Skill UI

This skill helps manage and optimize resource usage and API costs within Evernote integrations. It provides utilities for monitoring monthly upload quotas, compressing images, resizing large files, and performing storage cleanup to prevent exceeding account limits and ensuring efficient data handling.

Transforms messy invoices, receipts, and bank docs into structured folders by reading files, extracting vendors, dates, amounts, and descriptions, renaming them consistently, and sorting copies ready for tax prep or accountant handoff.

Use the Nutrient DWS Processor API to convert, OCR, redact, watermark, sign, and fill PDFs, Office files, HTML, and images via multipart POST requests, streamlining secure document automation in batch workflows.

Build and tune Obsidian Base files to define database-like views, filters, formulas, and summaries for notes, so you can craft tables, cards, lists, and dashboards inside your vault.

Comprehensive PDF toolkit for extracting text and tables, splitting/merging documents, filling forms, and generating new files via Python or CLI tools, enabling automated, large-scale document workflows in analytics, compliance, or reporting pipelines.

Persistent file-based planning for multi-step AI-agent tasks, using task_plan.md, findings.md, and progress.md as on-disk working memory with recovery hooks and optional session catch-up.

Automates uploading files from Claude to Google Drive by encoding them and POSTing through a deployed Apps Script, returning Drive links so workflows that produce deliverables can save them directly in Drive across languages.

Implements Manus-style file-based planning to organize complex tasks, enforcing persistent markdown plan/findings/progress files, enforcing read-before-decide and write-after-action rules, and enabling session recovery after /clear.

This skill guides the operation, consolidation, and maintenance of complex working systems within Google Workspace (Docs, Sheets, Slides). It emphasizes treating files as integrated systems—such as trackers or planning hubs—requiring careful inspection, precise edits, and structural cleanup rather than simple content rewriting. Use it for consolidating scattered data, cleaning shared spreadsheets, or ensuring the correct canonical version of a document is utilized.

Fetches Feishu cloud document content as Lark-flavored Markdown, extracts media tokens, and guides invoking feishu_doc_media to download images, files, and whiteboards while handling wiki token resolution.

Automates Feishu doc edits with seven modes (append, overwrite, replace_range, replace_all, insert_before/after, delete_range) plus optional title sync, letting teams tweak specific sections without rebuilding entire files.

Compresses natural-language memory files such as CLAUDE.md or todo lists into caveman-speak to reduce input tokens. It creates a readable backup in an out-of-tree directory, requires an explicit filepath, and refuses secret-looking or credential-containing files before sending text to the configured model provider.