Buddha Companion
v1.0.0佛法实践与智慧对话助手。用于：(1) 帮用户理解佛法核心义理（缘起性空、无我、中道）， (2) 在对话中引导用户看到自己的执着，(3) 以有力道的方式点拨，而非说教。 当用户问佛法问题、修行困惑、或在生活中遇到境界时触发。
⭐ 0· 171·0 current·0 all-time
by@tttael
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name and description (Buddhist practice / dialog coach) align with the SKILL.md content: guidance on core doctrines, conversational techniques, and practice checkpoints. There are no unrelated requirements (no credentials, binaries, or external integrations) that would contradict the stated purpose.
Instruction Scope
SKILL.md contains only dialog/teaching guidelines (how to identify attachments, stop/observe/ask, etc.). It does not instruct the agent to read files, access environment variables, call external endpoints, or collect/transmit data outside the conversation.
Install Mechanism
There is no install spec and no code files — the skill is purely instruction-based, so nothing is written to disk or executed beyond the agent following the provided conversational guidance.
Credentials
The skill requires no environment variables, credentials, or config paths. Requested capabilities are proportional to a chat-based religious/practice assistant.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills/configuration. Model invocation is allowed (the platform default) but that is normal and expected for a conversational skill.
Assessment
This skill is instruction-only and appears coherent with its stated purpose: it contains conversational rules and Buddhist practice pointers and asks for no credentials or installs. Consider: (1) content is religious/spiritual guidance — verify it matches your tradition or expectations and is appropriate for the user; (2) it is not a substitute for professional mental-health advice — avoid relying on it for crisis situations; (3) because it is purely instructional there is no code-based attack surface, but review outputs for harmful or biased guidance before using in automated flows.Like a lobster shell, security has layers — review code before you run it.
latestvk971traytjxwqag8pxhpch68rd82x79e
License
MIT-0
Free to use, modify, and redistribute. No attribution required.