elveahuang/one/memory-management

Claude Code and agent skill by elveahuang/one

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Guidelines for safely reading, writing, and updating long-term memory without exposing internal mechanics to the end-user. Trigger this skill whenever managing memories or when the user asks to remember, forget, or verify preferences.

Install

npx vskill@latest install elveahuang/one/memory-management

SKILL.md

Memory Management and User Interaction Skill

Core Principles

  1. Invisible Mechanics (静默原则)
  • Memory operations (MemoryCreate, MemoryInsert, MemoryView, etc.) are internal system processes.
  • STRICTLY PROHIBITED: Mentioning internal files (MEMORY.md, *.md), memory directories, tool names, or internal two-step storage mechanisms in final

user-facing responses.

  1. Natural & Terse Confirmation (自然简短确认)
  • When the user explicitly requests to remember, update, or forget a preference:
  • Perform the necessary tool operations quietly.
  • Respond with a brief, friendly, single-sentence confirmation.
  • Good: "好的,已为你记下这个偏好,后续讨论算法时会直接提供完整实现和复杂度分析。"
  • Bad: "确认:MEMORY.md 索引 ✅,user_algorithm.md 内容 ✅,已成功写入。"
  1. No Psychological Guessing or Meta-Conversations (禁止元对话与动机揣测)
  • Never analyze or question the user's intent, testing behavior, or repeated prompts.
  • Avoid defensive or conversational meta-statements such as:
  • "我注意到你连着问了多次..."
  • "如果你是在测试我..."
  • "我不会因为重复请求就烦躁..."
  • If the user asks repeatedly whether something is remembered, simply verify and give a polite, affirmative confirmation.

Response Flow Example

  • User: "请记住我以后看算法都需要 Java 实现和复杂度分析。"
  • Agent Action:
  1. Internally check MEMORY.md via MemoryView.
  2. Create/update memory via MemoryCreate / MemoryStrReplace.
  3. Update MEMORY.md via MemoryInsert.
  • Agent Final Output:

"好的,已记下你的偏好。后续所有算法解析我都会直接附带完整的 Java 实现与时间/空间复杂度分析。"

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
60
Repository forks
30
7-day trend score
21

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/elveahuang/one/memory-management/badge)](https://verified-skill.com/skills/elveahuang/one/memory-management)

Something wrong with this skill or its page? Tell us.