Email, calendars, task management, and automation (7.9K skills)
Search an agent's long-term memory for people, projects, and other facts. Save important corrections immediately, update outdated entries, and remove errors or duplicates while respecting which notebooks the current conversation can read or change.
Connect supported work apps through browser consent without sharing passwords with the agent. The skill checks available connection methods, provides a single-use authorization link when appropriate, and guides personal Slack account linking.
Request an owner’s permission to use a listed keychain credential needed by a command. An approval card appears in the conversation, and owner approval automatically reruns the blocked command with access shared across that conversation.
Help users discover and connect apps, then run available app tools through QM’s authenticated backend. It checks connection status, presents consent options, and keeps Composio project keys out of user-facing setup.
Guide a new user through optional account connections, a preferred assistant voice, and a review of current work. Save a lasting profile, then propose and set up specific help after confirming behavior and timing.
Install or remove memU long-term memory for the agent in use. The skill selects the host-specific guide, configures scheduled memory recording and retrieval before answers, and verifies the setup with local or cloud storage.
Build AI agents by connecting workflow blocks in AutoGPT's visual editor. This skill covers multi-step automation, scheduled runs, webhooks that start work after external events, execution monitoring, and custom agent development.
Defines how the internal Creator Agent in OpenCreator checks task state, applies changes, runs production stages, and verifies completion, with rules for handling conflicting updates, errors, and diagnostic reports.
Helps you use the AO command line to launch agents, manage work sessions and projects, and save reusable tasks as Cues. Also covers agent messaging, shared browser controls, previews, and local service checks.
Work through review comments on an artifact file one at a time. The skill reads the document and feedback, then follows your chosen approach to revise content, investigate issues, reply to comments, or mark them resolved.
Work through a plan or design in a focused interview, answering one question at a time. Each question includes a recommended answer, while facts available in the codebase are investigated directly to build shared understanding.
Automate website navigation, form entry, and clicks through a browser command line tool. Extract page text, capture screenshots, and compare page states to check interactions or test web app behavior across screen sizes.
Coordinate smaller agents to handle research, code exploration, and command execution during complex tasks. It separates responsibilities, avoids overlapping assignments, and helps the main agent maintain context and consistency over extended work.
Automate browser tasks through BrowserWing's HTTP API, from navigation and form filling to extracting search results. Inspect page structure to identify controls, capture screenshots, and run multiple actions in sequence.
Lets an agent ask for clarification, preferences, or approval through an on-screen dialog. Questions can offer single or multiple choices and custom text input, giving the agent a user response to guide its next step.
Configure and manage BrowserWing to create, save, and replay browser automation scripts. Use AI exploration to generate repeatable workflows, export scripts as SKILL.md files for agents, and diagnose service or execution problems.
Automate website navigation, form filling, data extraction, and web app checks while keeping page state between scripts. Use a new Chromium session or connect to an existing Chrome session through an extension.
Use MemOS Local to find past conversations, preferences, and decisions, then retrieve original messages or task context. The skill also guides sharing memories and reusable procedures with local agents or a configured team.
Evaluate everyday tasks using a deliberately high personal hourly rate. Review weekly activities, identify tasks to delegate or drop, and examine whether rising spending is keeping you from having more control over your time.
Check estimated token usage against daily limits before and after each automated loop run. Switch to reporting only, exit early when required, and record run outcomes so repeated agent work stays within configured limits.
Drafts a token budget extension request when an autonomous loop approaches its daily limit and high priority work remains. Uses logged results and remaining issues to justify the request, then pauses until a human increases the budget.
Check today's AI coding costs and token usage from local session logs with CodeBurn. Get a short summary of total spending, the most expensive models and projects, unusual usage, and one concrete suggestion for reducing costs.
Draft or revise individual emails, including replies, outreach, and follow-ups. Get a clear subject line and concise body that match the relationship, state the request early, and give the recipient a concrete next step.
Guide an agent through efficient use of an embedded browser by choosing targeted actions, searches, and waits. Reduce repeated tool calls and unnecessary page snapshots, while using more detailed inspection when the target or result remains unclear.