chuspeeism/dashi-ppt-skill

An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 6 minutes ago
Added to GitGenius on September 1st, 2026
Created on June 10th, 2026
Open Issues & Pull Requests: 18 (+0)
GitHub issues: Enabled
Number of forks: 719
Total Stargazers: 7,675 (+1)
Total Subscribers: 25 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 17.0 hours
Mean response time: 42.5 hours
90th percentile: 2.2 days
Tracked items: 26

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 13% of issues opened in the past year have been closed. Three people close 100% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 16
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 27 days
Stale 30+ days: 8
Stale 90+ days: 0

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 2

Top labels

  • enhancement (10)
  • bug (9)

Detailed Description

Dashi PPT Skill is an AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.

The tool solves the problem of creating polished presentations through AI agents by providing a skill that generates slides with built-in editing capabilities. Rather than producing static output, it renders presentations in the browser where users can modify unsatisfactory elements directly before exporting to standard formats. The skill includes twelve visual themes with over one thousand layout variations and thousands of controllable design elements, allowing agents to generate presentations that users can then refine interactively.

The tool suits workflows where an AI agent handles initial presentation generation but human review and adjustment are expected. It works well for users who want to feed documents to an agent and receive editable output rather than final, locked presentations. The browser-based editing interface lets users adjust content and styling without needing presentation software, and the ability to export to editable PPTX means the final output integrates with standard office tools. The skill supports multiple AI agent platforms including Claude Code, Codex, and several others.

Development activity shows consistent maintenance with regular updates addressing user feedback and feature refinement. The project maintains comprehensive documentation in multiple languages and actively supports integration with various AI agent ecosystems. The codebase demonstrates attention to user experience through the inclusion of extensive theme libraries and controllable design components, suggesting ongoing investment in making the tool practical for workplace use.