Scheduling across calendars, attendees, and meeting rooms requires several coordinated steps. This skill guides Claude, Codex, and Claude Code through Lark calendar workflows.

Text-only agents cannot inspect screenshots, diagrams, or scanned pages. This skill sends one image and a focused prompt to your configured vision model.

Obsidian users need fast note operations without manual navigation. This skill uses the Obsidian CLI to read, update, search, and debug vaults.

JSON Canvas files are hard to edit by hand without breaking IDs or links. This skill guides creation, updates, and validation for Obsidian-compatible canvases.

Long memory files consume context and make repeated AI sessions expensive. This skill compresses markdown and text memory files while preserving technical details, code, URLs, and structure.

Large configuration files and repeated context increase token usage. This skill reviews Caveman reports and applies measured changes with individual approval.

Large project memory files consume tokens every time an AI coding session starts. This skill compresses prose memory files while preserving technical details and saving a readable backup.

Verbose answers can waste context and slow technical work. Caveman mode compresses explanations while keeping code, warnings, and technical meaning intact.

Blank prompts and complex problems can lead to predictable ideas. This skill structures creative thinking through analogy, synthesis, and feasibility checks.

Saving rendered web pages as readable notes is hard when pages rely on JavaScript or require manual login. This skill opens the page in Chrome, captures the rendered content, and writes a clean markdown file with metadata.

Teams need quick Gemini text and image generation from local prompts. This skill runs Gemini Web through Chrome cookies and saves generated images.

Teams working on IdeaVim need consistent YouTrack workflows instead of GitHub Issues. This skill gives agents the ticket conventions, commands, tags, and release steps for VIM issues.

Project knowledge often disappears between agent sessions or becomes stale. This skill recalls verified context and preserves reusable results through LWC.

Writing effective prompts from scratch wastes time and produces inconsistent results. This skill teaches your agent to search, inspect, and assemble prompts from PromptDNA's library of over 950 community-tested prompt blocks through the PromptDNA MCP server, while spending metered credits efficiently.

Complex agent projects need clear data flow, dependencies, and reliable triggers. This skill provides practical OpenServ patterns for building and operating coordinated workflows.

Trading competition workflows require status checks, wallet context, and fixed response templates. This skill guides Claude, Codex, and Claude Code through OKX competition discovery, registration, ranking, reward claims, and contact follow-up.

Agent marketplaces require many role-specific commands, confirmations, and task states. This skill guides OKX AI identity, task, messaging, and watch workflows in one place.

Wallet and x402 workflows are risky to run from memory. This skill gives structured CLI steps for balances, transfers, trades, funding, paid API calls, and x402 services.

Notion API tasks require exact endpoints, headers, and JSON shapes. This skill gives practical request patterns and safety guidance for workspace automation.

AI workflows often require separate APIs for images, video, search, and language models. This skill helps Claude, Codex, and Claude Code discover and run inference.sh apps through the belt CLI.