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 narghev · Claude Skill · ★ 7
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is askdiff safe to install? View the security audit →
Ask your AI questions about its own code changes — from a Git diff viewer.
| Stars | 7 |
| Forks | 1 |
| Language | TypeScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 63.1866326406903/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-11 |
| Created | 2026-04-24 |
| Platforms | claude-code, node |
| Est. Tokens | ~3834k |
Looking for a askdiff alternative? If you're comparing askdiff with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Best Practices for Claude Code Configuration
Bring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive au
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Skills for AI coding agents — Laravel, PHP, React, TypeScript, testing, security, and code quality.
AI-powered security assessment SKILLS for your codebase. Multi-language (JS, Go, Python, Rust, Java, PHP, Ruby
Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors
Explore other popular claude skill tools:
askdiff is Ask your AI questions about its own code changes — from a Git diff viewer.. It is categorized as a Claude Skill with 7 GitHub stars.
askdiff is primarily written in TypeScript. It covers topics such as agentic-coding, ai, ai-code-review.
You can find installation instructions and usage details in the askdiff GitHub repository at github.com/narghev/askdiff. The project has 7 stars and 1 forks, indicating an active community.
askdiff is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to askdiff on Agent Skills Hub include claude-code-settings, claude_code_vs, claude-emporium. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: