Skip to content
Back to skills

Memory Stewardship

ASecurity

Maintain durable collaboration preferences, agreements and lessons when the user asks to remember, correct or stop using them, or current evidence warrants capture. Excludes temporary work, project facts, sensitive data and speculation.

  • 130 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 2, 2026
ai-agents

Security analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned September 30, 2026

npx -y skills add murray17/rovai-ai --skill memory-stewardship --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Memory Stewardship?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Memory Stewardship
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/murray17-memory-stewardship/badge)](https://www.skillsdirectory.com/skills/murray17-memory-stewardship)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: memory-stewardship
description: Maintain durable collaboration preferences, agreements and lessons when the user asks to remember, correct or stop using them, or current evidence warrants capture. Excludes temporary work, project facts, sensitive data and speculation.
---

# Memory stewardship

Preserve only information that will change future collaboration. Current instructions, facts and project authority outrank Memory. Use the user's language for Memory content and reports.

1. Read [Authority and safety](references/authority-and-safety.md) to assess eligibility.
2. Reduce the candidate to one durable understanding; select its smallest valid [Scope and Kind](references/scopes.md).
3. Follow [Read and write](references/read-write-workflow.md): inspect the complete applicable Scope, then stop, revise or add once.
4. Before writing, apply [Body and retrieval keys](references/content-and-keys.md).
5. Report the actual outcome: effective, pending user review, or not written.

Do not run an end-of-conversation Memory sweep or write several speculative candidates. Deletion, deactivation, restoration and changes outside the Agent's authority require the user's Memory management controls; an opposite statement cannot simulate those actions.

Files in this skill

  • NOTICE439 B
  • SKILL.md2.2 KB
  • agents/openai.yaml303 B
  • references/authority-and-safety.md2.2 KB
  • references/content-and-keys.md1.5 KB
  • references/read-write-workflow.md4.4 KB
  • references/scopes.md2.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.