memory-updater
Skill3 starsChanged 9 months agoApache-2.0View on GitHub
Update and maintain Memory Bank files (activeContext, progress, decisionLog). Triggers: MB, memory, 記憶, 進度, 更新記憶, update memory, 記錄進度, 更新上下文, sync, 同步, 記下來, note, 筆記, context, 脈絡, 追蹤, track, 狀態, status.
4 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- u9401066/zotero-keeperedited, first seen Nov 8, 2026
- u9401066/pubmed-search-mcpedited, first seen Oct 20, 2026
- u9401066/asset-aware-mcpedited, first seen May 6, 2026
- u9401066/nsforge-mcpedited, first seen Jan 4, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- u9401066/pubmed-search-mcp★ 2832% same
- u9401066/zotero-keeper★ 732% same
- u9401066/nsforge-mcp★ 432% same
- u9401066/asset-aware-mcp★ 032% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- bug-fixSkill
- changelog-updaterSkill
- code-auditSkill
- code-refactorSkill
- code-reviewerSkill
- code-review-workflowSkill
- ddd-architectSkill
- feature-developmentSkill
- git-doc-updaterSkill
- git-precommitSkill
- memory-checkpointSkill
- project-initSkill
- readme-i18nSkill
- readme-updaterSkill
- releaseSkill
- roadmap-updaterSkill
- security-reviewerSkill
- skill-generatorSkill
- skill-health-checkSkill
- test-generatorSkill
The file
Files
Memory Bank 更新技能
描述
維護和更新專案的 Memory Bank 記憶系統,確保專案狀態在對話間持久化。
觸發條件
- 「更新 memory bank」「MB」「記錄進度」
- 「更新上下文」「sync」「同步」
- 工作階段結束時
- 完成重要任務後
📁 Memory Bank 檔案結構
memory-bank/
├── activeContext.md # 當前工作焦點(最常更新)
├── progress.md # 進度追蹤 Done/Doing/Next
├── decisionLog.md # 重要決策記錄
├── architect.md # 架構文檔
├── productContext.md # 專案上下文
├── projectBrief.md # 專案簡介
└── systemPatterns.md # 系統模式🔧 操作步驟
Step 1: 讀取現有內容
使用 read_file 工具讀取要更新的檔案:
read_file("memory-bank/activeContext.md")
read_file("memory-bank/progress.md")Step 2: 判斷更新類型
| 情況 | 更新檔案 | 更新方式 |
| 開始新任務 | activeContext.md, progress.md | 新增 Doing |
| 完成任務 | progress.md | Doing → Done |
| 做出決策 | decisionLog.md | 新增條目 |
| 架構變更 | architect.md | 更新相關區塊 |
Step 3: 執行更新
使用 replace_string_in_file 進行精確更新(推薦):
replace_string_in_file(
filePath="memory-bank/progress.md",
oldString="## Doing\n\n- [ ] 任務 A",
newString="## Doing\n\n- [ ] 任務 A\n- [ ] 新任務 B"
)或使用 write_file 完整覆寫(適合大幅修改)。
📝 檔案格式規範
activeContext.md
# Active Context
> Last updated: 2026-01-15
## 🎯 當前焦點
[一句話描述正在處理的主要任務]
## 📁 相關檔案
- `path/to/file1.py` - [用途說明]
- `path/to/file2.ts` - [用途說明]
## ⚠️ 待解決問題
- [ ] 問題 1
- [ ] 問題 2
## 💡 備註
[其他需要記住的事項]progress.md
# Progress
## Done ✅
- [x] 已完成任務 1 (2026-01-15)
- [x] 已完成任務 2 (2026-01-14)
## Doing 🚧
- [ ] 進行中任務 1
- [ ] 進行中任務 2
## Next 📋
- [ ] 計劃任務 1
- [ ] 計劃任務 2decisionLog.md
# Decision Log
## 2026-01-15
### 決策:選擇 React 作為前端框架
- **背景**:需要選擇前端框架
- **選項**:React, Vue, Svelte
- **決定**:React
- **原因**:團隊熟悉度高,生態系完整
---
## 2026-01-14
### 決策:...⚡ 更新原則
1. 增量更新
✅ 正確:只修改相關區塊
❌ 錯誤:每次都覆寫整個檔案2. 保持簡潔
✅ 正確:「完成用戶認證模組」
❌ 錯誤:「今天我們完成了用戶認證模組的開發工作,包括...」3. 時間標記
✅ 正確:- [x] 完成功能 A (2026-01-15)
❌ 錯誤:- [x] 完成功能 A4. 檔案路徑完整
✅ 正確:`src/domain/entities/User.py`
❌ 錯誤:`User.py`🔄 與其他 Skills 整合
| Skill | 整合方式 |
memory-checkpoint | checkpoint 後呼叫 updater 寫入 |
git-precommit | commit 前強制更新 progress.md |
feature-development | 功能完成後更新 Done |
📊 輸出格式
執行完成後回報:
📝 Memory Bank 已更新
更新內容:
- ✅ activeContext.md - 更新當前焦點
- ✅ progress.md - 新增 1 個 Done 項目
- ⏭️ decisionLog.md - 無變更
下次記得:完成重要任務後執行「更新 memory bank」Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

