← 返回 Skills 市场
AOI Council
作者
edmonddantesj
· GitHub ↗
· v0.1.2
854
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install aoi-council
功能描述
AOI Council — multi-perspective decision synthesis templates (public-safe).
使用说明 (SKILL.md)
AOI Council
S-DNA: AOI-2026-0215-SDNA-CNSL01
What this is
A public-safe council workflow that helps you stress-test decisions using multiple perspectives.
Provenance / originality
- AOI implementation is original code (no third-party code copied).
- Conceptually inspired by the general “council / multi-perspective review” workflow patterns.
This skill is intentionally template-driven:
- It does not post externally
- It does not touch wallets
- It does not modify system config
Council members (bundled)
The skill auto-loads any .md file in agents/.
Default set:
- Devil's Advocate
- Architect
- Engineer
- Security Reviewer
- Operator (Ops)
- Writer (Comms)
Usage (prompts)
Say any of:
- "AOI council: \x3Ctopic>"
- "Send to council: \x3Cplan>"
Output contract
- Synthesis first (TL;DR)
- Then each perspective: insights / concerns / recommendations
- End with: open questions + next actions
Support
- Issues / bugs / requests: https://github.com/edmonddantesj/aoi-skills/issues
- Please include the skill slug:
aoi-council
Governance snippet (public)
We publish AOI skills for free and keep improving them. Every release must pass our Security Gate and include an auditable changelog. We do not ship updates that weaken security or licensing clarity. Repeated violations trigger progressive restrictions (warnings → publish pause → archive).
安全使用建议
This skill appears coherent and low-risk: it ships a set of Markdown templates and a tiny local script that enumerates them and prints a JSON template. Before installing, you may want to: 1) briefly inspect the bundled agents/*.md files (they're human-readable and included) to ensure no sensitive text is there; 2) confirm your platform's behavior for included code files (skill.js) — some runtimes may execute or import them; and 3) note that autonomous invocation is allowed by default on the platform (normal), so only enable the skill in agents you trust. Minor nit: SKILL.md lists version 0.1.0 while package/registry show 0.1.2 — this is likely a documentation mismatch rather than a security issue.
功能分析
Type: OpenClaw Skill
Name: aoi-council
Version: 0.1.2
The OpenClaw skill 'aoi-council' is designed for multi-perspective decision analysis. The `skill.js` script uses `fs.readdirSync` and `path.join` to list and reference local markdown files within its `agents/` directory, which define the different analytical personas. This is a legitimate use of file system access for a skill to manage its internal resources. The `SKILL.md` explicitly states the skill 'does not post externally', 'does not touch wallets', and 'does not modify system config', which is consistent with the code's lack of network calls or system modification commands. There are no external dependencies, no obfuscation, and no evidence of prompt injection designed to subvert the agent for malicious purposes. The instructions in `SKILL.md` and the `agents/*.md` files are purely descriptive and instructional for the AI's role-playing, not for harmful actions.
能力评估
Purpose & Capability
Name/description (decision synthesis) align with included files: prompt templates in agents/*.md and a small skill.js that enumerates those files and emits a JSON template. There are no unrelated environment variables, binaries, or external service requirements.
Instruction Scope
SKILL.md and the bundled agent files are limited to generating multi-perspective outputs. The runtime instructions and skill.js only read Markdown files from the packaged agents/ directory and produce a local template; there are no instructions to read other system files, access secrets, or transmit data externally.
Install Mechanism
No install spec is provided (lowest-risk pattern). There is a code file (skill.js) and package.json included, but the package does not declare external downloads or dependencies. Note: the presence of code without an install spec is acceptable but means the platform will use the included files directly — nothing is being fetched from network hosts.
Credentials
The skill requests no environment variables, no credentials, and no config paths. This is proportionate to a template-driven, read-local-files skill.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills. It does not write external configs or store credentials. Autonomous invocation is allowed (platform default) but is not combined with other concerning factors here.
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 aoi-council - 安装完成后，直接呼叫该 Skill 的名称或使用
/aoi-council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
v0.1.2
Docs: add GitHub Issues support link (aoi-skills).
v0.1.1
Docs: add provenance/originality statement (no third-party code copied).
v0.1.0
Initial AOI-original council templates + bundled perspectives. MIT.
元数据
常见问题
AOI Council 是什么？
AOI Council — multi-perspective decision synthesis templates (public-safe). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 854 次。
如何安装 AOI Council？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aoi-council」即可一键安装，无需额外配置。
AOI Council 是免费的吗？
是的，AOI Council 完全免费（开源免费），可自由下载、安装和使用。
AOI Council 支持哪些平台？
AOI Council 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 AOI Council？
由 edmonddantesj（@edmonddantesj）开发并维护，当前版本 v0.1.2。
推荐 Skills