发现 Skills

This skill should be used when developing, testing, or securing Helm charts for Kubernetes. Use it when the user asks to create a Helm chart, add Helm tests, sign a Helm chart, push a chart to an OCI registry, migrate to Helm 4, write values.schema.json, set up helm-unittest, or configure chart dependencies. Do NOT use this for general Kubernetes manifests without Helm (use kubectl or kustomize instead).

Atheris is a coverage-guided Python fuzzer based on libFuzzer. Use for fuzzing pure Python code and Python C extensions.

Advanced database design and administration for PostgreSQL, MongoDB, and Redis. Use when designing schemas, optimizing queries, managing database performance, or implementing data patterns.

Kafka, RabbitMQ, SQS/SNS, event sourcing, CQRS, saga patterns, dead letter queues, and idempotency. Use when designing asynchronous systems, implementing message-driven workflows, or building event streaming pipelines.

Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.

Formatted digital recipe card generation with ingredient scaling, nutritional information, and organized collections. Use when creating recipe cards, meal plans, grocery lists, or recipe collections.

Use this skill when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Apply it to identify code smells, architectural problems, dependency issues, missing documentation, security vulnerabilities, and to produce comprehensive technical debt documentation.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Teaches agents how to bridge the gap between raw data and self-evident visual narrative. Covers encoding meaning through shape, color, animation, and layering — so the 'why' is visible before a word is read. Mandatory for ANALYST (speccing), DESIGNER (layout and encoding), and BUILDER (implementation) when working on any analytics chart or dashboard panel. This is the 'connect the dots' skill.

Expert guidance for Vapor 4+ development, focusing on async/await, Fluent, and content negotiation.

Create and manage Raycast Snippets automatically. Use this skill when the user wants to save a prompt, template, or text snippet to their Raycast configuration.

从 Markdown 文件中自动提取并下载 Twitter 图片，生成可直接发布的版本。 当用户说"下载推文图片"、"提取Twitter图片"、"download twitter images"时触发。

Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.

Sync GitHub PRs, merges, and releases to PM workspace. Use when running /sync-github or /sync-dev commands, or generating release notes.

Implement Tree Items in the Umbraco backoffice using the official documentation

brainbase運用の統合ガイド（7 Skills統合版）。プロセス管理・_codex正本管理・環境変数管理・ブランチ/Worktree運用・開発サーバー起動・バージョン管理・launchd運用を統合。brainbase-ops-safety、codex-validation、env-management、branch-worktree-rules、worktree-dev-server、brainbase-ui-version、brainbase-ui-launchd-gotchasの7 Skillsを1つに集約し、運用時の参照を効率化。

brainbaseワークフロー検証用Orchestrator。要件分析→検証レポート生成の2 Phase workflowでプロジェクトワークフローの課題を特定。

Drives implementation with strict TDD and proves the resulting tests actually catch bugs via mutation testing. Use when implementing any feature, fixing any bug, refactoring code that has tests, or changing observable behavior. Use when the user says "implement", "add", "fix", "make it do X", "change how Y works", or asks "do my tests actually catch bugs". Do not use for pure config changes, documentation, or spike code committed for deletion.

Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.

Configure Supabase authentication providers (OAuth, JWT, email). Use when setting up authentication, configuring OAuth providers (Google/GitHub/Discord), implementing auth flows, configuring JWT settings, or when a user mentions Supabase auth, social login, authentication setup, or auth configuration.

Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, observability, token economics, ROI frameworks, and build-vs-not decision guidance (modern best practices)

Specialized role for performing E2E visual and interactive testing of ADK agents using the browser subagent and automation tools like Playwright.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

Quick architecture compliance check against CLAUDE.md principles. Use to validate code changes or audit specific paths.