업무 효율화 스킬

Save, organize, synchronize, and retrieve documents, conversations, and project information across local files, memory tools, knowledge repositories, and databases. Check for duplicates before storing information and choose a suitable home for each type of knowledge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving documents and conversations to a knowledge base
• Consolidating duplicate notes
• Synchronizing knowledge across storage systems

Turn lessons from complex tasks, debugging, failures, or rollbacks into short learning entries. Capture the root cause, a reusable action, and a recognizable signal, then merge examples that share a cause with existing notes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capture lessons after a complex task
• Record root causes and lessons from debugging
• Merge learning notes that share the same cause

Turn repeated local Hermes workflows into reusable ECC skills and release materials. Remove private data, credentials, account names, and local paths, then document public inputs, expected outputs, and remaining risks before sharing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a repeated local workflow into a public skill
• Removing private details from launch handoff documents
• Documenting overnight jobs without exposing private data

Summarize Claude Code token usage and estimated spending from the local ECC metrics log. Review costs by model, session, or date, compare spending with budgets, and export records to CSV while avoiding duplicate counting of session totals.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing today's spending with yesterday's
• Reviewing costs by model or session
• Checking spending against a budget

Documents a legacy workflow for extracting reusable solutions from Claude Code sessions and saving them as learned skills. Useful for reviewing existing setups and extraction settings; this version is deprecated in favor of continuous-learning-v2.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing legacy session-end extraction setups
• Adjusting extraction thresholds and pattern categories
• Reviewing saved learned skills

Build a scheduled agent that collects public website or API data, summarizes or scores it with Gemini Flash, and stores results. Includes guidance for duplicate removal and using user feedback to inform future scoring.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Collecting job listings and scoring their relevance
• Tracking product prices on a schedule
• Collecting news and classifying it by topic

Organize a real mailbox, draft replies using thread history, and verify sent messages. The workflow identifies the account and recipient, checks commitments and deadlines, and reports whether a message is drafted, sent, blocked, or awaiting verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sorting an inbox and identifying mail to archive
• Drafting replies based on conversation history
• Sending email and checking the sent copy

Navigate ECC by checking its current files to find suitable skills, commands, and configuration options. Get focused guidance on installation, reset procedures, project setup, and troubleshooting duplicate installs, with concrete files and next steps to inspect.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find ECC skills and commands for a task
• Check installation and reset procedures
• Plan ECC setup for an existing project

Turn Claude Code session patterns into reusable behavior rules with confidence scores. Keep project-specific lessons separate, review and share learned rules, and combine related patterns into skills, commands, or agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capture lessons from corrections and repeated workflows
• Keep learned conventions separate for each project
• Turn related behavior rules into skills or commands

Audit Claude Code agents, skills, rules, and MCP tool configurations to estimate how much space they consume in the model's context. Identifies oversized and overlapping components, then ranks recommendations by potential token savings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating why context space fills quickly
• Auditing a setup after adding skills or MCP servers
• Finding oversized files and duplicated instructions

Keep project context across Claude Code sessions by saving progress, decisions, blockers, and next steps. Commands retrieve project briefings, while a session-start hook loads a compact summary to help resume previous work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving progress and next steps before ending a session
• Resuming work from a previous session
• Reviewing the status of several projects

Review Claude Code settings for duplicate skills, outdated memory files, unused permissions, and other clutter. The workflow presents evidence for each candidate, requests individual approval, and records reversible cleanup actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing overlaps after installing many skills
• Checking outdated memory files and unused hooks
• Organizing duplicate permission entries

Design a persistent multi-agent workflow in Claude Code, with specialist roles, reusable commands, file-based memory, and scheduled tasks. Keep project context and decisions across sessions using JSON and Markdown files without an external database.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Coordinate specialist agents for development and writing
• Preserve project context across sessions
• Schedule recurring morning briefings

Set up recurring work in Claude Code by combining persistent memory, scheduled prompts, task queues, and optional computer control. The skill explains how to connect these components, including external scheduling for work that continues after a session closes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing pull requests at regular intervals
• Collecting and summarizing research findings daily
• Preparing meeting notes from saved context

Save project context and task handoffs as local Markdown documents that Claude, Codex, and other agents can share. The skill guides searching prior knowledge, recording evidence and remaining work, and checking the shared memory vault for structural problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Handing work from Claude to Codex
• Saving project context for a later session
• Finding earlier decisions and supporting evidence

Design a shared notification workflow across GitHub, Linear, local hooks, desktop alerts, and existing communication tools. Classify urgency and ownership, merge duplicate events, and decide which updates need immediate attention, a digest, or a log entry.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Consolidate GitHub, Linear, and local hook notifications
• Reduce duplicate alerts for CI failures
• Separate urgent alerts from digest updates

Audit repository settings, connected tools, and the agent's runtime setup to show what is usable now. Identify missing workflows and integrations, then recommend prioritized ECC skills, automation hooks, agents, or tool connections.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing the current setup before configuring Claude Code
• Listing connected tools and available capabilities
• Checking whether more plugins are needed

Search local notes, documents, and meeting transcripts using keywords and meaning. Combine both methods and use local AI models to reorder results by relevance, then retrieve full documents or selected passages without cloud processing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find decisions recorded in meeting transcripts
• Search notes by concept rather than exact wording
• Look up names and identifiers in project documentation

Set up a reusable Twilio phone number, send SMS and MMS, and check incoming texts. Deliver recorded or spoken messages by phone, or place conversational AI calls through Bland.ai or Vapi.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting and reusing an agent phone number
• Sending deployment alerts by SMS
• Checking texts received since the previous session

Search and edit notes in a SiYuan knowledge base through its API. Find text, read individual content blocks, create documents, update paragraphs, rename or delete notes, and export documents as Markdown.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Search existing notes by keyword
• Save meeting notes as a new document
• Append or update paragraphs in a note

Track updates across blogs and RSS/Atom feeds, then manage unread articles in one place. Automatically discover feeds, import subscription lists, and filter articles by blog or category using blogwatcher-cli.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check new posts across multiple blogs
• Import an existing feed subscription list
• Track read and unread articles

Build a dashboard that refreshes from email, websites, or local files. Track progress, highlight items needing attention, and retain a change history, with notifications when important changes or new issues appear.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracking application progress across email and websites
• Reviewing deals or shipments in one place
• Receiving alerts about important status changes

Turn researched property and rental details into browsable cards in Hermes desktop conversations. Each card can show photos, prices, features, source links, and questions to check, keeping shortlisted properties easy to compare during follow-up discussions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare shortlisted rental properties
• Organize property photos, prices, and features
• Review questions to check before a viewing

Give an AI agent its own email inbox using the AgentMail CLI. Send and receive messages, handle replies and attachments, complete email verification codes, and trigger ongoing workflows when new mail arrives.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an email address for an AI agent
• Sending messages and handling replies or attachments
• Completing verification with codes received by email