Email, calendars, task management, and automation (7.9K skills)
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.
Build a developer profile from past sessions or a questionnaire, then generate files and settings that personalize Claude's responses. Choose which outputs to create and compare changes when refreshing an existing profile.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Turn “this year so far” into a concrete date range from January 1 through today. Get local calendar dates and precise UTC boundaries to use when filtering records or calculating year-to-date metrics.
Review an agent's saved context and unread coordination messages at the start of a task. Summarize relevant assignments, move handled messages aside, and prompt the agent to preserve lasting decisions and outcomes before finishing.
Get the date range for the previous full quarter, based on when the skill runs. It returns local dates and precise UTC boundaries to define reporting periods for quarterly reviews, quarter-over-quarter comparisons, and timestamp-based queries.