Agent skill

Memory Evolution

by OPPO-Mente-Lab in OPPO-Mente-Lab/X-OmniClaw

Process pending X-OmniClaw task memories, update MEMORY.md, and rebuild the compact USER-PROFILE.md.

Apache-2.0Auto-check passedProductivity & Automation

Install Memory Evolution

skills CLI
$ npx skills add OPPO-Mente-Lab/X-OmniClaw --skill memory-evolution -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OPPO-Mente-Lab/X-OmniClaw memory-evolution --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OPPO-Mente-Lab/X-OmniClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/src/main/assets/skills/memory-evolution .claude/skills/memory-evolution && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
memory-evolution
GitHub stars
265
Token cost
~539 tokens
SKILL.md length
220 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Process pending X-OmniClaw task memories, update MEMORY.md, and rebuild the compact USER-PROFILE.md.

  • Works in 4 steps: Do not update MEMORY.md directly during… → Keep USER-PROFILE.md compact because it… → Put reusable task lessons and workflows… → …
  • Productivity & Automation work in your project
  • SKILL.md covers Memory Files, Preferred Tool, Recommended Calls and Daily Update Pattern, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Memory Evolution is an agent skill from OPPO-Mente-Lab/X-OmniClaw. Process pending X-OmniClaw task memories, update MEMORY.md, and rebuild the compact USER-PROFILE.md.

Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation. The repository describes itself as: An edge-native Multimodal Android Agent that integrates multimodal perception, memory and action. The licence is Apache-2.0.

When your agent uses it

  • Productivity & Automation work in your project

Example prompts

  • “/memory-evolution”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Do not update MEMORY.md directly during every normal task. Normal tasks should only append pending events.
  2. Keep USER-PROFILE.md compact because it is loaded by default for all tasks.
  3. Put reusable task lessons and workflows in MEMORY.md; put only distilled user habits and key preferences in USER-PROFILE.md.
  4. Do not duplicate gallery details in USER-PROFILE.md; summarize preferences, recent activity, and stable interests from IMAGE-MEMORY.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 8614c93. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Memory Evolution loads about 539 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~539

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OPPO-Mente-Lab/X-OmniClaw at commit 8614c93, republished under its Apache-2.0 licence (© OPPO-Mente-Lab). 220 words, ~539 tokens.

Download SKILL.mdSave it as .claude/skills/memory-evolution/SKILL.md (or your agent's skills folder).
name
memory-evolution
description
Process pending X-OmniClaw task memories, update MEMORY.md, and rebuild the compact USER-PROFILE.md.

Memory Evolution

Use this skill when the user asks to:

  • update global memory
  • evolve task memory
  • summarize task experience into the user profile
  • inspect memory evolution status
  • configure or verify the daily memory update mechanism

This skill maintains task-derived memories. Gallery-derived memories are maintained by gallery-memory.

Memory Files

  • MEMORY.md: task memory from X-OmniClaw usage, including habits, reusable workflows, failures, and project context.
  • memory/IMAGE-MEMORY.md: gallery memory from photos and screenshots.
  • memory/USER-PROFILE.md: compact user profile loaded by default. It should be rebuilt from both MEMORY.md and IMAGE-MEMORY.md.

Preferred Tool

memory_evolution

Use memory_evolution as the direct tool for this workflow.

Supported actions:

  • run: process pending task memory events, update MEMORY.md, and rebuild memory/USER-PROFILE.md
  • status: inspect the latest evolution run status and pending event count
Run evolution
json
{
  "action": "run"
}
Check status
json
{
  "action": "status"
}

Daily Update Pattern

The app owns a managed scheduled task named 全局记忆进化.

Its instruction should be equivalent to:

使用 memory_evolution 工具执行全局记忆进化:处理待沉淀的 X-OmniClaw 任务记忆,更新 MEMORY.md,并重建 USER-PROFILE.md。

Best Practices

  1. Do not update MEMORY.md directly during every normal task. Normal tasks should only append pending events.
  2. Keep USER-PROFILE.md compact because it is loaded by default for all tasks.
  3. Put reusable task lessons and workflows in MEMORY.md; put only distilled user habits and key preferences in USER-PROFILE.md.
  4. Do not duplicate gallery details in USER-PROFILE.md; summarize preferences, recent activity, and stable interests from IMAGE-MEMORY.md.

© OPPO-Mente-Lab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in app/src/main/assets/skills/memory-evolution of OPPO-Mente-Lab/X-OmniClaw.

Open the folder on GitHubat commit 8614c93

Compare with similar skills

Memory Evolution next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Memory Evolution compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Memory Evolution this skillOPPO-Mente-Lab/X-OmniClaw265—~539Automated safety check: PassApache-2.0
Agent Browserquran/quran.com-frontend-next1.9k42 repos~3.3kAutomated safety check: PassNone
Process Inboxtelegramdesktop/tdesktop33k2 repos~4.5kAutomated safety check: PassGPL-3.0
Perform Tasktelegramdesktop/tdesktop33k2 repos~3kAutomated safety check: PassGPL-3.0
Brave Searchbadlogic/pi-skills2.6k6 repos~592Automated safety check: PassMIT
Continuetelegramdesktop/tdesktop33k2 repos~9.4kAutomated safety check: PassGPL-3.0

Similar skills

  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 42 repos~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Process Inbox

    telegramdesktop/tdesktop

    Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.

    33k GitHub starsUsed in 2 repos~4.5k tokens
    Productivity & AutomationAuto-check passed
  • Perform Task

    telegramdesktop/tdesktop

    Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results.

    33k GitHub starsUsed in 2 repos~3k tokens
    Productivity & AutomationAuto-check passed
  • Brave Search

    badlogic/pi-skills

    Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.

    2.6k GitHub starsUsed in 6 repos~592 tokens
    Productivity & AutomationAuto-check passed
  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-check passed
  • Feishu Doc

    openclaw/openclaw

    Feishu document read/write workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~516 tokensUpdated today
    Productivity & AutomationAuto-check passed

More from OPPO-Mente-Lab/X-OmniClaw

All 14 skills in this repo
  • Feishu Bitable

    OPPO-Mente-Lab/X-OmniClaw

    Feishu multi-dimensional table (Bitable) operations. An agent skill from OPPO-Mente-Lab/X-OmniClaw.

    265 GitHub stars~631 tokensUpdated 4 mo ago
    Auto-check passed
  • Feishu Chat

    OPPO-Mente-Lab/X-OmniClaw

    Feishu chat operations. An agent skill from OPPO-Mente-Lab/X-OmniClaw.

    265 GitHub stars~592 tokensUpdated 4 mo ago
    Auto-check passed
  • Feishu Task

    OPPO-Mente-Lab/X-OmniClaw

    Feishu task management operations. An agent skill from OPPO-Mente-Lab/X-OmniClaw.

    265 GitHub stars~482 tokensUpdated 4 mo ago
    Auto-check passed
  • Feishu Urgent

    OPPO-Mente-Lab/X-OmniClaw

    Feishu urgent notification tool. An agent skill from OPPO-Mente-Lab/X-OmniClaw.

    265 GitHub stars~601 tokensUpdated 4 mo ago
    Auto-check passed
  • App Search

    OPPO-Mente-Lab/X-OmniClaw

    主流APP搜索。当用户想要在拼多多、美团、高德地图、抖音、快手、小红书、哔哩哔哩、知乎、百度、OPPO音乐、OPPO软件商店等APP中搜索时激活。覆盖电商购物、生活服务、短视频内容、知识搜索、音乐搜索、应用商店搜索等场景。

    265 GitHub stars~4.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Capcut Theme Video

    OPPO-Mente-Lab/X-OmniClaw

    CapCut (剪映) one-tap video creation on Android. An agent skill from OPPO-Mente-Lab/X-OmniClaw.

    265 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Memory Evolution

What does Memory Evolution do?

Process pending X-OmniClaw task memories, update MEMORY.md, and rebuild the compact USER-PROFILE.md. Memory Evolution is an agent skill from OPPO-Mente-Lab/X-OmniClaw.md.

When should I use Memory Evolution?

Memory Evolution fits situations like: productivity & Automation work in your project.

How do I install Memory Evolution in Claude Code?

Run `npx skills add OPPO-Mente-Lab/X-OmniClaw --skill memory-evolution -a claude-code`. Or copy the skill folder (app/src/main/assets/skills/memory-evolution in OPPO-Mente-Lab/X-OmniClaw) into .claude/skills/memory-evolution in your project. Claude Code loads it when a task matches its description.

How do I install Memory Evolution in Codex?

Run `npx skills add OPPO-Mente-Lab/X-OmniClaw --skill memory-evolution -a codex`. Or copy the skill folder (app/src/main/assets/skills/memory-evolution in OPPO-Mente-Lab/X-OmniClaw) into .agents/skills/memory-evolution in your project. Codex loads it when a task matches its description.

Can I use Memory Evolution in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OPPO-Mente-Lab/X-OmniClaw --skill memory-evolution -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-evolution, .gemini/skills/memory-evolution, .github/skills/memory-evolution and .opencode/skills/memory-evolution in your project.

What does Memory Evolution need to run?

SKILL.md names no scripts, command-line tools or credentials: Memory Evolution is instructions for the agent only.

Does Memory Evolution access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Memory Evolution safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Memory Evolution use?

Memory Evolution is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Memory Evolution use?

About 539 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Memory Evolution?

Skills that share tags, products or a category with Memory Evolution: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Process Inbox (telegramdesktop/tdesktop, 33k stars), Perform Task (telegramdesktop/tdesktop, 33k stars) and Brave Search (badlogic/pi-skills, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Memory Evolution?

OPPO-Mente-Lab (a GitHub organization) maintains it in OPPO-Mente-Lab/X-OmniClaw, which has 265 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on May 22, 2026.

Source: OPPO-Mente-Lab/X-OmniClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.