agentsclimarketplace

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

  • Configuration strategy

    SWEStash/swe-workflow-skills/plugins/backend/skills/configuration-strategy Skill

    1★ repo

    Design environment configuration, secrets management, and feature-flag hierarchy for a service or feature. Triggers: config strategy, environment variables, .env, secrets management, feature flag, config hierarchy, config precedence, twelve-factor config, environment-specific settings.

  • Refactoring

    SWEStash/swe-workflow-skills/plugins/backend/skills/refactoring Skill

    1★ repo

    Systematic code improvement via design principles, smell detection, and safe transformation patterns. Triggers: refactor this, clean this up, simplify this code, reduce complexity, extract this, this code is messy, tech debt, improve this code, code smell, rename, extract function, dead code.

  • Frontend architecture

    SWEStash/swe-workflow-skills/plugins/designer/skills/frontend-architecture Skill

    1★ repo

    Design frontend architecture — React component hierarchy, state management, design tokens, data fetching, routing, error boundaries, code organization. Triggers: component architecture, state management, design system, design tokens, component library, React structure, folder structure, Zustand vs Redux, React Query, code splitting, error boundary, compound component.

  • Configuration strategy

    SWEStash/swe-workflow-skills/plugins/devops/skills/configuration-strategy Skill

    1★ repo

    Design environment configuration, secrets management, and feature-flag hierarchy for a service or feature. Triggers: config strategy, environment variables, .env, secrets management, feature flag, config hierarchy, config precedence, twelve-factor config, environment-specific settings.

  • Dx audit

    SWEStash/swe-workflow-skills/plugins/em/skills/dx-audit Skill

    1★ repo

    Audit and improve developer experience — inner-loop feedback (build/test/reload times), CI wait and queue times, flaky tests, local environment setup, onboarding time-to-first-PR, tooling friction, docs discoverability; produce a prioritized remediation plan. Triggers: developer experience, DX audit, devex, builds are slow, CI takes forever, flaky tests, onboarding takes weeks, tooling friction, developer productivity, engineers are frustrated. Code health/debt hotspots → technical-debt-review; designing one pipeline → cicd-pipeline.

  • Technical debt review

    SWEStash/swe-workflow-skills/plugins/em/skills/technical-debt-review Skill

    1★ repo

    Strategic codebase health assessment — identify hotspots, categorize debt, produce remediation roadmap.

  • Api design

    SWEStash/swe-workflow-skills/plugins/frontend/skills/api-design Skill

    1★ repo

    Design RESTful and GraphQL APIs — endpoint naming, request/response contracts, error handling, pagination, versioning, auth patterns, OpenAPI specs. Triggers: design the API, API contract, REST API, GraphQL schema, error response format, pagination, API versioning, OpenAPI, swagger, endpoints. Use architecture-design for REST-vs-GraphQL or monolith-vs-microservices decisions.

  • Code slop cleanup

    SWEStash/swe-workflow-skills/plugins/frontend/skills/code-slop-cleanup Skill

    1★ repo

    Strip AI slop from a branch diff before PR — judge each hunk against the surrounding file's conventions, remove without changing behavior, re-run tests. Removal only: hunting bugs → code-reviewing; structural improvement → refactoring; repo-wide audit → technical-debt-review; pruning tests → test-suite-design.

  • Frontend architecture

    SWEStash/swe-workflow-skills/plugins/frontend/skills/frontend-architecture Skill

    1★ repo

    Design frontend architecture — React component hierarchy, state management, design tokens, data fetching, routing, error boundaries, code organization. Triggers: component architecture, state management, design system, design tokens, component library, React structure, folder structure, Zustand vs Redux, React Query, code splitting, error boundary, compound component.

  • Refactoring

    SWEStash/swe-workflow-skills/plugins/frontend/skills/refactoring Skill

    1★ repo

    Systematic code improvement via design principles, smell detection, and safe transformation patterns. Triggers: refactor this, clean this up, simplify this code, reduce complexity, extract this, this code is messy, tech debt, improve this code, code smell, rename, extract function, dead code.

  • Api design

    SWEStash/swe-workflow-skills/plugins/mobile/skills/api-design Skill

    1★ repo

    Design RESTful and GraphQL APIs — endpoint naming, request/response contracts, error handling, pagination, versioning, auth patterns, OpenAPI specs. Triggers: design the API, API contract, REST API, GraphQL schema, error response format, pagination, API versioning, OpenAPI, swagger, endpoints. Use architecture-design for REST-vs-GraphQL or monolith-vs-microservices decisions.

  • Mobile architecture

    SWEStash/swe-workflow-skills/plugins/mobile/skills/mobile-architecture Skill

    1★ repo

    Design mobile app architecture — native (Swift/Kotlin) vs cross-platform (React Native/Flutter) selection, navigation and deep linking, state management, offline-first design and data sync, local persistence, push notifications, platform constraints (background work, battery, permissions). Triggers: mobile app architecture, iOS app, Android app, React Native or Flutter, offline first, data sync, mobile state management, deep linking, push notifications, app structure. Web SPA component architecture → frontend-architecture.

  • Code slop cleanup

    SWEStash/swe-workflow-skills/plugins/qa/skills/code-slop-cleanup Skill

    1★ repo

    Strip AI slop from a branch diff before PR — judge each hunk against the surrounding file's conventions, remove without changing behavior, re-run tests. Removal only: hunting bugs → code-reviewing; structural improvement → refactoring; repo-wide audit → technical-debt-review; pruning tests → test-suite-design.

  • Configuration strategy

    SWEStash/swe-workflow-skills/plugins/security/skills/configuration-strategy Skill

    1★ repo

    Design environment configuration, secrets management, and feature-flag hierarchy for a service or feature. Triggers: config strategy, environment variables, .env, secrets management, feature flag, config hierarchy, config precedence, twelve-factor config, environment-specific settings.

  • Api design

    SWEStash/swe-workflow-skills/skills/api-design Skill

    1★ repo

    Design RESTful and GraphQL APIs — endpoint naming, request/response contracts, error handling, pagination, versioning, auth patterns, OpenAPI specs. Triggers: design the API, API contract, REST API, GraphQL schema, error response format, pagination, API versioning, OpenAPI, swagger, endpoints. Use architecture-design for REST-vs-GraphQL or monolith-vs-microservices decisions.

  • Architecture design

    SWEStash/swe-workflow-skills/skills/architecture-design Skill

    1★ repo

    Guide architectural and structural decisions using Architecture Decision Records (ADRs) — new services, pattern choices, database selection, component boundaries, state management, costly-to-reverse decisions. Triggers: how should I architect, which pattern, design decision, should I use X or Y, system design, ADR, component design, architectural trade-off. Owns internal-structure decisions — build vs buy/adopt a vendor or OSS capability → build-vs-buy.

  • Architecture documentation

    SWEStash/swe-workflow-skills/skills/architecture-documentation Skill

    1★ repo

    Design and maintain architecture documentation with multi-level diagrams (C4) and docs-as-code. Triggers: architecture diagram, document the architecture, C4 diagram, system context, container diagram, component diagram, architecture docs, docs-as-code, PlantUML, Structurizr, D2, Mermaid architecture, infrastructure diagram, runtime flow. Use architecture-design for ADRs.

  • Code archaeology

    SWEStash/swe-workflow-skills/skills/code-archaeology Skill

    1★ repo

    Understand unfamiliar or legacy code before changing it — map entry points, mine git history (blame, churn, log -S), trace data flow, recover the why behind odd code, pin current behavior with characterization tests, find seams for safe change. Triggers: understand this codebase, legacy code, inherited this project, what does this code do, why is it written this way, nobody knows how this works, onboard to this repo, is it safe to change this. Prioritizing debt → technical-debt-review; improving code you already understand → refactoring.

  • Code slop cleanup

    SWEStash/swe-workflow-skills/skills/code-slop-cleanup Skill

    1★ repo

    A comprehensive SWE workflow, encoded. Might be useful to you too.

  • Configuration strategy

    SWEStash/swe-workflow-skills/skills/configuration-strategy Skill

    1★ repo

    A comprehensive SWE workflow, encoded. Might be useful to you too.

  • Dx audit

    SWEStash/swe-workflow-skills/skills/dx-audit Skill

    1★ repo

    Audit and improve developer experience — inner-loop feedback (build/test/reload times), CI wait and queue times, flaky tests, local environment setup, onboarding time-to-first-PR, tooling friction, docs discoverability; produce a prioritized remediation plan. Triggers: developer experience, DX audit, devex, builds are slow, CI takes forever, flaky tests, onboarding takes weeks, tooling friction, developer productivity, engineers are frustrated. Code health/debt hotspots → technical-debt-review; designing one pipeline → cicd-pipeline.

  • Frontend architecture

    SWEStash/swe-workflow-skills/skills/frontend-architecture Skill

    1★ repo

    Design frontend architecture — React component hierarchy, state management, design tokens, data fetching, routing, error boundaries, code organization. Triggers: component architecture, state management, design system, design tokens, component library, React structure, folder structure, Zustand vs Redux, React Query, code splitting, error boundary, compound component.

  • Mobile architecture

    SWEStash/swe-workflow-skills/skills/mobile-architecture Skill

    1★ repo

    Design mobile app architecture — native (Swift/Kotlin) vs cross-platform (React Native/Flutter) selection, navigation and deep linking, state management, offline-first design and data sync, local persistence, push notifications, platform constraints (background work, battery, permissions). Triggers: mobile app architecture, iOS app, Android app, React Native or Flutter, offline first, data sync, mobile state management, deep linking, push notifications, app structure. Web SPA component architecture → frontend-architecture.

  • Refactoring

    SWEStash/swe-workflow-skills/skills/refactoring Skill

    1★ repo

    Systematic code improvement via design principles, smell detection, and safe transformation patterns. Triggers: refactor this, clean this up, simplify this code, reduce complexity, extract this, this code is messy, tech debt, improve this code, code smell, rename, extract function, dead code.

  • Technical debt review

    SWEStash/swe-workflow-skills/skills/technical-debt-review Skill

    1★ repo

    Strategic codebase health assessment — identify hotspots, categorize debt, produce remediation roadmap.

  • Ollygarden otel collector config decomposition

    ollygarden/skills/skills/ollygarden-otel-collector-config-decomposition Skill

    1★ repo

    Decide and execute plain-file decomposition for OpenTelemetry Collector YAML. Use for "should I split this collector config?", "break up this otelcol YAML", "organize it by signal or team", or "create environment overlays". Leaves simple configs intact and proves warranted splits equivalent after merge. Not for Helm, Kustomize, or Terraform packaging; use otel-collector for component facts and ollygarden-otel-collector-config-validation for behavioral proof.

  • Ollygarden otel collector config validation

    ollygarden/skills/skills/ollygarden-otel-collector-config-validation Skill

    1★ repo

    Behaviorally validate an OpenTelemetry Collector processor or connector against realistic telemetry. Use for "does my filter drop the right spans?", "prove this transform before shipping", "validate passes but behavior is wrong", or testing filter, transform, redaction, tail_sampling, routing, signaltometrics, count, or spanmetrics. Running the harness executes a pinned remote container and requires explicit confirmation. Not for syntax lookup (use `otel-collector`/`otel-ottl`), generic telemetry generation (`otel-telemetrygen`), or receiver/exporter testing.

  • Ollygarden otel collector k8s daemonset

    ollygarden/skills/skills/ollygarden-otel-collector-k8s-daemonset Skill

    1★ repo

    OllyGarden's opinionated, optimization-first OpenTelemetry Collector configuration for a Kubernetes node agent (DaemonSet). Use when authoring or reviewing a node-level/agent collector config for logs, metrics, and traces on Kubernetes, or when the user wants to reduce telemetry volume, cost, cardinality, or noise at collection time. Triggers on "collector daemonset config", "node agent collector", "otel collector on kubernetes", "reduce telemetry cost in the collector", "tune kubeletstats/hostmetrics/filelog", "drop noisy spans/logs/metrics in the collector".

  • Ollygarden otel declarative config

    ollygarden/skills/skills/ollygarden-otel-declarative-config Skill

    1★ repo

    Ollygarden's recommended patterns and anti-patterns for OpenTelemetry declarative configuration. Use when reviewing or authoring otel.yaml files, when deciding whether declarative config is right for a project, or when the user asks for "the right way" to configure OpenTelemetry. Triggers on "otel best practices", "otel anti-patterns", "is this otel config correct", "should I use declarative config".

  • Ollygarden otel go setup

    ollygarden/skills/skills/ollygarden-otel-go-setup Skill

    1★ repo

    Ollygarden's recommended pattern for setting up the OpenTelemetry SDK in Go services using otelconf. Covers project structure, the Providers struct, no-op fallback, runtime attribute injection, and the zap log bridge. Use when adding OTel to a Go project, structuring telemetry code, or reviewing an existing setup — including when DB spans show up as trace roots or GORM/database spans are disconnected from HTTP spans. Triggers on "go otel setup", "go telemetry pattern", "Providers struct go otel", "gorm WithContext", "root client span go".

  • Ollygarden otel java setup

    ollygarden/skills/skills/ollygarden-otel-java-setup Skill

    1★ repo

    Ollygarden's recommended pattern for setting up OpenTelemetry in Java services. Covers the Javaagent vs Spring Boot Starter vs manual autoconfigure decision-making, the Maven BOM dependency pattern, and the setup checklist (no query strings in telemetry, startup DB span hygiene, declarative YAML config, standard OTEL_* env vars honored). Use when adding OTel to a Java project, choosing a setup path, or reviewing dependency declarations. Triggers on "java otel setup", "javaagent vs starter", "opentelemetry-bom", "url.query", "query parameter PII".

  • Ollygarden otel js setup

    ollygarden/skills/skills/ollygarden-otel-js-setup Skill

    1★ repo

    Ollygarden's recommended pattern for setting up OpenTelemetry in Node.js services. Covers project structure, which auto-instrumentations to disable, the entry-point ordering, the programmatic NodeSDK fallback, and the setup checklist (no query strings in telemetry, startup/non-request span hygiene, declarative YAML config, standard OTEL_* env vars honored, lean resource with service.instance.id) closed by a required verification report. Use when adding OTel to a Node.js project, structuring telemetry code, or reviewing an existing setup. Triggers on "node otel setup", "NodeSDK pattern", "auto instrumentation node", "url.query", "query parameter PII", "service.instance.id".

  • Ollygarden otel sdk setup

    ollygarden/skills/skills/ollygarden-otel-sdk-setup Skill

    1★ repo

    OpenTelemetry SDK initialization and configuration. Use when setting up or reviewing TracerProvider, MeterProvider, or LoggerProvider; choosing exporters, processors, or propagators; configuring OTLP transport; or extending an existing SDK setup for new signals. Use this skill whenever the task involves wiring up the OpenTelemetry SDK, even if the user only mentions "add tracing" or "set up metrics" without saying "SDK."

  • Manage agent config

    Miyamura80/MCP-Template/.agents/skills/manage-agent-config Skill

    1★ repo

    Manage files under .claude/{skills,agents,rules}/, .agents/{skills,rules}/, or .codex/agents/. Covers dual-tool Claude/Codex layout and reminds to run make sync-agent-config.

  • Onboarding

    Miyamura80/MCP-Template/.agents/skills/onboarding Skill

    1★ repo

    Interview the user, inspect this template repo, run headless onboarding, and prune unused systems so a new project gets running quickly.

  • Login gov

    andreab67/agent-skills/login-gov Skill

    1★ repo

    Integrate with login.gov as a federal identity provider — OIDC and SAML federation, private_key_jwt client authentication, ACR value selection (auth-only, verified, facial-match, PIV/CAC), sandbox and production setup, token flow implementation, user attribute scopes, and Partner Portal configuration. Use this skill whenever the user mentions login.gov, federal SSO, private_key_jwt, IAL2, ACR values, identity proofing, PIV/CAC authentication, the login.gov Partner Portal, or any error from the login.gov IdP — even if they just say "integrate with login.gov" or "federal identity" without more detail.

  • Nextjs monorepo ci

    andreab67/agent-skills/nextjs-monorepo-ci Skill

    1★ repo

    Design, fix, and extend GitLab CI/CD pipelines for Next.js monorepos — multi-stage pipelines (validate, security, build, obfuscate, package, notify), Kaniko image builds, Semgrep SAST/secrets, gitleaks, javascript-obfuscator standalone output, Harbor registry, and IndexNow notify stage. Use this skill whenever the user mentions GitLab CI, a failing CI job, gitleaks, Kaniko, javascript-obfuscator, Harbor push, or any pipeline work in a Next.js monorepo — even if they just say "CI is broken" or "add a new app to the pipeline" without more detail.

  • Setup

    Background-Craft/hydrant-skills/skills/setup Skill

    1★ repo

    First-run install for hydrant-skills — detect the active harness, configure the hosted Hydrant MCP server, write a fenced "Hydrant lifecycle workflow" section into AGENTS.md (and CLAUDE.md if Claude Code), and verify the connection by calling `mcp__hydrant__list_spaces`. Use when the user asks for `/setup`, says "set up hydrant-skills", "install Hydrant MCP", "wire up Hydrant", or runs the toolkit for the first time after `npx skills add`.

  • Texforge

    UniverLab/skills/texforge Skill

    1★ repo

    CLI tool for compiling LaTeX documents to PDF without TeX Live, MiKTeX, or any external LaTeX distribution. Use this skill whenever the user wants to create a LaTeX project, compile .tex files to PDF, format or lint LaTeX documents, manage templates, or work with the texforge CLI. Activate when the user mentions "texforge new", "texforge build", "texforge fmt", "texforge check", "texforge init", "texforge template", creating a thesis or academic document, compiling LaTeX without installing TeX Live, using tectonic as a LaTeX engine, project.toml configuration, or any workflow involving .tex files and the texforge tool.

  • Wiki scaffold

    jpab/maieutic-tools/tools/anamnesis-wiki/skills/wiki-scaffold Skill

    1★ repo

    Creates a baseline wiki for codebases that have not run wiki-bootstrap. Faster and shallower — gets the structure in place without a full Socratic session.

  • Documentation architect

    GustavoGutierrez/engineering-skills/skills/documentation-architect Skill

    1★ repo

    Design scalable, navigable documentation ecosystems for onboarding, architecture, operations, ADRs, runbooks, and reference; use when asked to architect docs, plan information architecture, design doc systems, organize knowledge bases, structure living documentation, or fix documentation fragmentation.

    The same file is in 1 other repository

  • Solution architect

    GustavoGutierrez/engineering-skills/skills/solution-architect Skill

    1★ repo

    Design real technical solution architectures for scalable, secure, cost-aware systems by selecting patterns, components, integrations, data flows, and tradeoffs; use when asked for senior solution architecture, system architecture, SaaS architecture, LLM architecture, or architecture decisions after a spec.

  • Spec architect

    GustavoGutierrez/engineering-skills/skills/spec-architect Skill

    1★ repo

    Design high-level functional and technical specifications by defining scope, modules, contracts, boundaries, responsibilities, architecture models, constraints, and verification criteria.

  • Skill tracker setup

    cnuahs/skill-tracker/skills/skill-tracker-setup Skill

    1★ repo

    Install and configure the skill-tracker plugin. Clone the repo, install the plugin, configure tracked repos, create cron jobs, and verify setup. Safe to re-run for updates.

  • Codebase design

    rmerk/crewai-headless-flow/.agents/skills/codebase-design Skill

    1★ repo

    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

    The same file is in 19 other repositories

  • Improve codebase architecture

    rmerk/crewai-headless-flow/.agents/skills/improve-codebase-architecture Skill

    1★ repo

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    The same file is in 8 other repositories

  • Migrate to shoehorn

    rmerk/crewai-headless-flow/.agents/skills/migrate-to-shoehorn Skill

    1★ repo

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    The same file is in 15 other repositories

  • Request refactor plan

    rmerk/crewai-headless-flow/.agents/skills/request-refactor-plan Skill

    1★ repo

    Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

    The same file is in 13 other repositories

  • Setup pre commit

    rmerk/crewai-headless-flow/.agents/skills/setup-pre-commit Skill

    1★ repo

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    The same file is in 19 other repositories

  • Setup ts deep modules

    rmerk/crewai-headless-flow/.agents/skills/setup-ts-deep-modules Skill

    1★ repo

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    The same file is in 3 other repositories

  • Code cleanup

    looties-io/looties-skills/code-cleanup Skill

    1★ repo

    Safe, behavior-preserving code cleanup and refactoring workflow for recently changed, staged, or user-selected code. Use when asked to clean up code before a commit, improve readability, simplify/refactor without changing behavior, apply project coding conventions, review staged diffs for maintainability issues, or organize small validation-backed cleanup batches.

  • Plg onboarding

    buildwitharup/cortex/skills/plg-onboarding Skill

    1★ repo

    Use when the user wants to design, audit, or optimize a product-led growth (PLG) free-to-paid conversion flow. Also triggers on "free trial conversion", "PLG onboarding", "free-to-paid", "activation rate", "trial users not converting", "product qualified leads", "PQL", "user activation", "time to value", "onboarding flow", "in-app conversion".

  • Grails to ears

    anarefin/ai-agent-skills/grails-to-ears Skill

    no license1★ repo

    Reverse engineer a Grails 2.5.x project into a 100% complete EARS (Easy Approach to Requirements Syntax) specification file. Use this skill when the user wants to extract business requirements from an existing Grails codebase — including single controllers, single action services, multiple controllers/action services, or an entire plugin directory — and produce a standalone, code-free .md EARS file that can serve as a source of truth for regenerating the system in any architecture (DDD, CQRS, Event Sourcing, etc.). The skill also auto-resolves its own Open Questions on the first pass (Step 6.5): a fresh read-only subagent chases each question's breadcrumb footer and folds confident answers back into the spec as finalised statements, leaving only genuinely unresolvable items as [NEEDS REVIEW] — so a separate /resolve-open-questions run is usually unnecessary. Each module and content subsection is annotated with a `> **Source files:**` line listing the full project-relative paths it was extracted from, so a developer can cross-check the spec against the codebase (the EARS statements themselves stay code-free).

  • Springboot to ears

    anarefin/ai-agent-skills/springboot-to-ears Skill

    no license1★ repo

    Reverse engineer a Java Spring Boot project into a 100% complete EARS (Easy Approach to Requirements Syntax) specification file. Use this skill when the user wants to extract business requirements from an existing Spring Boot codebase — including single controllers, multiple controllers, or an entire project directory — and produce a standalone, code-free .md EARS file that can serve as a source of truth for regenerating the system in any architecture (DDD, CQRS, Event Sourcing, etc.). The skill also auto-resolves its own Open Questions on the first pass (Step 6.5): a fresh read-only subagent chases each question's breadcrumb footer and folds confident answers back into the spec as finalised statements, leaving only genuinely unresolvable items as [NEEDS REVIEW] — so a separate /resolve-open-questions run is usually unnecessary. Each module and content subsection is annotated with a `> **Source files:**` line listing the full project-relative paths it was extracted from, so a developer can cross-check the spec against the codebase (the EARS statements themselves stay code-free).

  • Api design

    tdyzzsp47/claude-skills/skills/api-design Skill

    1★ repo

    RESTを中心にAPI設計の全工程(リソース設計・エラー仕様・バージョニング・スキーマファースト)を体系的に進めるスキル。新規API定義・既存APIの見直し・GraphQL/gRPC選択判断が必要なときに使う。

  • Architecture design

    tdyzzsp47/claude-skills/skills/architecture-design Skill

    1★ repo

    要件からアーキテクチャ設計・技術選定・ADR作成までを行うスキル。基本設計フェーズで「どう作るか」の骨格を固めるときに使う。

  • Codebase exploration

    tdyzzsp47/claude-skills/skills/codebase-exploration Skill

    1★ repo

    未知・不慣れなコードベースを目的志向で効率よく理解するスキル。機能追加・バグ修正・レビューの前に全体構造と暗黙の規約を把握したいとき、または変更の影響範囲を事前に調査したいときに使う。

  • Refactoring

    tdyzzsp47/claude-skills/skills/refactoring Skill

    1★ repo

    外部から見た振る舞いを変えずにコードの内部構造を改善するスキル。技術的負債の可視化・優先順位付け・計画的返済も含み、開発速度の維持・回復を目的として使う。

  • Unopim plugin development

    unopim/agent-skills/skills/unopim-plugin-development Skill

    1★ repo

    Plugin and package development for UnoPim. Activates when creating modules/packages, service providers, models, repositories, controllers, routes, ACL, menus, migrations, credentials, cURL HTTP clients, attribute mapping, or scaffolding a third-party connector (WooCommerce, Shopify, Shopware, REST API). Use references: @quickstart (day-1 connector checklist), @core (package structure, service providers, config), @backend (PHP classes, models, repositories, events), @credentials (credential storage, connection testing, history), @http (cURL ApiClient, BasicAuth/OAuth), @mapping (attribute mapping + history).

  • Architect agent

    roronoazoroshao369/vibe-coding-os/skills/agents/architect-agent Skill

    1★ repo

    Vibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.