AgentScripts

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

ALWAYS invoke this skill when writing, editing, or generating ANY Rust code. This skill provides comprehensive Rust best practices from 5 authoritative sources (Microsoft guidelines, official API guidelines, style guide, language reference, and design patterns). Use for ALL Rust tasks including: writing new code, reviewing code, refactoring, fixing bugs, designing APIs, error handling, unsafe code, FFI, async patterns, macros, testing, or library development. This skill should be loaded proactively whenever Rust (.rs) files are involved.

Reference documentation for the Todoist Sync API. Use this skill when building integrations with Todoist, implementing sync functionality, or needing to understand Todoist API endpoints for tasks, projects, labels, filters, reminders, comments, workspaces, and user management. Load the relevant reference file(s) based on the resource type you're working with.

Use when writing or editing prose documents (READMEs, design docs, PR descriptions, blog posts, comments-as-prose, status updates, emails, wiki pages). Avoids the patterns that make text read as AI-generated. NOT for writing code — this is about documents.

Use when the user wants to brainstorm, iterate on a draft, plan an approach, or think something through together. Triggers on phrases like "let's think through", "help me plan", "brainstorm with me", "let's iterate", or when the user shares a draft/idea and asks for input. Drives the conversation through opinionated AskUserQuestion calls anchored in personas. Optional user-supplied steering input is treated as an extra prompt that shapes personas and focus.

Use when the user wants to build an implementation plan and a matching `/goal` prompt to drive Claude Code through it autonomously. Triggers on phrases like "plan and goal", "/plan-and-goal", "build a plan and a goal prompt", or when the user asks to scope a task into a plan file plus a goal directive. Produces a plan markdown file in /tmp and a self-contained goal prompt that points back at the plan.

Use when writing or modifying any Python code, including small local edits, single-line bug fixes, refactors, and new features. Applies on every Python change, not only large restructures.

Use when the user wants to install a skill from this AgentScripts repo into their global `~/.claude/skills/` directory by creating a symlink. Triggers on phrases like "symlink the skill", "install this skill globally", "link the <name> skill", or "/symlink-skill <name>". Creates `~/.claude/skills/<skill-name>` pointing to `./.claude/skills/<skill-name>` in this repo so edits in the repo take effect everywhere.

Create and edit presentation slides using Slidev framework when user requests slides, presentations, or deck modifications