Email, calendars, task management, and automation (7.9K skills)
Automate website interactions through a command-line browser tool. Navigate pages, fill forms, extract text, save screenshots or PDFs, reuse login sessions, and compare page states to check the effects of actions or website changes.
Hand off OpenRig work through persistent queue items that record the next owner, blockers, and closure reasons. The skill covers notifying recipients, escalating to a human, and keeping supporting evidence accessible across interruptions and missed messages.
Preserve the context of long Claude Code sessions across compaction, which shortens conversation history. Create a restore map linking decisions, files, and next steps, then use ranked readings and targeted transcript lookups to rebuild working context.
Build and refresh an index of available skills, including when to use each one and its exact file path. Resolve duplicate entries and give agents a current reference after skills are added, removed, moved, or renamed.
Draft clear, considerate comments for code reviews, issue replies, and team updates. Put the actionable point first, explain technical reasons when needed, and give a concrete next step while matching the conversation’s language.
Automate Chrome using an existing login session through CDP, Chrome’s remote control interface. Open pages, click elements, enter text, extract page content, run JavaScript, and inspect authentication tokens with agent-browser.
Use a randomized tarot spread to guide loosely defined tasks or choose among reasonable approaches. It interprets 36 cards across 12 areas, turning their themes into concrete next steps and possible investigation angles.
Decide when repeated search failures justify continuing document creation with existing knowledge. Track errors, distinguish retryable problems, and record verification limits, while excluding tasks that require current information or explicit external verification.
Check deliverables before marking a task complete. Review the requested file format, confirm every reference file was used, and compare the result with the original request to catch omissions and work that misses the goal.
Find input files in confirmed workspace folders, save outputs to explicit locations, and check the results against task requirements. Useful in restricted execution environments where familiar folders may be missing or inaccessible.
Track tasks that require several output files with an upfront checklist, checks after each file is created, and a final review. Confirm that every required file exists and has a nonzero size before reporting completion.
Describe the files you want created, updated, or organized, and let shell_agent choose how to perform the work. It selects tools such as Python or Bash, executes the operation, and handles errors with retries.
Delegate file creation to shell_agent when direct generation tools fail. Specify the required format and content, then locate generated files by extension or modification time, copy them to the working directory, and check their integrity.
Hand complex document generation or data processing to shell_agent when direct tools repeatedly fail. Define the required output, let the tool choose libraries and recover from errors, then verify the resulting files and content.
Use attached spreadsheets and documents as the primary source for reports and analysis. Identify relevant files, extract needed data, and cite filenames, turning to external searches or clearly labeled estimates only when the supplied material lacks required information.
Helps agents build outputs from supplied reference files by reading, checking, and citing their data first. External searches are reserved for missing details, verification, or tasks that explicitly require current information.
Locate missing files and verify their full paths before processing them. This workflow checks directory contents, searches by filename, and inspects permissions, size, and modification time to help resolve FileNotFoundError, an error indicating a file could not be found.
Track every required output in a visible checklist, update progress as each is completed, and review the original requirements before finishing. When one output is blocked, try alternatives and continue work on the remaining deliverables.
Handle repeated tool failures by documenting what went wrong and which deliverables remain blocked. Produce useful partial work with clear limits, distinguish unverified content from completed work, and provide concrete steps for recovery or handoff.
Track every required output in tasks involving multiple files, reports, or recipients. Build a checklist, update each item with completion evidence, and review the original requirements before declaring the task finished.
Find generated files that are missing from their expected locations in isolated or temporary execution environments. Search confirmed directories, identify the right file, copy it to the intended destination, and verify that it is readable and nonempty.
Track tasks that require several outputs by listing every deliverable, updating a visible checklist, and verifying that each result exists. Helps prevent work from ending while requested files, reports, or other outputs remain unfinished.
Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.
Find reusable skills in OpenSpace's local registry and explore its cloud library when needed. Review matching skills, choose where to import them locally, and decide whether to follow them or delegate the task.