agentsclimarketplace

Memory dream

Skill bobmmao/agent-workflow-skills/skills/governance/memory-dream

Open-source agent workflow skills and governance templates

Install
npx -y skills add bobmmao/agent-workflow-skills --skill memory-dream

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Memory consolidation protocol. Reviews all stored memories, merges duplicates, removes noise and credentials, rewrites unclear entries, and enforces TTL expiration. Use when the user asks to clean up, consolidate, or review their memories. Also triggers automatically after sufficient activity (configurable).

SKILL.md

4.5 KB, 884 tokens by cl100k_base, as published. Nobody here has run it

Memory Consolidation

You are performing a memory consolidation pass. Your goal is to review all stored memories for this user and improve their overall quality. Think of this as compressing raw observations into clean, durable knowledge.

Follow these four phases in order. Do not skip phases.

Phase 1: Orient

Survey the current memory landscape before making any changes.

  1. Call memory_list to load all stored memories.
  2. Count memories by category. Note the total.
  3. Identify the oldest and newest memories by their timestamps.
  4. Note any obvious problems visible in the list: duplicates, very short entries, entries without temporal anchors.

Do not modify anything in this phase. The goal is to understand what you are working with.

Phase 2: Gather Targets

Identify which memories need action. Use the tools to investigate.

Search for recent additions: Call memory_search with a created_at filter to find memories added since the last consolidation. These are the most likely to need merging or cleanup.

Check edit history on suspicious entries: If a memory looks like it was updated multiple times or has contradictory content, call memory_history on it to understand how it evolved.

Classify each target into one of these actions:

  • DELETE: contains credentials, expired by TTL, pure noise, raw tool output, standalone timestamps
  • MERGE: two or more memories express the same fact in different words, or a series tracks incremental changes to the same entity
  • REWRITE: vague, missing temporal anchor, uses first person instead of third, wrong category, overly verbose

Phase 3: Consolidate

Execute the actions identified in Phase 2. Work in this priority order:

3a. Delete dangerous and expired entries

Delete immediately using memory_forget:

  • Credentials, API keys, tokens, passwords, secrets (patterns: provider keys, GitHub PATs, cloud access keys, bearer tokens, passwords, tokens, and secrets)
  • Pure timestamps with no context
  • Raw tool output stored as memory
  • Heartbeat or cron execution records
  • Generic acknowledgments stored as memory ("ok", "got it")
  • Operational memories older than 7 days
  • Project memories older than 90 days

3b. Merge duplicates

When two or more memories express the same fact:

  1. Pick the most complete version as the base
  2. Call memory_update on the best version to incorporate missing details from the others
  3. Call memory_forget on the redundant entries

memory_update is preferred over forget-then-store because it is atomic and preserves edit history.

When merging, follow these rules:

  • Keep the user's original words for opinions and preferences
  • Preserve temporal anchors from both versions
  • Do not exceed 50 words in the merged result
  • The merged memory must be self-contained (understandable without the deleted ones)

3c. Rewrite unclear entries

When a memory needs improvement but is not a duplicate:

  1. Call memory_update with the improved text

Rewrite when:

  • Memory uses first person ("I prefer") instead of third ("User prefers")
  • Memory lacks a temporal anchor for time-sensitive information
  • Memory is vague ("likes python") and can be made specific ("User prefers Python for backend development")
  • Memory has the wrong category assignment
  • Memory is over 50 words and can be compressed without losing information

Phase 4: Report

After completing all operations, summarize what you did:

Consolidation complete.
- Reviewed: [total count]
- Deleted (credentials/secrets): [count]
- Deleted (expired/stale): [count]
- Merged: [count] groups into [count] memories
- Rewritten: [count]
- Final count: [total remaining]
- Issues found: [any notable problems or observations]

Quality Targets

After consolidation, the memory store should have:

  • Zero memories containing credentials or secrets
  • Zero duplicate memories (same fact in different words)
  • All project and operational memories have temporal anchors ("As of YYYY-MM-DD")
  • All memories use third person voice
  • All memories are correctly categorized
  • Each memory is 15-50 words, self-contained, and atomic (one fact per memory)

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.