업무 효율화 스킬

Explore websites with shell-style commands, treating URLs as paths and page elements as files. List links, search text, extract selected content, and navigate cached pages, with background fetching and configurable link prefetching.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• List links on a webpage
• Filter page content by text or regular expression
• Extract text from selected page elements

Automate website tasks with agent-browser, a command-line browser tool for AI agents. Fill forms, click controls, extract page text, capture screenshots, and test web apps, with support for saving and reusing login state.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Automating form entry and submission
• Extracting text from web pages
• Capturing screenshots and checking web app behavior

Find installable agent skills for a specific task using the Skills CLI, a tool for managing skill packages. It explains relevant options, provides installation commands and information links, and can install a chosen skill when requested.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find a skill for a specific task
• Review skill options and installation commands
• Install a selected skill

Send Aegis activity detections to Home Assistant as events that trigger automations. Use camera-specific conditions to connect detected activity with actions such as turning on lights or sending notifications.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn on an entrance light when activity is detected
• Send notifications after an Aegis detection
• Run different actions for specific cameras

Connect the Clawdbot agent in SharpAI Aegis to LINE Messenger to send messages and files, and reply to incoming messages through a messaging channel configured with LINE credentials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sending messages from Clawdbot to LINE
• Sending files through LINE
• Replying to messages received on LINE

Send SharpAI Aegis events as JSON to a webhook, a URL that receives event notifications. Choose which events to send and connect camera activity to Zapier, IFTTT, Make, n8n, or a custom endpoint.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Send person detection events to Zapier
• Pass clip analysis completion to n8n
• Connect alerts to a custom endpoint

Connect the Clawdbot agent in SharpAI Aegis to Signal using signal-cli. The channel supports sending messages and files, replying, and adding reactions, with settings for the command path and bot phone number.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting Clawdbot to Signal
• Sending messages and files through Signal
• Replying and adding reactions through Signal

Publish SharpAI Aegis camera events through MQTT, a messaging protocol used by automation platforms. Choose event types and connection settings to feed clip analysis, person detection, alerts, or camera outages into compatible workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect camera events to Home Assistant
• Feed detection events into Node-RED
• Publish camera outage events

Connect SharpAI Aegis's Clawdbot agent to a Matrix/Element room to search clips, receive alerts, and control cameras through conversation, with support for files, reactions, message edits, and threaded replies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search recorded clips through a Matrix conversation
• Receive camera alerts in a Matrix room
• Control cameras through Clawdbot

Build flexible daily plans that account for ADHD-related difficulties with time estimation and getting started. Narrow priorities to three tasks, add transition buffers, and choose small next actions that match the energy available that day.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing three priorities for today
• Planning a schedule with transition buffers
• Finding a small first step when starting feels difficult

Use a browser to research topics, extract page information, fill forms, and test websites. Guides agents through identifying page controls, interacting with web apps, saving screenshots or PDFs, and reusing saved login sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Researching topics and reading web articles
• Filling and submitting online forms
• Extracting page text and links

Automate laboratory data management in Benchling through its Python SDK and REST API. Manage biological sequences, sample inventory, electronic lab notebooks, and workflow tasks, with guidance for external data synchronization and SQL reporting.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Importing biological sequences in bulk
• Auditing sample inventory and recording transfers
• Creating electronic lab notebook entries

Keep preferences, procedures, and performance findings in knowledge pages that persist across sessions. Hindsight updates pages from retained conversations, while the available tools let agents retrieve pages, search memories, and ingest documents or local files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Carry writing preferences across sessions
• Keep procedures and performance findings available
• Search past conversations and ingested documents

Organize project memory so agents can retrieve context across sessions. Review priorities and source records, consolidate duplicate notes, archive stale material, or carry out authorized erasure while preserving the authority of official records and documenting affected data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming work with saved project context
• Tracing current priorities to their sources
• Consolidating duplicate notes and archiving old material

Find skills on SkillsMP or GitHub, install them for one agent or globally, and inspect available skills. Create custom skills with SKILL.md metadata, register them in agent.yaml, and validate the agent configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding skills on SkillsMP or GitHub
• Installing skills for one agent or globally
• Checking installed skills and their details

Answer questions using an existing wiki, combining relevant pages with citations to both wiki entries and original documents. Identify gaps and confidence levels, and optionally save useful answers as new pages after user approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find cited answers in an existing wiki
• Compare information across wiki pages
• Identify gaps and uncertain claims

Organize tasks into small work packets, review them, and dispatch approved work with execution logs. Tasks that change external state require approval, and added scope is handled through a new packet.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing tasks before they change external systems
• Keeping approved work within its agreed scope
• Tracking pending work packets and execution logs

Keep goals, decisions, evidence, and next actions organized during long or complex agent tasks. Use persistent records and checkpoints to resume work, coordinate agents, and verify changes across files before delivery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming long tasks from recorded checkpoints
• Checking consistency across repository changes
• Sharing task state between agents

Prepare for conversation compaction, which shortens an agent's working context, by saving active files, progress, decisions, blockers, and next steps. Afterward, use those notes and priority files to recover the working state and resume the task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving task state before running /compact
• Preparing handoff notes when an auto-compact warning appears
• Recovering active work after compaction

Keep parallel Claude Code sessions identifiable with project, branch, and task labels. Report clear progress states at major milestones, explain blockers, and include a suggested default when asking for missing information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Track implementation and testing in separate sessions
• Check progress across several feature branches
• Show dependencies between changes

Find the right pro-workflow skill or command for a task. This index groups tools by job, explains when to use each one, and distinguishes skills you invoke yourself from those the agent selects automatically.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a skill for a specific task
• Exploring the available workflow tools
• Checking manual and automatic invocation modes

Create a handoff document that records completed work, unfinished tasks, key decisions, changed files, and potential pitfalls. Include a ready-to-paste instruction so the next agent session can resume with the context it needs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving progress before ending a work session
• Resuming unfinished development in a new session
• Preserving decisions and their reasoning

Review saved lessons and correction history before starting a task. The skill ranks relevant findings, explains earlier mistakes, highlights sessions with frequent corrections, and suggests an approach based on those records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review relevant lessons before starting work
• Recall mistakes from similar tasks
• Identify work that previously needed frequent corrections

Review connected MCP servers, which give agents access to external tools, for unused or overlapping capabilities. Get recommendations to keep, disable, or review each server, with estimates of the request size each recommendation could save.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate slow or costly sessions
• Review configuration before adding an MCP server
• Find unused or overlapping tools