aka. Agent Skills
Discover skills for AI coding agents. Works with Claude Code, OpenAI Codex, Gemini CLI, Cursor, and more.
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.
Keep project documentation current and optimized for AI agents. Use when user asks to "update docs", "sync documentation", "update CLAUDE.md", "update README", "check documentation freshness", "document recent changes", or "optimize docs for AI".
Provides AI consultation workflows, prompt templates, and best practices for multi-model consultation. Use when user asks for "second opinion", "ask codex", "ask gemini", "AI code review", "external AI consultation", or needs prompt templates for code review, security audit, or architecture analysis.
Retrieve and display message history from Sinch Conversation API. Use when the user asks to show messages, view conversation history, list recent messages, see messages with a contact, check message history, or view last N messages. Supports filtering by contact, conversation, channel, and time range.
Release-please standards and configuration. Use when configuring release-please workflows, checking release automation compliance, or when the user mentions release-please, automated releases, or version management.
Generate project-specific rules and commands from PRDs for Blueprint Development methodology. Use when generating behavioral rules for architecture patterns, testing strategies, implementation guides, or quality standards from requirements documents.
Automatic selection of appropriate test tiers based on change scope. Guides unit tests for small changes, full suite for larger changes. Use when running tests, discussing testing strategy, or after code modifications.
Convert and manipulate images with ImageMagick. Covers format conversion, resizing, batch processing, quality adjustment, and image transformations. Use when user mentions image conversion, resizing images, ImageMagick, magick command, batch image processing, or thumbnail generation.
Modern Node.js development with Bun, Vite, Vue 3, Pinia, and TypeScript. Covers JavaScript/TypeScript projects, high-performance tooling, and modern frameworks. Use when user mentions Node.js, Bun, Vite, Vue, Pinia, npm, pnpm, JavaScript runtime, or building frontend/backend JS applications.
Check available messaging channels, channel capabilities, and channel configuration for Sinch Conversation API. Use when the user asks which channels are available, what channels can be used, how to reach someone, what messaging options exist, or channel capabilities for a contact or app.
CSS custom property architecture, theme systems, design token organization, and component library integration. Use when implementing design systems, theme switching, dark mode, or when the user mentions tokens, CSS variables, theming, or design system setup.
Detects and prevents manual edits to release-please managed files (CHANGELOG.md, version fields in package.json, pyproject.toml, Cargo.toml). Provides conventional commit templates. Use when editing changelogs, version bumps, release files, or when user mentions "release", "changelog", "version bump", or "conventional commits".
Coordinate multi-agent workflows: sequential, parallel, and iterative patterns. Defines agent handoffs, dependencies, communication protocols, and integration. Use when designing multi-agent workflows, coordinating agent handoffs, planning agent dependencies, or building complex agent pipelines.
Structured remote server troubleshooting workflow that follows investigation-only practices until user approval. Use when Claude needs to diagnose issues on remote SSH-accessible servers including k8s clusters, bare metal, and containerized services. Covers service/port access problems, configuration issues, service startup failures, and performance/resource issues. Emphasizes creating helper scripts on remote server, obtaining user approval before fixes, script-based repairs, and generating comprehensive analysis reports.
List Terraform Cloud runs for a workspace with filtering by status, operation type, and date. Use when reviewing run history, finding failed runs, or auditing infrastructure changes. Requires TFE_TOKEN environment variable.
Basedpyright static type checker configuration, installation, and usage patterns. Use when implementing type checking, configuring LSP, comparing type checkers, or setting up strict type validation in Python projects. Triggered by: basedpyright, pyright, type checking, LSP, mypy alternative, static analysis.
Python testing with pytest, coverage, fixtures, parametrization, and mocking. Covers test organization, conftest.py, markers, async testing, and TDD workflows. Use when user mentions pytest, unit tests, test coverage, fixtures, mocking, or writing Python tests.
Write safe context expressions in Claude Code slash command files. Covers backtick expressions, find vs ls patterns, and commands that always exit 0. Use when creating slash commands, writing context sections with backtick expressions, or debugging command execution failures.
Configure Claude Code security settings including permission wildcards, shell operator protections, and project-level access controls. Use when setting up project permissions, configuring allowed tools, or securing Claude Code workflows.
Go-specific container optimization patterns including static binary compilation, scratch/distroless base images, CGO handling, and systematic optimization journey from 846MB to 2.5MB (99.7% reduction). Covers ldflags, trimpath, and build flag optimizations specific to Go applications. Use when working with Go containers, Dockerfiles for Go apps, or optimizing Go image sizes.