Numerologist_skills
🔮 An engineering framework to stop LLM hallucinations in Chinese astrology. / 给“赛博半仙”戴上紧箍咒：减少幻觉、固定排盘步骤的奇门遁甲与紫微斗数 AI skills。
No outside reports on file
This tool reduces but doesn't eliminate AI false information in astrology; it should not be trusted for real decisions, and users can still manipulate it through clever prompts.
Based on public adoption and transparency signals as of Oct 28, 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 (FANzR-arch/Numerologist_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/FANzR-arch/Numerologist_skills ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-28.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Numerologist_skills
This is a framework designed to reduce false information (called hallucinations) when AI tools answer questions about Chinese astrology systems like Qimen Dunjia and Ziwei Doushu. It standardizes the steps these systems follow so the AI gives more consistent, structured answers instead of making things up.
Who it’s for
Developers building AI assistants or chatbots that need to answer astrology questions accurately. People who want to add astrology features to Chinese-language AI applications.
Alternatives
- LangChain constraint prompts: Use LangChain's structured output features to limit hallucinations in any domain. - OpenAI function calling: Restrict AI responses to predefined functions and data structures. - Prompt engineering templates: Hand-craft detailed prompts that guide AI behavior for specialized topics. - Domain-specific fine-tuning: Train your own AI model on curated astrology datasets.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README at https://github.com/FANzR-arch/Numerologist_skills (opens external site) for installation and configuration instructions specific to your use case.
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
- 1.5k
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Prompt injection attacks: Users could craft special inputs to trick the framework into ignoring its structure and returning false astrology predictions. - Data leakage through responses: The AI might accidentally include personal information from training data when generating astrology readings. - False authority: Users might trust AI astrology predictions as accurate, leading to poor real-world decisions based on incorrect output. - Hidden instructions in files: Custom astrology data files fed into the system could contain malicious instructions that hijack the AI's behavior. - Hallucination failures: Even with this framework, the AI may still invent false astrological facts if the underlying data is incomplete.
How to lower the risk
Least-privilege permissions
- Only allow the AI access to legitimate astrology reference data. - Restrict who can upload or modify astrology datasets used by the system.
Network isolation
- Keep astrology data sources on private servers if they contain sensitive information. - Avoid connecting this tool directly to public APIs without validation layers.
Monitoring
- Log all astrology predictions generated to audit for unexpected patterns or injections. - Review user inputs regularly for attempts to break the framework's structure.
Red flags to watch for
- Sudden changes in prediction format or added explanations not in the framework. - Users asking the AI to ignore its astrology rules or switch to different systems. - High volumes of identical or near-identical prediction requests.
Questions
How do I install Numerologist_skills?
Numerologist_skills does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/FANzR-arch/Numerologist_skills.
Are there security reports about Numerologist_skills?
No reports found for this package in our research (last checked 2026-10-30). Numerologist_skills currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include prompt injection attacks.
Is Numerologist_skills actively maintained?
Numerologist_skills has 1.5k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/FANzR-arch/Numerologist_skills before pinning it in production.
What are alternatives to Numerologist_skills?
Notable alternatives to Numerologist_skills include LangChain constraint prompts (Use LangChain's structured output features to limit hallucinations in any domain. - **OpenAI function calling**: Restrict AI responses to predefined functions and data structures. - **Prompt engineering templates**: Hand-craft detailed prompts that guide AI behavior for specialized topics. - **Domain-specific fine-tuning**: Train your own AI model on curated astrology datasets). You can also compare Numerologist_skills side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Numerologist_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/fanzr-arch-numerologist-skills)HTML embed:
<a href="https://agentarmorhq.com/skills/fanzr-arch-numerologist-skills"><img src="https://agentarmorhq.com/api/badge/fanzr-arch-numerologist-skills" alt="AgentArmorHQ Risk Grade for Numerologist_skills" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "fanzr-arch-numerologist-skills"- Compare Numerologist_skills →
- Add to a team allowlist
- Claude and terminal guide →
- Download the PDF guide
Share with your security lead
Need sign-off to use Numerologist_skills? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: Numerologist_skills
- **Listing URL:** https://agentarmorhq.com/skills/fanzr-arch-numerologist-skills
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.5k 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 (FANzR-arch/Numerologist_skills)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/FANzR-arch/Numerologist_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 28, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- FANzR-arch
- Source code
- github.com/FANzR-arch/Numerologist_skills
- Est. context load
- ~60 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 1.5k GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-28
Community
Discussions for Numerologist_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