Word, Excel, PowerPoint, PDF, meeting notes, and manuals (3.6K skills)
Add two to four introductory sentences to French and English whitepaper sections that start directly with tables, code, or lists, supplying practical context while keeping additions within defined line limits.
Audit French and English whitepapers and recap cards for outdated versions, missing language counterparts, and metadata problems. Receive document scores, an overall health report, and prioritized update suggestions, with optional proposed patches.
Turn articles, notes, or code history into talk preparation materials, including angles, titles, scripts, slide drafts, and revision sheets. Coordinate the stages with user checkpoints, or run an individual stage again.
Fetch official documentation from Anthropic and save local snapshots through an MCP tool. Initialize both baseline and current copies, then report the section count and storage path so later refreshes can be compared against the baseline.
Turn talk scripts, slides, and concept notes into reference sheets with section navigation, definitions, shareable links, a glossary, and six to ten anticipated questions with short answers for live Q&A and attendee follow-up.
Compare a saved baseline of Anthropic documentation with the current local snapshot, showing added, removed, and modified sections, line changes, and unchanged counts without making a network request.
Build and maintain Mintlify documentation sites by writing pages, organizing navigation, and creating API references. The skill guides edits to site settings, use of built-in components, consistency with existing content, and checks for broken links and build errors.
Add corporate sponsors to ZCF’s English, Chinese, and Japanese README lists, with optional advertising cards and API connection presets. Check for existing entries and keep sponsor information consistent across languages.
Compare code changes since the latest Git tag with English, Chinese, and Japanese documentation. Update affected guides and CLAUDE.md, check links and contents pages, or report inconsistencies without changing files.
Generate README.md and DESIGN.md outlines by inspecting a module's files, language, and dependencies. Python analysis also extracts classes, functions, and docstrings, providing a starting point for usage documentation and design records that you complete afterward.
Prepare conference LaTeX template archives for writing in Overleaf. The skill identifies the main file and dependencies, proposes cleanup for approval, and organizes sections, resources, and a README with submission and compilation guidance.
Co-write proposals, technical specifications, and decision documents through context gathering, section-by-section drafting, and revision. A fresh AI reader then tests the document to reveal unclear explanations, missing context, and contradictions before it is shared.
Clean data across multiple Excel sheets, compare totals between sheets, and summarize categories and proportions. Create charts and export a formatted workbook with unusual values highlighted for review.
Clean numeric columns in Excel, filter records above a chosen threshold, and count matching rows. The skill also covers checking row totals across sheets and marking qualifying cells with formatting for export.
Process multi-sheet Excel data by finding columns through keywords and counting specified values. Clean text fields to retain Chinese characters, then export the processed data as an Excel file with its size and download link.
Filter rows from a selected Excel sheet, summarize category counts and percentages, and export the required columns to a new workbook. The workflow also cleans filter values, renames columns, and provides a download link.
Scan multiple Excel sheets for rows with missing or invalid entries in a target column. Combine matching records with their source sheet names, then export an Excel file with every extracted data row filled red for review.
Clean Excel columns by removing unwanted prefixes from numeric values and extracting Chinese characters from text. Add the cleaned results as new columns, then save an Excel file and provide a download link.
Inspect multi-sheet Excel files, use Parquet, a column-based file format, for larger datasets, and clean text before analysis. Produce category summaries, identify maximum values, and export formatted reports or scatter plots with fitted straight trend lines.
Extract text and tables from Word documents, inspect highlights, cell backgrounds, and font sizes, and aggregate information across files. Embedded images can also be extracted and passed to a separate captioning script for descriptions.
Provide backup web search, image search, image downloads, and image generation for other PPT skills when the agent’s native equivalent is missing or fails. Selected images are saved locally for use in presentation files.
Check Excel measurements against limits written in the sheet, highlight rows exceeding those limits and cells containing division errors, and export a summary showing structure names, measured values, limits, and differences.
Turn presentation requirements, supplied documents, and completed research into one editable Markdown outline. Define the overall argument, each slide’s conclusion and evidence, and the connections between slides, then update the same outline when revisions are requested.
Extract coefficients associated with a chosen label across Excel sheets and check them against a standard value. Create a comparison workbook showing each value, its source sheet, and red highlighting for rows that fail the check.