No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by fivetaku · Claude Skill · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-office-skills safe to install? View the security audit →
English | 한국어 claude-office-skills Claude in Excel & Claude in PowerPoint skills, restored for Claude Code. Anthropic ships domain skills inside Claude in Excel and Claude in PowerPoint add-ins. This repo reconstructs those skills as plain files so you can drop them into Claude Code and use them outside the Office add-ins — on local spreadsheets, files, files, or any workflow where Claude Code has filesystem access. Quick Start • Skills • Install • Disclaimer Quick Start Clone Copy skills into Claude Code Trigger in Claude Code Each skill has natural-language triggers declared in its frontmatter. Just say what you want: Claude Code auto-matches the request to the correct skill. Skills 📊 claude-in-excel (6 skills)
| Stars | 70 |
| Forks | 11 |
| Language | Python |
| Category | Claude Skill |
| Quality Score | 68.7588501062901/100 |
| Last Updated | 2026-04-08 |
| Created | 2026-04-08 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
These tools work well together with claude-office-skills for enhanced workflows:
Explore other popular claude skill tools:
claude-office-skills is Claude in Excel & Claude in PowerPoint skills, restored as SKILL.md for Claude Code — DCF, LBO, 3-statement, comps, deck refresh, and more.. It is categorized as a Claude Skill with 70 GitHub stars.
claude-office-skills is primarily written in Python.
You can find installation instructions and usage details in the claude-office-skills GitHub repository at github.com/fivetaku/claude-office-skills. The project has 70 stars and 11 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: