で完了する。 v1.4 pev-bootstrap-playwright + v1.9 pev-bootstrap-project と並列の sibling。
myksyut/pev-harness/skills/pev-bootstrap-playwright Skill
3★ repopev-harness を使うプロジェクトに Playwright を導入する自動 bootstrap skill。 npm install / browser binary / playwright.config.ts template / seed test template / `npx playwright init-agents --loop=claude` (Playwright agents 自動生成) の 5 step を 1 操作で完了する。 pev-e2e-verify skill の Preflight が「未setup」と判定した時に自動的に提案される。
myksyut/pev-harness/skills/pev-bootstrap-project Skill
3★ repopev-harness を使うプロジェクトに必要な初期 file を 1 操作で生成する skill。 言語/構成 検知 (Node/Python/Go/Rust + E2E config) で team-conventions.md の Verification commands を auto-populate、 .gitignore に .pev-artifacts/ を追記、 オプションで .linear-config / settings.local / 個人 override skeleton を AskUserQuestion 経由で対話的に生成。 既存 file 衝突は「上書き / merge / skip」分岐。
GhostlyGawd/recursive-harness/skills/loop-prompt-architect Skill
3★ repoConsultant procedure for authoring self-contained loop prompts. Trigger when the user asks for a prompt that runs "until it's done/verified/bug-free", wants /goal + /loop templates, says "loop Claude until X is finished", needs a fuzzy goal turned into checkable done-criteria, or returns with a failed loop-run to autopsy. Forges wishes into 3-7 binary Definition-of-Done criteria, per-iteration verification, a state artifact, a stuck protocol, and three exits (success/budget/blocked). AUTHORS loop prompts as deliverables — NOT the built-in /loop runner, NOT build-loop.
syncfusion/react-ui-components-skills/skills/syncfusion-react-blockeditor Skill
no license3★ repoImplement the Syncfusion React BlockEditor component for block-based content editing. Use this skill for block-based rich content editing, document creation, CMS interfaces, markdown alternatives, editor setup, block configuration, toolbar or menu customization, drag-and-drop behavior, formatting options, APIs, accessibility, real-time collaborative editing with Yjs integration, user presence and remote cursors, document version history and snapshot management in React.
unix2dos/skills/code-refactor Skill
3★ repoUse when refactoring Go code for better structure, maintainability, extensibility, or testability - follows SOLID principles and idiomatic Go patterns
PranavNagrecha/Salesforce-Intelligence/.claude/skills/architect-async-and-events Skill
3★ repoSalesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.
PranavNagrecha/Salesforce-Intelligence/.claude/skills/architect-cross-org-compare Skill
3★ repoSalesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.
PranavNagrecha/Salesforce-Intelligence/.claude/skills/architect-impact-analysis Skill
3★ repoSalesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.
Architect integration topology
PranavNagrecha/Salesforce-Intelligence/.claude/skills/architect-integration-topology Skill
3★ repoSalesforce Org Intelligence for AI agents - a read-only, offline, source-available MCP server and CLI answering metadata, dependency, permission, Apex and Flow questions grounded in real retrieved org metadata.
PranavNagrecha/Salesforce-Intelligence/.claude/skills/developer-apex-refactor Skill
3★ repoAnswers code-source-focused developer questions across the full org code surface: Apex classes, Apex triggers, and the v1.4 frontend tier (LWC, Aura, Visualforce). Triggers: "where is field X used in Apex", "find LWC components reading this field", "what calls this Apex from VF", "Aura references to this object", "who reads/writes this field from code", "what classes call MyClass.someMethod", "is it safe to rename this method", "find all Apex references to this", "what Apex/LWC/VF touches this object". Call `sfi.run_analysis` with `{ "name": "sfi.find_code_usages", "args": { … } }` (incoming readsFrom/writesTo/callsApex/references edges from ApexClass, ApexTrigger, LightningComponentBundle, AuraDefinitionBundle, VisualforcePage, or VisualforceComponent nodes) — the single code-usage tool. For strictly Apex-only questions, narrow it with `nodeTypes: ['ApexClass','ApexTrigger']` (the former `find_apex_usages` Apex-only view, now folded in). Optionally follows up with `sfi.search_apex_source` to surface the actual lines. Discloses the heuristic-confidence boundary explicitly: string-BUILT dynamic SOQL, dynamic field access, reflective `get()`, LWC `record[fieldName]` dynamic access, and Aura framework attributes are invisible to the scanners (inline static SOQL and constant-string `Database.query` fields ARE resolved at parsed confidence by the default-on AST pass); heuristic matches need a human spot-check before refactor commits.
Eipi-Tong/agentic-coding-starter-kit/.claude/skills/refactor Skill
no license3★ repoPlan and execute a code refactor with preserved behaviour. Use when the user asks to refactor, clean up, simplify, extract, or reorganise existing code without changing what the app does.
rolandbrecht/agent-skills/structural-refactor Skill
3★ repoUse this skill for any structural code search or replacement task — it is the right choice whenever grep/sed would feel clunky or risky. Trigger on ANY of these patterns: **Structural find-and-replace across a codebase:** "replace all fetch(url, options) calls with the new fetchWithRetry signature", "rename the first argument of every logger.log call from msg to message", "swap the argument order of this helper across all files" **Cross-language or multi-format refactoring:** "update this API pattern in all .js and .ts files", "change all SQL SELECT * to SELECT col1, col2 in our query templates", "modernize these HTML button attributes" **Code migration / deprecated API patterns:** "migrate all createStore() calls to configureStore()", "update all axios.get(url) to the new axios({url, method}) form", "Python 2 print statements to Python 3 print() functions across the whole project", "modernize old Python 2 idioms to Python 3" **Safe multi-file replacements that regex would botch:** multiline expressions, nested parentheses, string literals that contain the search term, balanced brackets **Extracting structural patterns with JSON output for scripting:** "find all function calls that pass a hardcoded string as the first argument", "list every TODO comment with its location" Trigger keywords: structural replace, comby, code migration, refactor pattern, swap arguments, rename parameter, update API calls, deprecated pattern, multi-file replace, across all files, Python 2 to 3, 2to3, pyupgrade, modernize Python. Do NOT trigger for: pure text/string searches (use grep), AST-level semantic analysis like dead code or circular imports (use ast-code-graph), single-file edits you can just read and edit directly.
Immoderate-humulin783/odoo-skills/skills/odoo Skill
no license3★ repoOdoo engineering workflows for addon development, codebase exploration, debugging, architecture/refactor review, manifest/docs sync, and routing to migration work. Use when the user mentions Odoo, addons, modules, manifests, models, XML views, security CSVs, record rules, Odoo shell, OWL/QWeb/assets, or when an Odoo codebase is detected.
Information architecture navigation
hueyexe/frontend-agent-skills/information-architecture-navigation Skill
3★ repoUse when organizing, critiquing, or implementing navigation, labels, taxonomy, hierarchy, search, content grouping, or wayfinding for a digital product.
madnpc/skills/skills/codebase-design Skill
no license3★ repo适用于设计或优化模块接口、决定 seam、提升模块深度与可测试性。Use when designing or improving module interfaces, deciding where a seam belongs, deepening a module, or improving testability and AI navigability. 中文关键词:代码库设计、模块设计、接口设计、模块边界、依赖边界、可测试性、代码重构。
ligyDt/ai-ide-init-template/codebuddy/.codebuddy/skills/integration-onboarding Skill
3★ repo安全选择、配置和验证 MCP、插件与外部研发服务。用于接入文档、设计、任务、测试支付或运维能力。
ligyDt/ai-ide-init-template/codebuddy/.codebuddy/skills/monorepo-awareness Skill
3★ repo在单仓多包、多应用、多语言或共享库项目中识别包边界、依赖影响、构建范围和跨包变更风险。
ligyDt/ai-ide-init-template/codex/.agents/skills/architecture-decision Skill
3★ repo形成可追溯的技术与集成决策记录。用于选择技术栈、定义接口或数据边界、评估第三方依赖、确定存储与运行方式,或在多个实现方案之间需要明确取舍及验证依据时。
ligyDt/ai-ide-init-template/codex/.agents/skills/integration-onboarding Skill
3★ repo安全选择、配置和验证 MCP、插件、连接器与外部研发服务。用于需要接入官方文档、代码托管、设计、浏览器、任务管理、文档产物、测试支付或未来部署监控能力,并需界定授权与非生产验证方式时。
ligyDt/ai-ide-init-template/codex/.agents/skills/monorepo-awareness Skill
3★ repo在单仓多包、多应用、多语言或共享库项目中识别包边界、依赖影响、构建范围和跨包变更风险。
ligyDt/ai-ide-init-template/cursor/.cursor/skills/architecture-decision Skill
3★ repo记录技术选型、接口边界、数据流、第三方依赖和关键取舍。用于影响后续实现或运行方式的决定。
ligyDt/ai-ide-init-template/cursor/.cursor/skills/integration-onboarding Skill
3★ repo安全选择、配置和验证 MCP、插件与连接器。用于接入文档、代码托管、设计、任务、支付测试或部署监控能力时。
ligyDt/ai-ide-init-template/cursor/.cursor/skills/monorepo-awareness Skill
3★ repo在单仓多包、多应用、多语言或共享库项目中识别包边界、依赖影响、构建范围和跨包变更风险。
ligyDt/ai-ide-init-template/skills/ai-ide-init-template Skill
3★ repo将 AI IDE Init Template 的初始化能力安装到 Codex、Cursor、CodeBuddy 或 TRAE 项目中。用于新项目需要直接接入项目上下文、角色分工、流程 Skills、安全边界、MCP 基线、Hooks 和离线验证脚本,或只安装跨工具通用 Skills 时。
ligyDt/ai-ide-init-template/trae/.agents/skills/architecture-decision Skill
3★ repo记录技术选择、接口边界、数据流、第三方依赖和回退依据。用于关键架构取舍。
ligyDt/ai-ide-init-template/trae/.agents/skills/integration-onboarding Skill
3★ repo安全选择和验证 MCP、插件或外部研发能力。用于接入公开文档、代码托管、设计、任务、支付测试或运维能力。
ligyDt/ai-ide-init-template/trae/.agents/skills/monorepo-awareness Skill
3★ repo在单仓多包、多应用、多语言或共享库项目中识别包边界、依赖影响、构建范围和跨包变更风险。
tayyabexe/skills/skills/hugging-face-jobs Skill
3★ repoThis skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tokens, secrets management, timeout configuration, and result persistence. Designed for general-purpose compute workloads including data processing, inference, experiments, batch jobs, and any Python-based tasks. Should be invoked for tasks involving cloud compute, GPU workloads, or when users mention running jobs on Hugging Face infrastructure without local setup.
The same file is in 27 other repositories
Axect/skills/xkcd-py Skill
3★ repoGenerate a Python matplotlib plot script following the user's mandatory xkcd style — `with plt.xkcd():` context, `pparam = dict(...)` axis-config, raw-string LaTeX labels, wide canvas (`figsize=(10, 6)`), `dpi=300` savefig. Supports parquet / CSV / NumPy (`.npy`, `.npz`) and four variants: single line, multi-line + legend, scatter / errorbar, multi-panel subplots. Writes the `.py` only — does NOT execute it; the user runs it (typically `uv run`). Use when asked to write an xkcd-style / hand-drawn / sketch-style matplotlib script, plot data in xkcd style from parquet / CSV / `.npy`, scaffold an xkcd line / scatter / errorbar / subplot script, or match the lab's xkcd template. Triggers on: xkcd plot, xkcd matplotlib, xkcd style, hand-drawn / sketch plot, plt.xkcd, comic-style plot; xkcd 플롯, xkcd 그래프, 손그림 그래프, 스케치 스타일 플롯, xkcd 스크립트, xkcd 코드.
rshade/agent-skills/skills/design-principles Skill
3★ repoAudit a codebase against well-known software design principles: SOLID, DRY, YAGNI, KISS, Law of Demeter, Separation of Concerns, Composition over Inheritance, and the code-relevant 12-Factor subset. Scores findings by impact and effort, runs adversarial debate on contested violations, and generates a prioritized DESIGN_AUDIT.md. Use when reviewing code quality beyond what linters catch, assessing design health before a refactor, or onboarding to an unfamiliar codebase. Can be invoked standalone or delegated from tech-debt.
The same file is in 2 other repositories
rshade/agent-skills/skills/tech-debt Skill
3★ repoSystematic technical debt analysis across architecture, testing, documentation, and infrastructure. Investigates the codebase, scores findings by impact and effort, and generates a prioritized TECH_DEBT.md remediation plan. Delegates to specialized skills for code quality (scout) and linting (lint-fix). Use when assessing overall project health, planning cleanup sprints, or onboarding to an unfamiliar codebase.
The same file is in 2 other repositories
Sameeh07/AGENT-SKILLS/skills/expo-tailwind-setup Skill
no license3★ repoSet up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling
The same file is in 9 other repositories
7bata/claude-workflow-kit/plugins/workflow/skills/scaffold Skill
2★ repo在当前项目目录里铺设方法论脚手架(CLAUDE.md + docs 七件套 + .gitignore + README)。后端技术栈固定为 Go(版本基线见 skill 内表格),数据库由 Claude 按项目意图判断。用户说"搭脚手架/初始化项目/开新项目/scaffold"时触发。
Ed3Design/ed3design-engineering-bundles/cad-design/skills/fusion-mcp-bridge Skill
2★ repoUse when driving Fusion 360 from Claude Code through the local MCP-Bridge (HTTP server on 127.0.0.1:7654 with bearer-token auth, single-threaded Custom-Event handler). Covers the API quirks that consistently bite without a documented protocol: component activation before geometry, single-revolve over loft+combine-join, cut-before-shell sequencing, tool-body combine-cut for complex cuts, boolean-union before cuts on multi-body components, bridge timeout/lock recovery, screenshot setup, and the `fusion` CLI that replaces curl boilerplate. Trigger on phrases like "Fusion 360 via MCP", "fusion-mcp-bridge", "Fusion Custom-Event", "run Fusion API script", or any `fusion` CLI command. Do NOT load for general parametric CAD (use `cad-construction`), mechanical-design rules (use `mechanical-design-principles`), or OpenSCAD/FreeCAD (use `cad-api-scripting`).
Victron cerbo modbus device onboarding
Ed3Design/ed3design-engineering-bundles/embedded-systems/skills/victron-cerbo-modbus-device-onboarding Skill
2★ repoUse when a new Victron Modbus-TCP device (EV Charging Station, energy meter, inverter) is connected to the Cerbo GX LAN but does not appear in the Cerbo UI or D-Bus, despite being reachable via ping. Trigger on phrases like "EVCS not visible in Cerbo", "new Modbus device does not appear", "Cerbo does not detect wallbox", "dbus-modbus-client does not find device", "Victron device not showing in GX", "Cerbo Device List empty even though device is on the network". Do NOT load for VE.Can/VE.Bus devices (different bus protocol), for Cerbo-Setup-from-scratch (different skill scope), or for VRM cloud connectivity problems.
cheukswiss/etdxm/.claude/skills/team-bootstrap Skill
2★ repo首次创建 Teammate 的引导流程——太子首次协作或尚书首次派发六部时加载,完成 Team 创建与分层启动
qte77/claude-code-plugins/plugins/codebase-tools/skills/hardening-codebase Skill
2★ repoAudit and tighten codebase quality gates — architecture, lint, types, tests, docs, code review. Use when onboarding a project, before a release, or when validation is too permissive.
qte77/claude-code-plugins/plugins/codebase-tools/skills/researching-codebase Skill
2★ repoInvestigates codebase before planning. Use before any non-trivial implementation task to gather context in isolation.
The same file is in 1 other repository
qte77/claude-code-plugins/plugins/cpp-desktop/skills/analyzing-cpp-codebase Skill
2★ repoAnalyzes C++ desktop codebase architecture, dependency graphs, framework detection, and migration assessment. Use when exploring an unfamiliar C++ project or assessing upgrade paths.
ajaygunalan/flow-friction/skills/index-codebase Skill
no license2★ repoBuild the documentation index for a codebase from scratch — README, diagrams, markdown files, AGENTS.md
ajaygunalan/flow-friction/skills/walkthrough Skill
no license2★ repoGenerate a D2 diagram that explains how a codebase feature, flow, or architecture works. Designed for fast onboarding — a visual mental model readable in under 2 minutes. Use when asked to walkthrough, explain a flow, trace a code path, show how something works, or explain the architecture.
Paretofilm/superpowers-gstack/skills/ios-e2e-scaffold Skill
no license2★ repoOne-shot XCUITest scaffolding for iOS SwiftUI apps: audits the Scene tree, generates ranked TIER-1/2/3 stubs, suggests accessibility identifiers, emits an xcresult runner. Manual only — modifies project files.
Paretofilm/superpowers-gstack/skills/macos-e2e-scaffold Skill
no license2★ repoOne-shot XCUITest scaffolding for macOS SwiftUI apps: audits the project, generates ranked TIER-1/2/3 stubs, suggests accessibility identifiers, emits an xcresult runner. Manual only — modifies project files.
Paretofilm/superpowers-gstack/skills/setup-routing Skill
no license2★ repoGenerate a tailored CLAUDE.md with routing rules for the Superpowers + GStack workflow. Asks about project type, evaluates relevant skills from both frameworks, and produces a project-specific routing plan.
launch52-ai/flutter-template/.claude/skills/feature-init Skill
2★ repoInitialize new feature with Clean Architecture folder structure and skeleton files. Creates scaffold for domain, data, and presentation layers with TODOs. Use AFTER /plan to create the initial structure, then run /domain and /data to fill in details.
launch52-ai/flutter-template/.claude/skills/init Skill
2★ repoInitialize a new Flutter project. Gathers requirements, runs flutter create, adds dependencies, configures environment, and sets up main.dart. Run this first when creating a new app.
launch52-ai/flutter-template/.claude/skills/social-login Skill
2★ repoGoogle Sign-In and Apple Sign-In with Supabase or custom backend. OAuth setup, platform config, PKCE/nonce security, sealed Failures, mock repository. Use when adding social login or troubleshooting OAuth.
fernando-bertholdo/4-successful-AI-life/plugins/ui-excellence/skills/systems/refactoring Skill
2★ repoAudit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off", "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent design tokens, creating dark mode themes, improving data visualization clarity, or polishing UI details before launch. Covers grayscale-first workflow, constrained design scales, shadows, and component styling. For typeface selection, see web-typography. For usability audits, see ux-heuristics.
RockyHong/super-bootstrap/plugins/super-bootstrap/skills/harness-bootstrap Skill
2★ repoInstall or sync the generic harness runway in any repo — greenfield or with code present. Scaffolds CLAUDE.md, skeleton docs (overview, techstack, work/), path-scoped rules, and core plugin pins; bakes in doc-sync discipline. On greenfield it writes empty product skeletons; stack-matched skill/MCP/hook curation is gated tier-2, orchestrated by /super-bootstrap; opt-in earn-gated scale module (parked + test-queue containers, venue-map rule, backlog fact fields). Monorepo tier fans path-scoped rules out per package; adopt mode retires superseded harness forks on re-run. Solo dev workflow.
RockyHong/super-bootstrap/plugins/super-bootstrap/skills/release-init Skill
2★ repoDetect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.
RockyHong/super-bootstrap/plugins/super-bootstrap/skills/super-bootstrap Skill
2★ repoPublic entry for the super-bootstrap pipeline — thin orchestrator. Git-inits if absent, then dispatches /super-bootstrap:harness-bootstrap to install or sync the generic runway (always; the runway self-detects fresh-vs-sync). Checks whether seed docs are substantive: greenfield seeds three GAP cards (overview, techstack, tech-curation) via /super-bootstrap:log and stops at the resolve gate; substantive seed docs run gated tier-2 tech curation (resolve-plugins + release-init). Zero product prework. Solo dev workflow.
giacomogaglione/claude-awesome-stack/stacks/python-ml/skills/notebook-refactor Skill
2★ repoExtract Jupyter notebook cells into tested Python modules while preserving the exploration workflow. Use when converting prototyping notebooks into production code.