208 skills (repositories by asgeirtj) · sorted by popularity
Guide browser tasks in the person's own Chrome using existing sign-ins. Covers tab management, site permissions, form entry, GIF recordings, and console inspection, with clear steps for handling connection failures and unresponsive pages.
Helps Claude work in desktop apps by viewing screenshots, clicking, typing, and scrolling. It covers access approval, choosing appropriate tools, and handling app restrictions for tasks in Notes, Finder, settings, and other native apps.
Guide browser work inside the Claude desktop app, including reading page text, opening tabs, and handling existing sign-ins. Covers site approvals, browser visibility, and connection problems when a cloud session uses the desktop browser.
Create and update dashboards with charts, metrics, and tables drawn from connected data sources or attached files. Link displayed values to their sources so readers can inspect queries, calculations, and freshness while reviewing business indicators or recurring reports.
Create and revise presentation decks in the Slides artifact format. Organize sections and slide order, arrange text, images, and diagrams, apply a supplied design system, and update selected slides while preserving the rest of an existing deck.
Create and revise shared documents in Claude Docs, where people and Claude can edit together. The skill guides document creation, targeted changes, and comment replies through the connector, with updates appearing live to readers.
Build and revise a design system from brand materials or code. Organize colors, typography, spacing, components, and assets into structured files, with usage guidelines and previews, using the supported Design System artifact format.
Create and revise posters, social graphics, web pages, and app screens on a Design canvas. Apply brand colors, fonts, and shared components, organize multiple artboards, and make targeted changes to existing designs.
Research a topic across multiple sources and turn the findings into a readable report. The skill coordinates separate research agents to compare options, examine markets or trends, and synthesize literature into a coherent narrative.
Create, edit, and clean spreadsheet files, including Excel workbooks and CSV data. Build formulas and formatting with openpyxl, a Python library, then recalculate and validate workbooks to check for formula errors and file problems.
Verify documents, spreadsheets, presentations, and web deliverables before sharing them. Combine file checks with inspection of freshly rendered output, and scan for unfinished text to catch clipped content, layout problems, and leftover placeholders.
Find topic-specific API guidance and implementation patterns for Three.js projects. Ten references cover scene setup, geometry, materials, lighting, textures, animation, loading models, custom visual effects, postprocessing, and mouse or touch interaction.
Create or revise presentation decks using individual HTML slide sources and a shared visual theme. Assemble and check the slides, inspect rendered images, and export to PPTX by default, with PDF or HTML available on request.
Check password-manager warnings for exposed passwords and prepare official reset pages for affected accounts. The user enters and submits each replacement, while the skill tracks password changes, authorized saves, and fresh sign-in checks separately.
Manage coding-agent sessions across connected machines through Herdr, tmux, and MSP. See which sessions need attention, review their output, open sessions with a brief, send instructions, answer approval dialogs, and stop or close sessions.
Review connected mailboxes, identify messages needing attention, organize the inbox, and prepare replies using the latest conversation. Send within the user's approved scope and check the provider's reported sending status.
Create, edit, or inspect PowerPoint and Google Slides decks through the shared Presentations skill. Supports focused slide updates, editable charts, speaker notes, and checks of slides and exports before delivering the presentation.
Create, edit, and inspect spreadsheets for reusable budgets, models, and trackers. Check formulas and dependent totals, preserve unrelated data, and deliver an editable workbook or a link to the updated native spreadsheet.
Review a ChatGPT Space page and its existing schedules, then set up recurring work such as refreshing figures, summarizing activity, or maintaining tasks. Adjust timing and instructions, preserve useful schedules, and remove or disable work that is no longer needed.
Draft or edit emails, messages, documents, and slides in the user's own voice. Use relevant writing samples to match the audience and medium while preserving the intended meaning, facts, and any wording that should stay.
Design multi-agent workflows for research, reviews, and migrations. Organize work across different evidence sources, add independent checks, and combine findings while preserving source references, unresolved questions, and limits on what was examined.
Review visual design choices before creating or styling web pages, components, apps, dashboards, or interactive reports. It flags repetitive colors, typography, layouts, and motion patterns to avoid, while keeping explicit user requests and other specified styles in control.
Create and revise fixed-layout PDFs such as reports, guides, and printable documents. The skill also covers reading, merging, splitting, cropping, and filling existing PDFs, with rendering checks and visual review before delivery.
Organize existing ChatGPT Pages and Spaces around the work readers need to do. The skill reviews page structure, moves pages, consolidates duplicate content, and improves navigation while preserving distinct requirements, historical context, and relevant layout details.