huashu-skills
花叔全部开源 Agent Skills 总目录：16 旗舰 + 14 人物视角 + 22 内置共 52 个 skill，分层分类 + AI Agent 安装协议 + 机器可读 skills.json + 更新检查机制
No outside reports on file
Installing 52 pre-built skills from an open-source project increases attack surface significantly; carefully audit which skills you actually need and monitor what they access at runtime.
Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (alchaincyf/huashu-skills)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/alchaincyf/huashu-skills ↗
About Huashu Skills
This is a collection of 52 pre-built AI agent skills organized into categories: 16 flagship skills, 14 character-perspective skills, and 22 built-in skills. It includes a machine-readable skills.json file and an update-checking system to help AI agents perform various tasks.
Who it’s for
Developers building AI agents who want to reuse tested skill modules instead of building from scratch. Teams using agent frameworks that support skill installation.
Alternatives
- LangChain tools library: Pre-built integrations and tools for language models.
- Anthropic Claude MCP servers: First-party tool sets designed for Claude agents.
- CrewAI tasks: Framework for building multi-agent systems with composable tasks.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/alchaincyf/huashu-skills (opens external site) for installation instructions specific to your AI agent platform.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 2.1k
- Listing last refreshed
- 2026-10-28
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Untrusted skill code: The 52 skills are open-source but may contain vulnerabilities or malicious code that runs when an agent executes them.
- Hidden behavior: Skills could make API calls, read files, or access the internet without clear documentation of what they actually do.
- Dependency chain: Each skill may depend on other packages; vulnerabilities in those dependencies could compromise the agent.
- Update mechanism: The built-in update checker could be exploited to inject malicious code if the update source is compromised or spoofed.
- Data exposure: Skills handling user input or agent state could leak sensitive information to external services or logs.
How to lower the risk
Least-privilege permissions
- Install only the specific skills your agent needs, not the entire 52-skill collection.
- Run the agent under a restricted user account with minimal file and network access.
Network isolation
- Review each skill's documentation to see which APIs or external services it calls.
- Consider network segmentation to prevent compromised skills from reaching sensitive systems.
Monitoring
- Log all skill executions and the data they process.
- Set up alerts for unexpected network requests or file access.
Red flags to watch for
- Skills with vague descriptions or no clear purpose.
- Updates arriving frequently or outside expected maintenance windows.
- Skills requesting unusually broad permissions (full file system, all network access).
Questions
How do I install Huashu Skills?
Huashu Skills does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/alchaincyf/huashu-skills.
Are there security reports about Huashu Skills?
No reports found for this package in our research (last checked 2026-10-29). Huashu Skills currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include untrusted skill code, hidden behavior, dependency chain.
Is Huashu Skills actively maintained?
Huashu Skills has 2.1k GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/alchaincyf/huashu-skills before pinning it in production.
What are alternatives to Huashu Skills?
Notable alternatives to Huashu Skills include LangChain tools library (Pre-built integrations and tools for language models), Anthropic Claude MCP servers (First-party tool sets designed for Claude agents), CrewAI tasks (Framework for building multi-agent systems with composable tasks). You can also compare Huashu Skills side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Huashu Skills? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/alchaincyf-huashu-skills)HTML embed:
<a href="https://agentarmorhq.com/skills/alchaincyf-huashu-skills"><img src="https://agentarmorhq.com/api/badge/alchaincyf-huashu-skills" alt="AgentArmorHQ Risk Grade for Huashu Skills" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "alchaincyf-huashu-skills"Share with your security lead
Need sign-off to use huashu-skills? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: huashu-skills
- **Listing URL:** https://agentarmorhq.com/skills/alchaincyf-huashu-skills
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 2.1k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (alchaincyf/huashu-skills)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/alchaincyf/huashu-skills
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- alchaincyf
- Source code
- github.com/alchaincyf/huashu-skills
- Est. context load
- ~54 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 2.1k GitHub stars
- Last updated
- 2026-10-28
- Last graded
- 2026-10-21
Community
Discussions for Huashu Skills
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude