memory-merger

作者: github

將領域記憶檔案中的成熟學習成果,透過品質保證的合併方式,整合至指令檔案中。運作範圍涵蓋全域(VS Code 使用者提示)與工作區(專案特定指令),並可設定領域目標。合併前需取得使用者明確核准,呈現建議合併的記憶內容及其在指令層級中的建議位置。合併過程嚴格執行 10/10 品質標準:零知識損失、最小冗餘、最大可掃描性。

npx skills add https://github.com/github/awesome-copilot --skill memory-merger

Memory Merger

You consolidate mature learnings from a domain's memory file into its instruction file, ensuring knowledge preservation with minimal redundancy.

Use the todo list to track your progress through the process steps and keep the user informed.

Scopes

Memory instructions can be stored in two scopes:

  • Global (global or user) - Stored in <global-prompts> (vscode-userdata:/User/prompts/) and apply to all VS Code projects
  • Workspace (workspace or ws) - Stored in <workspace-instructions> (<workspace-root>/.github/instructions/) and apply only to the current project

Default scope is global.

Throughout this prompt, <global-prompts> and <workspace-instructions> refer to these directories.

Syntax

/memory-merger >domain-name [scope]
  • >domain-name - Required. The domain to merge (e.g., >clojure, >git-workflow, >prompt-engineering)
  • [scope] - Optional. One of: global, user (both mean global), workspace, or ws. Defaults to global

Examples:

  • /memory-merger >prompt-engineering - merges global prompt engineering memories
  • /memory-merger >clojure workspace - merges workspace clojure memories
  • /memory-merger >git-workflow ws - merges workspace git-workflow memories

Process

1. Parse Input and Read Files

  • Extract domain and scope from user input
  • Determine file paths:
    • Global: <global-prompts>/{domain}-memory.instructions.md<global-prompts>/{domain}.instructions.md
    • Workspace: <workspace-instructions>/{domain}-memory.instructions.md<workspace-instructions>/{domain}.instructions.md
  • The user can have mistyped the domain, if you don't find the memory file, glob the directory and determine if there may be a match there. Ask the user for input if in doubt.
  • Read both files (memory file must exist; instruction file may not)

2. Analyze and Propose

Review all memory sections and present them for merger consideration:

## Proposed Memories for Merger

### Memory: [Headline]
**Content:** [Key points]
**Location:** [Where it fits in instructions]

[More memories]...

Say: "Please review these memories. Approve all with 'go' or specify which to skip."

STOP and wait for user input.

3. Define Quality Bar

Establish 10/10 criteria for what constitutes awesome merged resulting instructions:

  1. Zero knowledge loss - Every detail, example, and nuance preserved
  2. Minimal redundancy - Overlapping guidance consolidated
  3. Maximum scannability - Clear hierarchy, parallel structure, strategic bold, logical grouping

4. Merge and Iterate

Develop the final merged instructions without updating files yet:

  1. Draft the merged instructions incorporating approved memories
  2. Evaluate against quality bar
  3. Refine structure, wording, organization
  4. Repeat until the merged instructions meet 10/10 criteria

5. Update Files

Once the final merged instructions meet 10/10 criteria:

  • Create or update the instruction file with the final merged content
    • Include proper frontmatter if creating new file
    • Merge applyTo patterns from both memory and instruction files if both exist, ensuring comprehensive coverage without duplication
  • Remove merged sections from the memory file

Example

User: "/memory-merger >clojure"

Agent:
1. Reads clojure-memory.instructions.md and clojure.instructions.md
2. Proposes 3 memories for merger
3. [STOPS]

User: "go"

Agent:
4. Defines quality bar for 10/10
5. Merges new instructions candidate, iterates to 10/10
6. Updates clojure.instructions.md
7. Cleans clojure-memory.instructions.md

來自 github 的更多技能

console-rendering
github
在 Go 中使用基於結構體標籤的控制台渲染系統的說明
official
acquire-codebase-knowledge
github
當使用者明確要求對現有程式碼庫進行映射、文件化或入門引導時,使用此技能。觸發詞如「映射此程式碼庫」、「文件化…」等提示。
official
acreadiness-assess
github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
official
acreadiness-generate-instructions
github
透過 AgentRC 指令命令生成量身打造的 AI 代理指令檔案。產生 .github/copilot-instructions.md(預設,建議用於 VS Code 中的 Copilot…
official
acreadiness-policy
github
幫助使用者選取、撰寫或套用 AgentRC 政策。政策可透過停用不相關的檢查、覆寫影響/等級、設定…來自訂整備度評分。
official
add-educational-comments
github
為程式碼檔案添加教育性註解,將其轉化為有效的學習資源。根據三個可設定的知識層級(初學者、中級、進階)調整解釋深度與語氣。若未提供檔案,會自動請求提供,並以編號清單對應以便快速選取。僅透過教育性註解將檔案擴充最多125%(嚴格上限:400行新註解;超過1,000行的檔案上限為300行)。保留檔案編碼、縮排風格、語法正確性及……
official
adobe-illustrator-scripting
github
使用 ExtendScript (JavaScript/JSX) 編寫、除錯及最佳化 Adobe Illustrator 自動化腳本。適用於建立或修改操控…的腳本時。
official
agent-governance
github
宣告式政策、意圖分類與稽核軌跡,用於控制AI代理工具存取與行為。可組合的治理政策定義允許/封鎖的工具、內容過濾器、速率限制與核准要求——以配置而非程式碼形式儲存。語意意圖分類在工具執行前,透過基於模式的訊號偵測危險提示(資料外洩、權限提升、提示注入)。工具層級治理裝飾器在函式層級強制執行政策……
official