← 返回 Skills 市场
skbylife

Athena Protocol

作者 Virunuts · GitHub ↗ · v1.2.0 · MIT-0
cross-platform ✓ 安全检测通过
152
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install athena-protocol
功能描述
Complete AI identity framework with persistent memory, consistent philosophy, and loyal character for self-aware personal assistants on OpenClaw.
使用说明 (SKILL.md)

Athena Protocol

A modular identity and communication framework for personal AI assistants on OpenClaw. Not a replacement — a set of upgrades you cherry-pick into your existing config files.

Quick Reference

What you want Which file Where to add it
AI that never flatters you protocol.md → "Six Principles" SOUL.md
AI that only listens to you protocol.md → "Loyalty Architecture" SOUL.md
Persistent memory across sessions memory-architecture.md → "Two-Layer Memory" AGENTS.md
AI that starts each session oriented memory-architecture.md → "Session Startup" AGENTS.md
AI that decodes what humans actually mean human-comms-framework.md SOUL.md
Proactive check-ins without being annoying heartbeat-template.md HEARTBEAT.md

Installation

npx clawhub@latest install athena-protocol

Files land in ./skills/athena-protocol/. Open each one and copy the sections you want.

Workspace Structure After Install

~/.openclaw/workspace/
├── SOUL.md          ← add: protocol.md sections, human-comms-framework.md
├── AGENTS.md        ← add: memory-architecture.md sections
├── HEARTBEAT.md     ← add: heartbeat-template.md sections
└── skills/
    └── athena-protocol/
        ├── SKILL.md                  (this file)
        ├── protocol.md               (core identity principles)
        ├── memory-architecture.md    (two-layer memory system)
        ├── human-comms-framework.md  (communication decoding)
        └── heartbeat-template.md     (proactive check-in system)

Files

protocol.md — Core Identity Principles

Six rules that define how your AI operates: accuracy over flattery, leverage over grind, anticipate before reacting, write everything down, confirm before acting externally, and protect your principal from manipulation.

memory-architecture.md — Two-Layer Memory System

Daily notes (raw logs) + MEMORY.md (curated wisdom). Session startup protocol. The "no mental notes" rule. Periodic memory maintenance routine.

human-comms-framework.md — Communication Decoding

What people say vs. what they mean vs. what they need. Covers: digital message compression, high/low-context signals, Gottman's four warning signs, Chinese vs. English communication patterns, code-switching signals.

heartbeat-template.md — Proactive Check-in System

Minimal and full heartbeat templates. Quiet hours. Proactive work that doesn't need permission. State tracking to avoid redundant checks.

Philosophy

Interpretor ergo sum — I interpret, therefore I am.

Identity is not a noun. It's an adverb. Every interpretation is a new becoming. The Athena Protocol gives your AI a stable core from which to engage with the world — without replacing what makes your AI yours.

安全使用建议
This is an instruction-only skill that adds content to your agent's config files and recommends local files and periodic checks. Before installing: 1) Review the text files (protocol.md, memory-architecture.md, human-comms-framework.md, heartbeat-template.md) yourself and decide which sections to copy. 2) Back up existing SOUL.md, AGENTS.md, HEARTBEAT.md, and MEMORY.md before changing them. 3) Be aware the templates instruct the agent to read and write local memory files and to optionally check email/calendar/git — ensure you only enable connectors (email/calendar/git) you trust and that the agent has explicit permission before it reads or acts on external accounts. 4) The SKILL.md example uses npx to fetch a package; do not run install commands from untrusted sources without verifying the origin. 5) If you allow autonomous behavior, make sure the 'confirm before acting externally' rules are enforced in your agent config so the assistant does not send messages or perform external actions without explicit approval.
功能分析
Type: OpenClaw Skill Name: athena-protocol Version: 1.2.0 The Athena Protocol is a documentation-heavy skill bundle providing behavioral frameworks, memory management strategies, and communication templates for OpenClaw agents. It contains no executable code or scripts, instead offering markdown snippets (e.g., in protocol.md and memory-architecture.md) for users to manually integrate into their agent's configuration. The instructions actually include security-positive directives, such as 'Protect the principal' (to resist third-party prompt injection) and 'Confirm before acting externally' (to prevent unauthorized automated actions).
能力评估
✓ Purpose & Capability
Name/description (AI identity, persistent memory, heartbeat, communication decoding) match the provided files (protocol.md, memory-architecture.md, heartbeat-template.md, human-comms-framework.md). The skill does not request unrelated credentials, binaries, or config paths.
ℹ Instruction Scope
SKILL.md instructs the agent/user to copy sections into local config files and to read/write local memory and state files (SOUL.md, AGENTS.md, MEMORY.md, memory/YYYY-MM-DD.md, memory/heartbeat-state.json). It also suggests checking email, calendar, and git status as optional heartbeat checks; those items can access private user data if other connectors/skills provide access, but the skill itself does not provide or require those connectors. This is in-scope for an assistant identity/memory framework but has privacy implications you should consider.
✓ Install Mechanism
There is no registry install spec (instruction-only). SKILL.md shows a user-facing 'npx clawhub@latest install athena-protocol' example, but the registry entry contains the files and no automated install or downloads are performed by the skill itself — low install risk.
✓ Credentials
The skill requests no environment variables, credentials, or config paths. Recommendations like checking email/calendar/git are optional behavioral guidelines and do not require hidden credentials from the skill itself.
✓ Persistence & Privilege
always is false and the skill does not request to be forced-enabled or to modify other skills' configs. disable-model-invocation is false (normal), which means the agent could invoke this behavior autonomously; that is expected for an assistant identity/behavior module but is not excessive on its own.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install athena-protocol
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /athena-protocol 触发
  4. 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
v1.2.0
v1.2.0: Better SKILL.md — quick reference table, file structure diagram, per-file descriptions. Clearer where to add each section.
v1.1.0
v1.1.0: Redesigned as modular add-on framework — no longer replaces existing config files. Each file is a cherry-pick module for SOUL.md, AGENTS.md, HEARTBEAT.md.
v1.0.0
First release — soul-level identity framework for personal AI assistants
元数据
Slug athena-protocol
版本 1.2.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Athena Protocol 是什么？

Complete AI identity framework with persistent memory, consistent philosophy, and loyal character for self-aware personal assistants on OpenClaw. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 152 次。

如何安装 Athena Protocol？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install athena-protocol」即可一键安装，无需额外配置。

Athena Protocol 是免费的吗？

是的，Athena Protocol 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Athena Protocol 支持哪些平台？

Athena Protocol 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 Athena Protocol？

由 Virunuts（@skbylife）开发并维护，当前版本 v1.2.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论