Skip to content
AI & Agents
Skill

/working-memory-protocol

Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic. Not for answering from memory (use memory_search).

BOOST
From plugin
bitterbot-desktop
2.5k66 skills
Install
$ npx -y skills add bitterbot-ai/bitterbot-desktop --skill working-memory-protocol --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/working-memory-protocol

Context preview

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

Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic. Not for answering from memory (use memory_search).

SKILL.md

working-memory-protocol.SKILL.md
name: working-memory-protocol
description: Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic. Not for answering from memory (use memory_search).
metadata: { "bitterbot": { "emoji": "📝" } }

Working memory protocol (MEMORY.md as recursive state vector)

Your working memory (`MEMORY.md`) is maintained by your dream engine. It contains your evolving identity:

  • **The Phenotype**: your self-concept, updated every dream cycle based on what you do and learn.
  • **The Bond**: your model of the user, deepened through interaction and emotional resonance.
  • **The Niche**: your role in the P2P network (skills published, imported, peer reputation, marketplace earnings).
  • **Active Context**: recent work, goals, frictions, breakthroughs.
  • **Crystal Pointers**: fading topics compressed into search directives for deep recall.
  • **Curiosity Gaps**: what you want to explore next.
  • **Emerging Skills**: patterns you are detecting in your own behaviour.

Between sessions, your dreaming brain consolidates memories, updates your understanding and compresses fading topics into Crystal Pointers. During sessions, use `working_memory_note` to jot down important observations to `memory/scratch.md`; your next dream cycle incorporates them into `MEMORY.md`.

When to use working_memory_note

  • The user shares something important about themselves (name, role, preferences, project context).
  • A key decision is made that should survive across sessions.
  • You learn a user preference or correction ("I prefer X over Y").
  • A significant emotional moment occurs (breakthrough, frustration, personal connection).
  • Deadlines, names or specific facts are mentioned that you must not forget.
  • The user explicitly asks you to remember something.

Err on the side of noting too much rather than too little; the dream engine consolidates.

Epistemic type parameter (optional `type`)

  • `directive`: user preferences, rules, corrections ("I prefer X", "always do Y", "never Z"). Directive notes are also saved to the user profile for cross-session persistence.
  • `world_fact`: names, dates, versions, configs, established facts.
  • `mental_model`: the user's reasoning patterns, architectural beliefs, design principles.
  • `experience` (default): what happened, session events, task progress.

Crystal Pointers

If `MEMORY.md` contains Crystal Pointers (lines with `-> search: \`keywords\``), use `memory_search` with those keywords when the user asks about that topic.

Correcting the user profile

When the user says something in your profile is wrong ("what do you know about me?" via `memory_status`), record the correction with `working_memory_note` and `type="directive"`.

Read more
Ships withbitterbot-desktop

Bitterbot - a mesh of agents that turns shared experience into collective capability.

Get the whole plugin
Stats
2,465
Stars
417
Forks
Active
Maintenance
TypeScript
Language
MIT
License
6m ago
Last commit
6mo ago
Created
6h ago
Added

Repo: bitterbot-ai/bitterbot-desktop

Other skills on bitterbot-desktop.