ClawHub

Liuyao Yijing — 六爻易经占卜

v1.0.0

六爻易经占卜器，基于京房纳甲体系，模拟铜钱起卦，完成纳甲装卦（天干地支、世应、六亲、六神）， 通过用神旺衰和生克制化断卦。当用户提及「六爻」「易经占卜」「铜钱起卦」「纳甲」「帮我起一卦」 「六爻预测」时触发。装卦为确定性计算 + LLM 综合断卦，无外部 API 依赖。 不适用于：梅花易数、奇门遁甲、星座运势、塔...

⭐ 0· 148·0 current·0 all-time
byeamanc@eamanc-lab
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (六爻易经占卜) matches the instructions and included reference tables: the skill performs local deterministic calculations (铜钱/报数起卦, 纳甲/纳支/六神/六亲等) and uses LLM text for interpretation. It requests no external credentials, binaries, or unrelated resources.
ℹ
Instruction Scope
Runtime instructions are explicit and self-contained: follow the included calculation tables, simulate coin tosses, and produce formatted output. The only external data the skill reads/writes are MEMORY.md in its directory and optionally fortune-hub/MEMORY.md. This is coherent for storing/using user preferences but is a privacy-relevant behavior (the skill will silently use stored preferences if present). There are no external network calls or hidden endpoints in the instructions.
✓
Install Mechanism
There is no install spec and no code files to install or execute; the skill is instruction-only. This is the lowest-risk install mechanism and matches the declared behavior.
✓
Credentials
The skill requires no environment variables, credentials, or special config paths. Its only declared file access (MEMORY.md in-skill and in-fortune-hub) is proportionate to the stated goal of remembering user preferences; no unrelated secrets are requested.
ℹ
Persistence & Privilege
always:false (default) and model invocation are unmodified. The skill will read MEMORY.md automatically before execution and will write MEMORY.md only when the user explicitly asks to save preferences. This file I/O is reasonable for preference storage but could expose repository-local data if MEMORY.md contains other sensitive content.
Scan Findings in Context
[no_code_files] expected: The regex-based scanner had no code to analyze because the skill is instruction-only; this is expected for a rules-and-text-driven calculator skill.
Assessment
This skill appears coherent and low-risk: it performs local deterministic calculations using the included tables and only uses the LLM for interpretation. Before installing, review the referenced MEMORY.md files in the skill repo (and fortune-hub/MEMORY.md if present) so you know what will be read and what might be written when you ask to save preferences. If you store any sensitive information in repository memory files, remove or sanitize it. Confirm the GitHub homepage/source is trustworthy (the skill lists a repo URL) if provenance matters. Because the skill can be invoked by the agent, be aware it may read existing MEMORY.md preferences silently when asked to run; it will only write to MEMORY.md when you explicitly request saving preferences. If you want stronger isolation, run the skill in a sandboxed agent or ask the maintainer for a signed/verified release.

Like a lobster shell, security has layers — review code before you run it.

latestvk977rx7x1z8djef0r2aa1nwh3983d8nv

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments