업무 효율화 스킬

Preserve development progress when stopping midway through a phase. The skill records completed work, remaining tasks, decisions, and blockers in .continue-here.md, creates a Git commit for unfinished work, and provides instructions for resuming.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving progress before ending a work session
• Carrying decisions and blockers into the next session
• Committing unfinished work before a pause

Capture tasks and ideas in GSD as structured todos, notes, backlog entries, or future ideas with trigger conditions. You can also browse pending todos, choose work to start, and review previously captured future ideas.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving tasks as structured todos
• Capturing quick notes and promoting them later
• Parking ideas in the backlog

Retrieve past decisions, recurring patterns, and unexpected issues from MemPalace before planning a phase. The skill produces a concise file with source references for the planner and falls back to GSD’s native memory when MemPalace is unavailable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing past decisions before planning a phase
• Checking recurring patterns and previous pitfalls
• Preparing a source-backed memory summary for the planner

Route requests for idea exploration, rough planning, time-boxed technical investigation, phase specifications, or thought capture to the appropriate GSD skill. It selects and invokes a skill based on the intended task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore an idea or opportunity
• Sketch a rough design or plan
• Run a time-boxed technical investigation

Draft business emails in several tones using the purpose, recipient relationship, and context. Get copy in your language, English, or both, plus optional follow-up sequences with suggested timing, organized in a Markdown document.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft an English follow-up on a customer quote
• Compare formal, friendly, and direct email versions
• Prepare business emails in two languages

Turn reusable lessons from a conversation into proposed skill library updates. It checks existing skills for overlap and conflicting rules, then stages each lesson with a reason and an exact supporting quote from the session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserve a corrected approach for future work
• Record lasting user preferences
• Update existing skills with new lessons

Create a new Claude Code session containing only the last quarter of the current conversation. Preserve the most recent work, reduce conversation tokens, and get a command to resume the copied session directly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing with only the last quarter of a conversation
• Reducing tokens while keeping the most recent work
• Resuming a copied session with a direct command

Create a new Claude Code session from the later half of the current conversation. Keep recent work while reducing conversation tokens, then receive a command to resume the copied session directly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing a long conversation with its later half
• Reducing tokens while keeping recent work
• Resuming a copied session with a direct command

Create or update a HANDOFF.md document with the goal, progress, successful and failed approaches, and next steps. It gives an agent in a fresh conversation the context needed to continue the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing to continue work in a fresh conversation
• Handing ongoing work to another agent
• Recording approaches that failed

Turn an idea into a goal package for /goal. Collect decisions through Plannotator, review testable requirements, explore the codebase, and produce an approved execution plan with verification steps and a clear completion condition.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a rough feature idea into testable requirements
• Agreeing on scope and success criteria before implementation
• Creating an execution plan grounded in the codebase

Use Plannotator to review plans, code changes, documents, and running local apps in a browser. This reference covers returning feedback to agents, browsing past decisions, sharing guided code reviews, and leaving questions for later replies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing and approving plans or specifications
• Reviewing local code changes or pull requests
• Annotating documents or running local apps

Open the assistant’s latest rendered message in Plannotator and return specific annotations for revision. The skill distinguishes requested edits from approval, approval with notes, and a closed session, so each review result receives the appropriate response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Annotate the assistant’s latest response for revision
• Approve a response without requesting further work
• Approve with notes to guide subsequent work

Open files, folders, or URLs in Plannotator’s annotation interface, then have the agent address the returned comments. Use it to review Markdown, plain-text configuration files, or HTML through a shared feedback workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a Markdown document
• Commenting on configuration files
• Opening a folder for annotation

Review Markdown files, HTML files, URLs, or folders in Plannotator’s annotation interface. The agent responds to requested changes and distinguishes them from approvals, optional approval notes, and sessions closed without feedback.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a Markdown document
• Collecting comments on HTML or web pages
• Opening a folder for annotation

Automate a logged-in Chromium browser using the plugin’s injected tools. Read pages, fill forms, manage tabs, inspect page activity, and investigate website problems or test interfaces while working with the user’s existing browser logins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading pages that use an existing browser login
• Filling forms and navigating between tabs
• Investigating website errors and page activity

Use the bsk command-line tool and browser extension to automate logged-in Chromium. Read pages, complete forms, export tables or lists as JSON or CSV, manage tabs, test interfaces, and investigate website failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading pages with an existing browser login
• Exporting tables or lists as JSON or CSV
• Filling forms and managing browser tabs

Inspect and update Atlas preferences in config.toml using the explanations and constraints written in the file. The skill guides agents through explaining changes, editing only relevant lines, saving safely, and checking the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspect current Atlas preferences
• Change a setting within its allowed values
• Clear an optional setting

Save established decisions, project facts, failed approaches, and system architecture to Atlas shared memory. The skill checks existing entries to avoid duplicates and creates self-contained records that other agents and future sessions can use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Carry decisions and their reasons into future sessions
• Share project facts and conventions with other agents
• Record failed approaches to avoid repeating them

Support ClawHub staff moderation through its local admin tool, including skill reports, removals and restores, user restrictions, publisher and package management, and staff email, with approval checks and verification after changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Triage skill reports and restore hidden listings
• Ban users or lift account restrictions
• Manage organization publishers and package ownership

Research websites, extract page content, and interact with sites using search tools or an existing browser session. Handles login-dependent and dynamically loaded pages, with browser controls for navigation, forms, screenshots, and media inspection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Researching social media and dynamically loaded pages
• Reading and interacting with sites that require login
• Finding previously visited pages in history or bookmarks

Turn “last week” into the previous complete Monday-to-Sunday date range. Get local calendar dates and precise UTC boundaries to use for weekly digests, week-over-week comparisons, and queries that filter records by timestamp.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting the reporting period for a weekly digest
• Checking the date range for week-over-week comparisons
• Getting UTC boundaries to search last week's records

Convert periods such as last month, this quarter, or the past 45 days into explicit date ranges. Get local dates and exact UTC boundaries in readable text or JSON for time-based searches and reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Confirm the full date range for last month's report
• Set UTC boundaries for the past 30 days
• Check quarter-to-date or year-to-date ranges

Turn “last month” into the full previous calendar month's date range. Get local calendar dates and precise UTC boundaries, the global time reference, to set consistent periods for monthly reports, summaries, or timestamp searches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set the reporting period for the previous calendar month
• Confirm the dates for a month-end summary
• Define UTC boundaries for last month's timestamp searches

Turn “last seven days” into a concrete date range ending today. Get local calendar dates and precise UTC boundaries, the global time reference, to use as consistent limits for reports or timestamp searches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set the reporting period for the last seven days
• Define UTC boundaries for timestamp searches
• Check the local dates covered by a trailing week