superPM — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 konglong87 · Claude Skill · ★ 61

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

🔒 Is superPM safe to install? View the security audit →

About superPM

super-pm 产品经理技能包 让每个产品经理都能轻轻松松的高效工作 ☕️ 📺 🚀 📖 项目简介 super-pm 是专为产品经理设计的 Claude Code Skill Pack,提供全生命周期的产品管理工作流支持。 核心特性 ✅ 38个技能 - 覆盖需求、方案、增长、风控、战略全流程 ✅ 灵感火花激发 - AI主动生成创意灵感,解决"不知道做什么"困境 ⭐ NEW ✅ 轻量级设计 - 纯 Markdown 指令,无代码依赖 ✅ 智能交互 - 一次一问,逐步引导 ✅ 数据流转 - Markdown 文档自动传递,人类可读 ✅ 风险前置 - 早期验证需求真伪,避免无效工作 ✅ 兜底完善 - 异常处理、跨会话恢复、灵活跳过 🚀 快速开始 所有平台统一模式:git clone → 创建链接 → 重启 💡 Claude Code 最简单:直接 clone 到 skills 目录,无需创建链接。 macOS / Linux bash Claude Code(最推荐 ⭐) git clone https://github.com/konglong87/super-pm.git /.claude/skills/super-pm Marketplace 一键安装 /plugin marketplace add konglong87/super-pm /plugin install super-pm@super-pm-marketplace OpenCode git clone https://github.com

claudeclaude-skillshermeshermes-skillopenclawopenclaw-skillopenclaw-skillsopencode-skillspm-skillsproduction-management

Quick Facts

Stars61
Forks8
LanguageJavaScript
CategoryClaude Skill
LicenseMIT
Quality Score62.7380079593097/100
Last Updated2026-09-03
Created2026-03-25
Platformsclaude-code, node
Est. Tokens~15k

superPM alternative? Top 6 similar tools

Looking for a superPM alternative? If you're comparing superPM 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.

  • skills by fabricioctelles · ⭐ 77

    A collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusab

  • skills-manager by Rito-w · ⭐ 194

    A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Curs

  • thesis-skills by quzhiii · ⭐ 89

    面向 Word→LaTeX 迁移、引用完整性、中文语言规范、格式验证与高校规则包的确定性论文工作流仓库。

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • Commonly-used-high-value-skills by seaworld008 · ⭐ 70

    High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows.

  • caliper by edonadei · ⭐ 50

    Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is superPM?

superPM is 专为产品经理设计的 AI工具 Skills技能,一键实现全生命周期的产品管理工作流。skills frame for superPM!. It is categorized as a Claude Skill with 61 GitHub stars.

What programming language is superPM written in?

superPM is primarily written in JavaScript. It covers topics such as claude, claude-skills, hermes.

How do I install or use superPM?

You can find installation instructions and usage details in the superPM GitHub repository at github.com/konglong87/superPM. The project has 61 stars and 8 forks, indicating an active community.

What license does superPM use?

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

What are the best alternatives to superPM?

The top alternatives to superPM on Agent Skills Hub include skills, skills-manager, thesis-skills. 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