claude-keysmith — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 Jia-Ethan · Claude Skill · ★ 757

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is claude-keysmith safe to install? View the security audit →

About claude-keysmith

Illustrative preview / 示意预览;实际路径与输出以本机 dry-run 为准。 claude-keysmith 先预览、再写入、可撤销的 Claude Code 指令部署工具。 简体中文 · English · Reference · 智能体安装 · Desktop · Privacy · License 简体中文 Keysmith 系列为本地 AI 工具安全部署、验证和撤销自定义指令。 把一份 Markdown 存进 keysmith 目录,并在 / 插入可识别、可卸载的 import block。 [!WARNING] 项目 / local scope 只影响该仓库;user scope 会影响加载 的新会话。 还会对齐 的 ,并安装 managed shell wrapper。默认只预览,显式 才写入。先阅读 、 和 。 选择哪个 Keysm

claude-codedesktop-appdeveloper-toolsmacosprompt-managementpythontauriwindows

Quick Facts

Stars757
Forks138
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score65.9361111182858/100
Last Updated2026-09-11
Created2026-06-29
Platformsclaude-code, cli, python
Est. Tokens~14k

Compatible Skills

These tools work well together with claude-keysmith for enhanced workflows:

  • claude-overlay — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)
  • Clutch — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • Codex-Mate — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • mcp-remote-macos-use — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)
  • macLLM — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (58%)

claude-keysmith alternative? Top 6 similar tools

Looking for a claude-keysmith alternative? If you're comparing claude-keysmith 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.

  • claude-code-history-viewer by jhlee0409 · ⭐ 2.1k

    desktop app to browse and analyze your Claude Code conversation history

  • OpenContext by 0xranx · ⭐ 729

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • daymon by daymonio · ⭐ 368

    Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr

  • OpenCovibe by AnyiWang · ⭐ 261

    Local-first desktop app for AI coding agents (Claude Code, Codex). Built with Tauri v2 + Svelte 5.

  • skills-hub by qufei1993 · ⭐ 1.7k

    A cross-platform desktop app to manage Agent Skills in one place and sync them to multiple AI coding tools’ gl

  • fyagent by fy-agent · ⭐ 1.1k

    For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式,带到每一个 AI 工具里。

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is claude-keysmith?

claude-keysmith is Managed Claude Code instruction deployment with safe CLI recovery and an unsigned macOS/Windows desktop beta.. It is categorized as a Claude Skill with 757 GitHub stars.

What programming language is claude-keysmith written in?

claude-keysmith is primarily written in Python. It covers topics such as claude-code, desktop-app, developer-tools.

How do I install or use claude-keysmith?

You can find installation instructions and usage details in the claude-keysmith GitHub repository at github.com/Jia-Ethan/claude-keysmith. The project has 757 stars and 138 forks, indicating an active community.

What license does claude-keysmith use?

claude-keysmith is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to claude-keysmith?

The top alternatives to claude-keysmith on Agent Skills Hub include claude-code-history-viewer, OpenContext, daymon. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools