Email, calendars, task management, and automation (7.9K skills)
Organize competing tasks by impact, difficulty, and dependencies, then choose one main priority. State what completion looks like, keep unrelated requests queued, and finish and verify the chosen task before reassessing the remaining work.
Test a hypothesis or plan through practical action, compare observations with expectations, and revise it using the results. Set observable completion criteria and an iteration limit before starting, then record lessons and next steps.
Guide an agent to ground judgments in evidence, separate facts from inferences and unknowns, verify results, and diagnose failures. It also selects a suitable methodology skill when investigation, prioritization, validation, or another structured approach would help.
Breaks a long-running goal into small, tracked actions and records observable evidence for each success criterion. Checkpoints preserve progress so the agent can resume after interruptions and verify completion against the current work.
Search local session histories across Codex, Claude Code, OpenCode, and other coding agents. Find earlier requests, inspect transcripts and child sessions, and reconstruct past work using recorded evidence, with filters for dates, projects, platforms, and models.
Automate forms, clicks, screenshots, and website checks in a browser where you are already signed in. A separately launched browser also supports scraping and network capture, while login or verification steps can be handed to a person.
Turn tasks in tasks.md into individual GitHub issues after breaking down work. The skill checks the repository’s remote URL and creates issues in the matching GitHub repository so the tasks can be tracked there.
Analyze complex tasks before implementation through four structured phases. Clarify the problem, examine dependencies and impacts, challenge assumptions, and compare alternatives to produce a decision rationale, explicit uncertainties, and actionable recommendations.
Capture desktop screenshots on macOS, Linux, and Windows. Save the full screen, a selected window, or a region defined by coordinates, with support for a specified file path, the default location, or temporary storage.
Find reusable Agent Skills by keyword, category, or tag through prompts.chat. Review descriptions and included files, retrieve a chosen skill, and install its instructions, reference documents, scripts, and configuration files for Claude.
Extract selected content from known web URLs and save it as Markdown, text, or HTML. Use command-line workflows for repeatable collection, with optional MCP integration that lets an AI agent call scraping tools.
Organize complex tasks using three Markdown files for plans, findings, and progress. The skill keeps decisions, discoveries, errors, and test results in project files that an agent can consult when making decisions or resuming work.
Automate a real browser from the terminal to navigate pages, fill forms, extract data, and investigate interface problems. Use page snapshots to identify controls, and capture screenshots or traces, records of browser activity, for review.
Coordinate multiple AI agents under a lead coordinator for research, development, and review. Assign specialized roles, use voting to make shared decisions, preserve collective knowledge, and pause or resume work through managed sessions.
Turn prompts, bug fixes, design ideas, and workflow lessons from conversations into organized Obsidian notes. It captures context, tags, and analysis, then can automatically commit and push saved notes to GitHub for backup and version history.
Organize scattered files by type, purpose, or date, find duplicates, and review older material. Get a proposed folder structure, then approve file moves and renaming, with confirmation required before any deletion.
Organize content ideas, contacts, meeting history, and goals in structured files. Use saved writing preferences and past posts to draft consistent content, prepare meeting briefs, and review weekly progress across publishing and relationships.
Manage complex agent tasks through agreed requirements, plans, execution, verification, and cleanup. The workflow sets approval boundaries, assigns skills to defined work units, records evidence, and reports verified deliverables alongside any remaining blockers.
Package project links, reports, demos, or Codex session summaries into a readable static HTML page. Remove sensitive information, upload the page or existing static files through PinMe, and return the resulting share URL.
Automate website navigation, form filling, clicks, data extraction, and screenshots through the browse CLI, a command-line tool. Choose a local browser or a remote Browserbase session to suit the website and task.
Copy cookies, browser data used to maintain sign-ins, from a local Chromium-based browser into Browserbase. Use the saved context with the browse CLI to access authenticated sites, filter domains, and refresh expired cookies.
Find NVIDIA skills for a product or workflow using the current catalog. Get up to three relevant recommendations with reasons, installation commands, and starter prompts, or use an already installed skill when one fits.
Preserve coding-agent progress in readable session files, including goals, decisions, changed files, and next steps. Helps resume long-running work after disconnects or editor restarts and gives another agent concise handoff instructions.
Inspect, search, create, and edit data exposed as files through Mirage. Guides agents through the appropriate tools, reading before editing, and retrying changes when a file has been updated since it was read.