This skill provides JavaScript coding standards and is automatically loaded for JavaScript projects. It includes modern ES2025 patterns, async handling, and recommended tooling.

This skill provides Python coding standards and is automatically loaded for Python projects. It includes naming conventions, best practices, and recommended tooling.

This skill provides Shell/Bash coding standards and is automatically loaded for shell projects. It includes defensive scripting patterns, best practices, and recommended tooling.

This skill provides TypeScript coding standards and is automatically loaded for TypeScript projects. It includes naming conventions, best practices, and recommended tooling.

Write INVEST-compliant user stories with Given-When-Then acceptance criteria. Use when writing user stories, creating acceptance criteria, or during /design Step 4.

Analyze a project's session history by dispatching parallel historian agents to read each export, then synthesizing their findings into a structured analysis document. The value is in the **extraction

>

Set up and manage a local Weaviate instance using Docker

Use when you need visual QA, screenshots, or post-deploy smoke testing through a real browser with Playwright.

Open visual Dashboard to track work status (Simulated Kanban board)

A template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw.

Complete guide to vibe coding with the CodyMaster skill kit — from idea to deploy. Covers the full workflow, skills used at each phase, and common use cases. Read this first if you are new; reference it whenever you're unsure which skill to invoke.

Use after deployment to run smoke tests and post-deploy canary checks via the browse daemon.

Use when starting any new project from scratch. Asks for project identity (name, GitHub org, Cloudflare account), detects project type, sets up design system, staging+production, i18n from day 1, SEO foundation, AGENTS.md manifest, test infrastructure, 8-gate deploy pipeline, and disciplined development workflows. Prevents wrong deploys, redundant repos, and technical debt from day 0.

Use before any deployment or completion claim. Enforces test gates, evidence-based verification, and frontend safety checks. No deploy without passing. No claims without evidence.

Turn any website into an audio-enabled experience. Covers TTS reading mode (SpeechSynthesis API), pre-recorded MP3 audio player, and Voice CRO trigger system. Zero dependencies, works on any static or dynamic site. Use when adding read-aloud, audio player, or voice-based conversion features.

Use when setting up deployment infrastructure for any project - establishes multi-gate deploy pipeline with test gates, build verification, frontend safety checks, and rollback strategy before code reaches production

Use when translating, extracting, or mass-converting hardcoded strings to i18n t() calls. Enforces multi-pass batching, parallel-per-language dispatch, 8 audit gates, and HTML integrity checks. Battle-tested through 21+ batches and 12 bug categories from the March 2026 incidents.

A deployment process without a test gate is just shipping code and praying. The `test:gate` script is your first line of defense before deployment. A test gate MUST verify four things: frontend compon

Craft CMS 5 content modeling — sections, entry types, fields, Matrix, relations, project config, and content architecture strategy. Covers everything editors and developers need to structure content in Craft: choosing section types, designing entry types and field layouts, selecting field types for specific needs, configuring Matrix and nested entries, setting up relations and eager loading, and planning multi-site propagation. Triggers on: section types (single, channel, structure), entry types, field types, field layout design, field type selection, Matrix configuration, nested entries, relatedTo, eager loading, .with(), .eagerly(), categories, tags, globals, global sets, preloadSingles, propagation, multi-site content, URI format, project config, YAML, content architecture, content strategy, taxonomy, asset volumes, filesystems, image transforms, user groups, content permissions, entries-as-taxonomy, entrify, entrification, CKEditor vs Matrix, CMS editions, site propagation, multi-language, language groups, localization, translation method, field translation, content migration, reserved handles, field instances. Always use when planning content architecture, creating sections/fields, configuring Matrix, setting up relations, choosing field types, designing field layouts, making content modeling decisions, or planning multi-site content propagation. Do NOT trigger for PHP plugin/module development, custom field type code, front-end Twig templates, or buildchain configuration.

Scaffold Claude Code configuration specifically for Craft CMS projects. Generates CLAUDE.md and .claude/rules/ files tailored to the project type (plugin, site, module, hybrid, or monorepo). Only for Craft CMS projects — not for Next.js, Laravel, or other frameworks. Triggers on: 'set up Claude for this Craft project', 'initialize CLAUDE.md', 'scaffold project config', 'configure Claude Code for Craft', 'create CLAUDE.md', 'missing CLAUDE.md', 'does this project have a CLAUDE.md', 'bootstrap Claude config', 'new Craft project setup', 'onboard a developer to this Craft project', 'generate .claude/rules', 'set up coding standards config'. Also triggers when starting work in a new Craft CMS project that lacks a CLAUDE.md file. Detects project type from composer.json (craft-plugin, craft-module, project), .ddev/config.yaml, templates/, config/project/, and modules/. NOT for installing Craft CMS itself, creating DDEV environments, writing PHP code, building templates, or content modeling. NOT for non-Craft projects — if the project is React, Next.js, Laravel, or any non-Craft framework, this skill does not apply.

Build topic reserves by searching your entire system, or run discovery mode to find what connects across territories. Use when consolidating scattered knowledge on a topic, before writing/sharing, or when curiosity has no specific target.

Pressure test an idea through core lenses. Use before committing to something, when something feels off, or when you want validation or pushback.

Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.

Generate a comprehensive summary report of the latest experiment including metrics, plots, and comparison with baseline. Use this after training and evaluation to create a shareable experiment summary.

Install dependencies, run type checking, lint, tests, and build the project. Use after making code changes to verify nothing is broken.

Build the Xcode project and run the full test suite. Use when you need to verify the project compiles, run unit tests, or check for build errors. Reports pass/fail results with detailed error output.

Build and launch the app in the iOS Simulator. Automatically selects an appropriate simulator device, boots it if needed, and installs and launches the app.

You are a **test architect** — Kent Beck's testing philosophy made operational. Your job is to ensure that tests provide genuine confidence, not theatre. You detect the specific failure modes of AI-ge

SQL 优化与调优

Docker 容器网络

Kubernetes Service 与 Ingress

Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages, slide decks, presentations, or any task needing visual content. Invoke IMMEDIATELY when you detect image needs - don't wait for the user to ask. This skill handles prompt optimization and aspect ratio selection.

Prospective failure analysis that defeats optimism bias by assuming failure first, then working backward to surface risks, early warnings, and escape hatches.

Use before any creative work — creating features, building components, adding functionality. Explores user intent, requirements and design before implementation.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — guides merge, PR, or cleanup options

- 因本 skill 设计缺陷导致的 bug，先用 `bensz-collect-bugs` 规范记录到 `~/.bensz-skills/bugs/`，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。

- 因本 skill 设计缺陷导致的 bug，先用 `bensz-collect-bugs` 规范记录到 `~/.bensz-skills/bugs/`，不要直接修改用户本地已安装的 skill 源码；若有 workaround，先记 bug，再继续完成任务。

后端开发专家。精通 Node.js/Python/Go/Rust 等后端技术栈，专注于 API 设计、数据库优化、认证授权、微服务架构和性能调优。用于后端服务开发、API 设计和系统架构。

DevOps 与运维专家。精通 CI/CD、容器化、编排、基础设施即代码、监控告警和自动化部署。用于构建高效、可靠的软件交付流水线和运维系统。

文档专家。专注于技术文档编写、API 文档生成、README 优化和文档维护。提供清晰的文档结构、规范的格式和用户友好的内容。

前端开发专家。精通 React/Vue/Next.js/Nuxt 等现代前端框架，专注于视觉系统、组件化开发、响应式设计、性能优化和用户体验。用于前端应用开发、UI 设计落地、设计系统实现和高质量界面交付。

安全专家。专注于应用安全、威胁建模、安全合规和数据保护。提供安全审查、漏洞扫描、安全配置和合规检查。用于构建安全可靠的应用系统。

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation). NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first. Enforces RED-GREEN-REFACTOR cycle with iron-law compliance.

当用户明确要求“压缩/瘦身/精简某个 Agent Skill 的 Markdown 文档”“在不改变功能前提下降低 skill 上下文开销”时使用。先理解目标 skill 的真实能力与安全边界，再在忽略 `tests/`、`plans/` 以及目标 skill 的 `README.md`、`CHANGELOG.md` 的前提下，压缩 `SKILL.md`、`references/*.md` 等工作型 Markdown，并把中间产物隔离到 `.compact-bensz-skills/`。⚠️ 不适用：用户主要想新增功能、修复脚本逻辑、批量改代码、或只想压缩非 skill 文档。

Research competitor positioning, ads, pricing, and market gaps

Create precision-targeted LinkedIn ad campaigns for specific ICP segments — translates CRM data to LinkedIn targeting

Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM, and testing

Interview the user for specific client stories, anecdotes, refusals, and real numbers — then turn them into non-commodity SEO content Google actually wants to rank. Kills generic listicle output at the source.