skills.rest
mbadoz
mbadozCOMMUNITY
Explore all skills by this author →
GitHub

openclaw-skelette

Enforces strict file-role separation for OpenClaw agent skeletons.

2|Updated Apr 5, 2026
Search Tags:#architecture#audit#memory-management#openclaw#agent-skeleton#zero-amnesia
One-click install
npx skills add https://github.com/mbadoz/mbadoz-skills --skill openclaw-skelette
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openclaw-skelette
Source: https://github.com/mbadoz/mbadoz-skills/tree/main/plugins/openclaw-skelette/skills/openclaw-skelette
Command: npx skills add https://github.com/mbadoz/mbadoz-skills --skill openclaw-skelette

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Solves the problem of ambiguous OpenClaw agent skeletons by enforcing strict file-role separation.

Core Features & Use Cases

  • Strict file separation by role (IDENTITY.md, SOUL.md, AGENTS.md, MEMORY.md, TOOLS.md, HEARTBEAT.md, USER.md) to prevent cross-contamination of responsibilities.
  • Reads references/file_structures.md to ensure correct role definitions before drafting or auditing.
  • Procedure for creation and audit: generate isolated file contents and validate against the audit checklist.
  • Use Case: when designing new OpenClaw agents or auditing existing skeletons for zero-ambition context bleed.

Quick Start

Generate a complete OpenClaw skeleton by creating the seven role files with explicit content that enforces single responsibility and no implicit context bleed.

Frequently Asked Questions about openclaw-skelette

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce strict file-role separation when designing OpenClaw agent skeletons?▼

Ensure zero-amnesia operation in OpenClaw agents by isolating context into specific role files: IDENTITY.md, SOUL.md, AGENTS.md, MEMORY.md, TOOLS.md, HEARTBEAT.md, and USER.md. This separation prevents cross-contamination of responsibilities and maintains persistent context.

How do I audit an existing multi-file OpenClaw agent for context bleed?▼

Audit an existing OpenClaw agent by validating its multi-file structure against references/file_structures.md and an audit checklist. Confirm each file maintains a single responsibility to eliminate implicit context bleed.

What files are required to build a complete OpenClaw agent skeleton?▼

A complete OpenClaw agent skeleton requires seven role files: IDENTITY.md, SOUL.md, AGENTS.md, MEMORY.md, TOOLS.md, HEARTBEAT.md, and USER.md. Each file must contain dedicated content enforcing single responsibility.

Why does my OpenClaw agent suffer from context leakage across components?▼

OpenClaw agents suffer context leakage when file roles are ambiguous and responsibilities overlap. Enforcing strict file-role separation and generating isolated content for each component prevents cross-contamination and enables zero-amnesia operation.

Can I use this approach to architect multi-file agents for memory management?▼

Yes, this approach applies to designing or auditing multi-file OpenClaw agents across memory management and other components. It ensures explicit file responsibilities and zero-amnesia operation through strict role separation.

Do I need references/file_structures.md to create a valid OpenClaw agent skeleton?▼

Yes, consulting references/file_structures.md is required to ensure correct role definitions before drafting or auditing OpenClaw agent skeletons. It provides the foundational structure for strict file-role separation.

Related Skills

Explore More Software Engineering Skills→
No-Trade-No-LifeNo-Trade-No-Life
351

recent-changes-digest

Generate Markdown reports summarizing git commit ranges and contributors.

Official
Intermediate
RheasilviaRheasilvia

openclaw-migration

Migrate OpenClaw user data, personas, and workspace configurations to Hermes Agent.

Community
Advanced
seanchiuaiseanchiuai
14

Status

Aggregate memory, cron, and ClaudeClaw status into a concise agent health summary.

Community
Intermediate
moughamirmoughamir

clean-architecture

Apply Clean Architecture rules to enforce dependency direction and boundary isolation.

Community
Advanced