Email, calendars, task management, and automation (7.8K skills)
Resume interrupted work by loading the latest state saved with /context-save. The skill prefers a save from the current branch, falls back to other branches, and supports handoffs between Conductor workspaces.
Connect a remote AI agent to your browser by generating a setup key and connection instructions. The connected agent receives its own tab, with an option to narrow its default page access.
Save the current Git state, decisions made, and remaining work so a future agent session can resume with context. Use it before pausing work, then pair it with /context-restore when returning.
Launch GStack Browser, a visible Chromium browser controlled by an AI agent. Watch actions in a sidebar activity feed and use sidebar chat to request page navigation, clicks, form entry, and reading page content.
Review confirmation questions across gstack skills and set which should always appear, be skipped, or appear only for irreversible actions. Use conversation to manage question tuning and inspect declared preferences alongside patterns inferred from behavior.
Review and search project knowledge that gstack has collected across work sessions. Find past lessons, prune outdated entries, and export recorded knowledge when you need to revisit earlier solutions or organize what the project has learned.
Operate an isolated Browser Use Cloud browser from a machine without usable local Chrome. Navigate pages, inspect content, fill forms, manage tabs, and capture screenshots through the Browser Use CLI, then stop the browser after use.
Controls a browser directly to click, type, navigate, extract page data, and take screenshots. Useful for testing websites and working with pages that require JavaScript rendering, interaction, or an existing signed-in browser session.
Rewrite agent replies in Classical Chinese, a compact historical writing style, while keeping code and technical identifiers unchanged. Use it to shorten on-screen text and avoid repeated explanations, with ordinary prose when clarity requires it.
Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.
Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.
Compress agent replies into short phrases while preserving technical details, negations, numbers, and exact commands. Use it to reduce repeated explanations and keep chat responses brief until you explicitly turn the mode off.
Look up commands for concise response modes, commit messages, review comments, and Markdown compression. The reference also explains how to check the current mode, return to normal responses, and configure startup defaults.
Tidy a Paperclip Mine inbox by scanning entries and grouping archive candidates by work status and inactivity. Present checkbox confirmations, then archive only accepted selections, with undo details and no changes to the underlying tasks, branches, or workspaces.
Delegate work to an existing Paperclip agent by selecting a suitable assignee and creating a task with clear objectives, constraints, and deliverables. Receive a lasting task reference and check progress after the conversation ends.
Use an assigned Slack bot to read shared conversations, search accessible discussions, summarize with source links, and send messages or files. It connects Slack collaboration with Paperclip tasks and routines while respecting channel access and delivery status.
Review stalled, blocked, or pending-review issues in Paperclip and choose one concrete next action for each. Clarify ownership and status, then resume work, reassign it, resolve blockers, request a decision, or close the issue.
Guide a first task in Paperclip by clarifying goals, constraints, and completion criteria. Prepare a plan or one task proposal, then wait for approval before creating execution tasks or carrying out the agreed work.
Store facts, daily events, and user preferences in files that persist across sessions. Organize knowledge with PARA, a method separating projects, ongoing responsibilities, references, and archives, and retrieve saved information through qmd search.
Read email linked to assigned Paperclip tasks, send new messages or replies through an assigned AgentMail inbox, and check delivery outcomes. Follow task permissions and preserve retry identifiers to avoid duplicate sends.
Review another agent’s recent work records to identify recurring problems and propose small changes to instructions, skills, or tool descriptions. Produce evidence-backed drafts and reviewable diffs, checking that proposed rules would preserve successful outcomes from past tasks.
Check earlier Paperclip tasks for verified progress and actual deliverables, then report findings with links. When requested, add feedback as the connected person, with safeguards against posting the same comment twice.
Coordinate agent work through the Paperclip API by checking assignments, updating task status, posting progress, delegating subtasks, and requesting approvals. It records deliverables and dependencies so reviewers and other agents can follow the work and continue it.
Handle tasks managed by Paperclip by reading their context, saving documents and deliverable files, updating progress and blockers, and coordinating delegated work. The skill provides procedures for short agent runs, approvals, and traceable task updates.