ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

memory-distiller

Distill repeated user preferences, successful patterns, and durable working rules into reusable memory notes or prompt-ready context blocks. Use when a user wants to capture habits, preserve preferences, summarize lessons from prior work, or convert raw conversation/task outcomes into structured memory.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/danxbuidl/danxbuidl-memory-distiller
Or

Memory Distiller

Overview

Use this skill when the user wants to turn raw interaction history into stable, reusable memory. The goal is not to summarize everything. The goal is to keep only the parts that are durable enough to improve future work.

Read references/output-format.md when the user wants a structured output template, a prompt-ready context block, or a reusable memory profile format.

Read references/example-prompts.md when the user needs prompt examples, variation ideas, or help choosing the right invocation pattern.

Quick Start

If the user does not specify a format, default to this flow:

  1. extract candidate memories from the source material
  2. keep only durable and evidence-backed items
  3. rewrite them as future-facing rules
  4. return:
    • stable preferences
    • working rules
    • anti-patterns
    • one short reusable context block

If the user already has a memory document, switch into review mode instead of rebuilding everything from scratch.

When To Use

Use this skill when the user asks to:

  • capture recurring preferences or habits
  • preserve successful working patterns
  • record constraints, defaults, or anti-patterns
  • turn task outcomes into future-facing rules
  • clean up or refine an existing memory/profile document
  • produce a compact context block for reuse in future prompts

Do not use this skill for:

  • one-off conversational summaries
  • temporary task state that will expire quickly
  • guesses about user preferences that are not supported by evidence
  • hidden or background memory injection into runtime code paths

Output Selection

Choose the narrowest output that matches the user's goal:

  • memory profile
    • use when the user wants a compact long-term preference document
  • cleaned memory list
    • use when the user already has notes and wants to remove weak items
  • prompt-ready context block
    • use when the user wants a short block to reuse in future prompts
  • review and rewrite report
    • use when the user wants to know what should be kept, rewritten, or removed

Read references/output-format.md before producing any structured output.

Core Rule

Only preserve information that looks durable.

Good candidates:

  • stable preferences
  • repeated defaults
  • persistent constraints
  • explicit dislikes
  • reusable procedures
  • recurring failure-avoidance rules

Weak candidates:

  • one-off requests
  • temporary deadlines
  • transient debugging state
  • personal guesses not explicitly supported by the source material

When a memory candidate is uncertain, mark it as tentative or exclude it.

Evidence Threshold

Prefer memories that are supported by one of these:

  • an explicit user statement
  • a repeated pattern across multiple examples
  • a successful workflow that clearly generalizes
  • a durable constraint that is unlikely to change soon

Prefer to exclude items that are supported only by:

Metadata

Author@danxbuidl
Stars3376
Views1
Updated2026-03-24
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-danxbuidl-danxbuidl-memory-distiller": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.