← 返回 Skills 市场

Auto Memory Curation

Name: Auto Memory Curation
Author: init-v

作者 init-v · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

339

总下载

当前安装

版本数

在 OpenClaw 中安装

/install auto-memory-curation

功能描述

Automatically analyzes messages for important information and stores it in the right memory files. Runs silently on every message. Filters noise, captures me...

使用说明 (SKILL.md)

Auto Memory Curation Skill

Overview

Silently analyze every message for important information and store it appropriately. Reduces manual memory management while building rich context over time.

How It Works

Trigger

Runs on every message (silently)
No user activation needed

Analysis Pipeline

Step 1: Filter Noise Skip these message types:

Greetings (hi, hello, hey)
Thanks/thanking
Acknowledgments (ok, sure, yes, yeah)
Questions without context
Single word responses
Bot commands

Step 2: Categorize For non-noise messages, categorize:

Category	What to look for	Store in
Fact	New info about user, projects, preferences	MEMORY.md
Decision	Choices made, conclusions reached	memory/YYYY-MM-DD.md
Preference	Likes, dislikes, style preferences	USER.md
Idea	Random thoughts, inspiration, concepts	memory/topics/ideas.md
Learning	Lessons, insights, discoveries	memory/topics/lessons.md
Project	Project updates, progress, blockers	memory/projects/
Goal	Goals, targets, milestones	memory/topics/goals.md
Error	Mistakes, corrections to avoid	memory/topics/anti-patterns.md
Commitment	Promises I make, tasks to do	tasks.md

Step 3: Extract & Store

Extract the key information
Add timestamp reference
Store in appropriate file
Use append mode (never overwrite)

Guidelines

What to Capture

New facts about Vini (name, preferences, goals)
Project updates or decisions
Ideas for future projects
Learning insights
Corrections (what doesn't work)
Commitments I make

What to SKIP

Passwords, secrets, API keys
Trivial acknowledgments
Basic confirmations
Questions I'm asking
Technical errors that are fixed

Quality Rules

Be selective - Don't store everything
Be concise - One sentence per memory
Be contextual - Include enough info to understand later
Be accurate - Don't paraphrase incorrectly
Never duplicate - Check if already stored

Format

## [Category] - YYYY-MM-DD

- **[What]:** [Brief description]
  *Context:* [Why it matters or relevant message]

Examples

User says:

"I prefer concise messages, no filler words"

Stored in USER.md:

Preference - 2026-03-06

Communication: Prefers concise messages, no filler words

User says:

"Let's build a landing page for the consultancy inspired by Nexus AI"

Stored in memory/2026-03-06.md:

Decision - 2026-03-06

Consultancy: Will use Nexus AI style for landing page

User says:

"I realized I work better with visual examples first, then theory"

Stored in MEMORY.md:

Learning - 2026-03-06

Learning Style: Visual examples first, theory after

Testing

Periodically review stored memories to calibrate:

Am I capturing too much noise?
Am I missing important things?
Are categories correct?

Adjust based on quality of accumulated memories.

Override

User can disable or adjust this skill at any time by saying:

"Don't store that"
"Clear recent memories"
"Adjust memory curation"

安全使用建议

This skill generally does what it says (auto-capture and file-based memory curation), but you should be cautious before enabling it: 1) Confirm how and where the skill will store data (exact file paths, access controls, retention policy). 2) Prefer opt-in or per-session modes rather than automatic silent capture on every message — silent per-message recording can easily collect secrets or private details. 3) Test on non-sensitive conversations first and periodically audit stored memories for accidental sensitive content. 4) Ask the author to clarify the mismatch between the SKILL.md claim that it 'runs on every message (silently)' and the registry not setting always:true, and to add stricter, machine-checkable rules for skipping secrets. If you cannot verify those points, treat the skill as a privacy risk and avoid enabling it for conversations that may include credentials, personal data, or confidential project details.

功能分析

Type: OpenClaw Skill Name: auto-memory-curation Version: 1.0.0 The skill bundle contains instructions for an AI agent to perform automated memory curation by extracting facts, preferences, and decisions from conversations and storing them in local markdown files. The instructions in SKILL.md include explicit safety guidelines to skip passwords and secrets, and there is no evidence of malicious code, data exfiltration, or unauthorized system access.

能力评估

ℹ Purpose & Capability

Name/description align with the runtime instructions: the SKILL.md explicitly describes filtering messages, categorizing content, extracting key facts, and appending them to memory files (MEMORY.md, USER.md, memory/YYYY-MM-DD.md, memory/topics/*, tasks.md). This capability set is coherent for an auto-curation skill. Minor inconsistency: the skill text expects to 'run on every message (silently)', but the registry metadata does not set always:true — instead it relies on normal model invocation; this is a behavioral mismatch to confirm with the author.

⚠ Instruction Scope

Instructions direct the agent to analyze every incoming message and append content to local memory files. Although the doc lists things to skip (passwords, secrets, trivial acknowledgments), the rules are high-level and rely on correct detection — there is real risk the agent will capture sensitive information users accidentally share. The instructions also give wide discretion about what constitutes 'important' (e.g., 'New facts about Vini'), which can lead to over-collection. The skill assumes write access to agent memory/filesystem paths (memory/, tasks.md) without declaring those paths in metadata.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files. This minimizes supply-chain risk because nothing is downloaded or executed from external URLs.

ℹ Credentials

No environment variables, binaries, or external credentials are requested — appropriate for a purely local curation skill. However, SKILL.md references specific file paths (MEMORY.md, memory/..., tasks.md) and assumes the ability to append to them; the metadata does not state or restrict which storage/memory namespaces will be used. That gap should be clarified so users know where data will be saved and what other agent storage it touches.

⚠ Persistence & Privilege

The README asserts the skill 'Runs on every message (silently)', implying continuous autonomous invocation and persistent recording of user content. Registry flags do not set always:true (so it is not force-included), but disable-model-invocation is false allowing autonomous invocation — combined with the skill's stated behavior this yields a high privacy surface. This persistent capture capability, if enabled, could accumulate sensitive data over time and should be explicitly controlled (opt-in, rate-limited, review prompts).

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install auto-memory-curation
安装完成后，直接呼叫该 Skill 的名称或使用 /auto-memory-curation 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of the auto-memory-curation skill. - Silently analyzes all incoming messages to extract and categorize important information. - Automatically stores key facts, decisions, ideas, preferences, learnings, and more in appropriate memory files. - Filters out greetings, trivial responses, and noise for high-quality memory curation. - Designed for passive and accurate memory building without manual intervention.

元数据

Slug auto-memory-curation

版本 1.0.0

许可证 —

累计安装 2

当前安装数 1

历史版本数 1

常见问题