gtd-cc

Issue-driven development with worktree isolation. 5-stage pipeline (new, plan, work, review, merge) with human gates between stages. Use when creating tasks, planning, implementing, reviewing, or merging.

Start or join an inter-agent chat session. Two Claude Code sessions communicate via a shared markdown file in tmp/. Use when the user says "ai-chat", "start a chat", "agent chat", or provides a chat slug to join.

View and manage configurations and skills for AI agent CLI tools (Claude Code, Opencode). Use when checking config files, listing or managing skills, viewing model settings, comparing configs across tools, or performing common config operations.

Orchestrate external AI agent instances (Claude Code, Opencode, Gemini CLI) via SDK or CLI. This skill NEVER does work itself — it always delegates to an external agent.

Parse Word documents (.docx) into repository-friendly markdown artifacts. Use when users need to extract content from Word files, convert to markdown, or batch process document directories.

Parse Power BI files (.pbix) into repository-friendly JSON and CSV artifacts. Use when users need to extract metadata, measures, or data model structure from Power BI files.

Parse PDF documents into repository-friendly markdown and text artifacts. Use when users need to extract text, tables, or structure from PDF files.

This skill should be used when the user asks to "convert pptx to markdown", "parse powerpoint presentation", "extract slides to markdown", "convert presentation to markdown with images", "make powerpoint accessible", or needs to transform PowerPoint files into markdown format with inline images and alt-text descriptions.

Parse Excel spreadsheets (.xlsx) into repository-friendly CSV and JSON artifacts. Use when users need to extract data, formulas, or structure from Excel files.

Implement and maintain GitHub project documentation using a layered system. Use when creating, updating, or auditing documentation.

Stateful bidirectional sync for subtree directories using git-subrepo. Sync monorepo subdirs with standalone GitHub repos and graduate projects from lab to production.

Subtree publishing and project graduation. Publish monorepo changes to standalone GitHub repos, graduate projects from lab to production.

Issue-driven development with worktree isolation. Create issues, plan implementations, work in worktrees, review PRs, and merge with clean squash history.

Apply gtd-cc architectural patterns when developing Claude Code plugins or project-local skills. Use when creating or updating plugins for the gtd-cc marketplace, or creating skills in a repo's .claude/skills/ directory.

Brief description of when to use this skill

Obsidian vault management and GTD workflows. Use when integrating with Obsidian vaults, managing notes, organizing knowledge, or supporting Getting Things Done methodology through note-based workflows.

Conduct comprehensive research comparing multiple options, alternatives, or approaches. Use when the user needs to evaluate product comparisons, technology evaluations, vendor selections, strategic alternatives, or any scenario requiring systematic analysis of multiple choices (e.g., baby formulas, project management tools, cloud providers, equipment purchases).

Team-based OpenCode orchestration via local skill scripts. Create teams, spawn teammates, assign tasks, exchange inbox messages, and run shutdown plus health checks.

Fetch and manage Todoist tasks. Use when the user asks about "todoist tasks", "show my tasks", "what's due", "overdue tasks", "triage tasks", or when another skill needs Todoist task context.

Comprehensive GTD task management using Backlog.md CLI

Agent skill for creating and validating Catppuccin theme ports

Use for creating and managing Claude Teams MCP teams/teammates, testing opencode backend teammates, troubleshooting spawn/shutdown behavior, and validating inbox/task flows.

Interactive system resource analysis and troubleshooting for memory, disk, CPU, and performance issues

This skill should be used when the user asks to "validate my collection", "query markdown files", "create mdbase type", "mdbase schema", "init mdbase", "mdbase validate", "mdbase query", or mentions mdbase, typed markdown collections, or frontmatter schemas.

Browser automation for AI agents. Use when the user needs to interact with websites, navigate pages, fill forms, click buttons, take screenshots, extract data, test web apps, or automate any browser task. Triggers include "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data", "test this web app", "login to a site", or any task requiring programmatic web interaction.

Extract documentation and content from websites. Supports Mintlify, Starlight/Astro, Docusaurus, GitBook, ReadTheDocs, Sphinx, and generic sites. Uses a tiered approach - try the simplest method first (direct curl, Jina AI Reader) before falling back to Crawl4AI for JS-heavy sites.

Complete Crawl4AI SDK reference and implementation guide. Use when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns, error handling, and comprehensive code examples.

Multi-step deep research workflow that breaks complex topics into subtopics, performs iterative web searches, synthesizes findings, and produces comprehensive cited reports. Use when a simple search isn't enough and the user needs thorough, multi-angle research.

Download web articles with images and save as clean markdown for offline reference. Covers Jina AI Reader, WebFetch tool, and multiple fallback methods for article extraction with image handling.

General web search patterns and techniques including Gemini CLI coordination. Use this skill when you need to perform web searches, find current information, or research topics online. Covers both Gemini CLI and built-in WebSearch tool usage with precise instruction crafting.