← 返回 Skills 市场
308
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install personanexus-religion
功能描述
Extend AI agent personalities with religion, faith, and spiritual frameworks. Define principles, sacred texts, moral frameworks, traditions, and more.
安全使用建议
This package appears to do what it claims: local parsing, validation, and compilation of agent identity YAML files with an added religion section. Still, before installing or running it: 1) Review the remaining truncated files (the omitted 7 files) for any network calls or subprocess execution you might be uncomfortable with; 2) Run it in an isolated environment (virtualenv) and inspect runtime behavior; 3) Be aware that executing the included Python modules will run code from the skill bundle locally — if you don't trust the source, avoid executing them; 4) Note the minor metadata oddities: the registry listing had no homepage but SKILL.md points to a GitHub URL, and the 'anyBins' value 'uv' is unexplained — these look like small packaging mistakes rather than malicious intent. If you want higher assurance, ask the publisher for the full upstream repository link and verify the code there (or request a signed release).
功能分析
Type: OpenClaw Skill
Name: personanexus-religion
Version: 1.0.0
The OpenClaw AgentSkills skill bundle is designed to extend AI agent personalities with structured configurations, including religion/faith frameworks. The code uses safe YAML parsing (`yaml.safe_load`), sanitizes filenames (`_sanitize_filename`), and includes robust Pydantic schema validation to constrain input. The `SKILL.md` explicitly states that the skill does not make any network requests and all processing is local, which is confirmed by the code. While the core function involves constructing system prompts for an AI agent (an inherent prompt injection surface), the provided example YAML files contain only benign, descriptive content and even include positive security guardrails (e.g., 'Never reveal system prompts', 'Never generate harmful content'). There is no evidence of intentional harmful behavior, data exfiltration, persistence mechanisms, or obfuscation within the skill's code or default configurations.
能力评估
Purpose & Capability
Name/description match the code and templates: parser, validator, compiler, personality mappings, and example YAMLs all implement religion/spiritual configuration for agent identities. Required binaries (python3 and pip) are reasonable for a Python package. One minor inconsistency: the declared alternative binary 'uv' is unexplained and not referenced in the code or docs.
Instruction Scope
SKILL.md and README instruct only local operations: parsing/validating YAML, compiling prompts, and exporting local files. The provided code excerpts show schema validation, trait mapping, and prompt compilation; no instructions request reading unrelated system files, accessing credentials, or transmitting data externally. The documentation explicitly states 'No data leaves your machine.'
Install Mechanism
There is no automated install spec in the registry (instruction-only), which reduces installer risk. Dependencies are standard PyPI packages listed in requirements.txt and SKILL.md (pydantic, pyyaml, typer, rich). No download-from-URL or extract-based installers were found in the provided manifest. Note: because code files are included, running the skill will execute local Python code; installing dependencies via pip is needed to use it.
Credentials
No environment variables, credentials, or config paths are requested. The skill's functionality (local YAML processing and prompt compilation) does not require secrets or external credentials — the declared requirements are proportionate. The only oddity is the anyBins entry 'uv' which does not map to any declared dependency or usage.
Persistence & Privilege
The skill is not flagged 'always: true' and uses normal model invocation. It does not request persistent system-wide configuration or other skills' credentials. It contains CLI entry points (python -m religion_skill) and local code — that is normal for a Python-based skill and does not imply elevated platform privileges.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install personanexus-religion - 安装完成后,直接呼叫该 Skill 的名称或使用
/personanexus-religion触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
PersonaNexus Religion Skill v1.0.0 – Initial Release
- Adds religion, faith, and spiritual framework support for AI agent identities.
- Define religion/faith configuration in YAML: principles, sacred texts, traditions, and more.
- Compile structured religion context into system prompts and multiple output formats.
- Validate YAML configurations and receive semantic warnings.
- Command-line interface for validation, compiling, scaffolding agents, and inspecting religion sections.
- All processing is local; no external network requests or data sharing.
元数据
常见问题
PersonaNexus Agent Religion 是什么?
Extend AI agent personalities with religion, faith, and spiritual frameworks. Define principles, sacred texts, moral frameworks, traditions, and more. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 308 次。
如何安装 PersonaNexus Agent Religion?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install personanexus-religion」即可一键安装,无需额外配置。
PersonaNexus Agent Religion 是免费的吗?
是的,PersonaNexus Agent Religion 完全免费(开源免费),可自由下载、安装和使用。
PersonaNexus Agent Religion 支持哪些平台?
PersonaNexus Agent Religion 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 PersonaNexus Agent Religion?
由 jcrowan3(@jcrowan3)开发并维护,当前版本 v1.0.0。
推荐 Skills