Skip to content
Agent Orchestration
Skill

/memory-stewardship

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.

BOOST
From plugin
rovai-ai
19812 skills
Install
$ npx -y skills add murray17/rovai-ai --skill memory-stewardship --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/memory-stewardship

Context preview

The summary Claude sees to decide when to auto-load this skill.

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.

SKILL.md

memory-stewardship.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.

Ships withrovai-ai

Desktop and web workspace for lasting teams of coding agents, with shared conversations, task delegation, and collaborative memory.

Get the whole plugin

Other skills on rovai-ai.