Loading...
Loading...
Found 3,022 Skills
Use when creating temporary files, drafts, experiments, or any content that should not be committed to version control. Ensures proper placement in .claude/.scratch with gitignore configuration.
This skill provides Zig memory management guidance. It ensures proper use of defer/errdefer patterns, allocators, and leak detection. Essential for writing Zig code with dynamic allocation, fixing memory leaks, implementing resource cleanup, and working with allocators.
Securely manages API credentials for multiple providers (Anthropic Claude, Google Gemini, GitHub). Use when skills need to access stored API keys for external service invocations.
Generate and edit draw.io diagrams in XML format with proper font settings, arrow placement, and Japanese text support. Use when creating flowcharts, architecture diagrams, sequence diagrams, or any visual diagrams in .drawio format. Handles font family settings, arrow layering, text sizing, and PNG export validation.
Best practices for using Vercel Workflow DevKit. Use when creating, modifying, or debugging workflows, steps, hooks, webhooks, or any durable function using the Workflow DevKit. Ensures proper usage of directives, error handling, serialization, streaming, and workflow patterns.
Audit and refactor existing SKILLs. Use when improving drafts, fixing quality, or aligning to spec. For creating new skills from scratch use skill-creator (anthropics/skills).
Implement secure error handling to prevent information leakage and provide appropriate error responses. Use this skill when you need to handle errors in API routes, prevent stack trace exposure, implement environment-aware error messages, or use the error handler utilities. Triggers include "error handling", "handle errors", "error messages", "information leakage", "stack trace", "handleApiError", "production errors", "error responses".
Creates GitHub pull requests in draft mode following Conventional Commits format. Use when user requests "create PR", "make pull request", "open PR", or similar. Automatically pushes branch, analyzes changes, generates structured title/body with proper labels, and assigns to creator. Never modifies code or merges branches.
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false
Validate code changes by intelligently selecting and running the appropriate test suites. Use this when editing code to verify changes work correctly, run tests, validate functionality, or check for regressions. Automatically discovers affected test suites, selects the minimal set of venvs needed for validation, and handles test execution with Docker services as needed.
Mobile-first UI components including bottom navigation, bottom sheets, pull-to-refresh, and swipe actions. Touch-optimized with proper gesture handling.
Use when creating Storybook play functions, writing interaction tests in stories, or reviewing play function code in pull requests. Ensures consistent structure, proper query priorities, correct async handling, and best practices for Storybook interaction testing.