Wrap Up

codewithmukesh/dotnet-claude-kit/skills/wrap-up

作者 codewithmukesh23300897f4d1無授權條款754 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫2 個月前更新

Owns the session handoff lifecycle: the end-of-session ritual that captures completed work, pending tasks, and learnings into .claude/handoff.md, and the session-start protocol that loads it back. Triggers on: /wrap-up, "wrap up", "done for today", "that's all", "end session", "signing off", "handoff" — and at session start: "start session", "session start", "load handoff", "pick up where we left off", "what were we working on".

AI 產生的概覽

在 session 結束時把已完成工作、待辦事項與經驗寫入交接檔案,並在 session 開始時重新載入。

功能
這個技能定義了一套雙向的 session 延續流程。session 結束時,它會檢視 git 狀態與對話內容,把已完成工作、待辦事項、經驗與脈絡寫入 .claude/handoff.md,並將值得長期保留的經驗歸入 MEMORY.md 和 .claude/instincts.md。session 開始時,它會載入交接檔案、記憶與直覺模式,偵測方案檔,並先提供恢復摘要,再詢問要進行什麼工作。它只包含指示,產出交接文件與恢復摘要。
適用情境
適用於結束一次工作 session、切換專案或達到里程碑時,也適用於開始 session 以接續先前的脈絡。它也適合隱含的結束情境,例如任務完成後的一句謝謝。若只想在 session 中途儲存而不結束,技能會指向另一個檢查點流程。
執行需求
不需要指令稿或套件,只包含指示。它會讀寫專案中的檔案,包括 .claude/handoff.md、MEMORY.md 和 .claude/instincts.md,並使用 git status 與 diff。它涉及方案檔(.slnx/.sln),並提到 Roslyn MCP 工具與 instinct-system 技能。

/wrap-up

What

The session continuity ritual. Sessions are ephemeral; knowledge is permanent. Wrap-up bridges sessions in both directions:

  • Session END — capture exactly three things: what was DONE, what is PENDING, and what was LEARNED. Write them to .claude/handoff.md and flow durable learnings into MEMORY.md.
  • Session START — load the handoff, memory, and instincts, then present a resume summary so no session starts blind.

When

  • End of a working session — "done for today", "that's all", "signing off"
  • Before switching projects or after a major milestone
  • Implicit endings — "thanks" after completed tasks, "good enough for now": offer the handoff, don't just say goodbye
  • Start of a session — "start session", "load handoff", "what were we working on"
  • For a mid-session save without ending, use /checkpoint instead

How

Session End

  1. Review the session — From git status/diff and the conversation: files touched, tasks completed vs unfinished, decisions made and why, user corrections observed.
  2. Check uncommitted changes — If any exist, offer to commit before wrapping.
  3. Write the handoff — .claude/handoff.md, using the format below. Single file, always overwritten — only the current state matters. If the existing handoff has pending tasks from someone else, ask before overwriting: merge, overwrite, or skip.
  4. Extract learnings — Corrections and discoveries worth keeping go to MEMORY.md (via instinct-system); emerging patterns update .claude/instincts.md (via instinct-system). The handoff's Learned section is the trigger, not the destination — handoffs are ephemeral.
  5. Confirm — Summarize the handoff and learnings captured for the user.

Handoff File Format (.claude/handoff.md)

Write it for a stranger with zero context — file paths, rationale, specific next steps. "Continue the refactor" is useless; "Refactor src/Orders/CreateOrder.cs to the Result pattern — see Catalog for the established pattern" is actionable.

markdown
# Session Handoff
> Generated: 2026-06-12 | Branch: feature/order-validation
## Completed- [x] Added FluentValidation to CreateOrder (src/Orders/Features/CreateOrder.cs:15-35)- [x] Fixed N+1 in GetOrderDetails (src/Orders/Features/GetOrderDetails.cs:28)
## Pending- [ ] Add validation to UpdateOrder (src/Orders/Features/UpdateOrder.cs)  - Reference: CreateOrder validator for the established pattern- [ ] Full test run — 2 pre-existing Catalog failures, not from today
## Learned- FluentValidation validators must be registered in the module's DI setup- Test fixture seeds 1 item per order, which hides N+1 queries
## Context- Branch: feature/order-validation | Last commit: "Add CreateOrder validation"- Uncommitted changes: no | Solution: src/MyApp.slnx

When multiple developers share the project, add a ## Decisions Made table (Decision | Choice | Rationale) and ## Open Questions.

Learning Extraction Checklist

  1. Did the user correct anything? → MEMORY.md via instinct-system
  2. Did we discover something non-obvious? → Learned section
  3. Did we decide something with rationale? → document the "why"
  4. Did a tool/approach fail? → note it so the next session doesn't retry it

Good learning: "EF compiled queries don't work with Include()". Bad learning: "Worked on Orders module" (vague) or "Used TimeProvider" (already a rule).

Session Start

  1. Load context — Read .claude/handoff.md (pending work), MEMORY.md (permanent rules), .claude/instincts.md (patterns at 0.7+ confidence). Missing files are fine: note it and start clean — never block on them.
  2. Detect the solution — Find .slnx/.sln (current dir, then parents, then children) so Roslyn MCP tools work from the first prompt.
  3. Present a resume summary — Last session's work, pending tasks, active rules/instincts count, detected solution. Then ask what to work on — never auto-start pending work.

Example

User: /wrap-up
Claude: Wrapping up session...
## Session Summary- Implemented OrderService with validation pipeline- Fixed N+1 query in GetOrdersByCustomer
## Pending- [ ] Add retry logic to payment gateway calls (OrderService.cs:42)
## Learnings Captured- User prefers explicit mapping over AutoMapper → MEMORY.md
Written to .claude/handoff.md. See you next session.

Related

  • /checkpoint — Mid-session save (commit + brief note) without ending the session
  • instinct-system — Routes session learnings: patterns become instincts, user corrections become permanent MEMORY.md rules

來源與署名

來源:codewithmukesh/dotnet-claude-kit位於skills/wrap-up提交2330089

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

更多來自 codewithmukesh/dotnet-claude-kit 的技能

Workflow Mastery

codewithmukesh

Claude Code workflow mastery for .NET developers. Covers parallel execution with git worktrees, plan mode strategy, verification loops, auto-formatting hooks, permission setup for dotnet CLI, prompting techniques, subagent patterns, and context discipline — token budget management, MCP-first navigation, lazy loading, and subagent isolation — all adapted for the .NET ecosystem. Load this skill when setting up Claude Code for a .NET project, optimizing workflows, running parallel sessions, when context is running low or sessions feel sluggish, when exploring a large codebase efficiently, or when the user mentions "productivity", "workflow", "parallel", "worktree", "plan mode", "permissions", "hooks", "10x", "setup Claude Code", "speed up development", "context", "tokens", "budget", "running out of context", "too many files", or "large codebase". Inspired by tips from Boris Cherny (creator of Claude Code) and the Anthropic team.

待分類7542 個月前更新

Vertical Slice

codewithmukesh

指導 .NET 開發者以垂直切片架構組織應用程式,涵蓋功能資料夾、端點分組與處理常式模式。

Software Development7542 個月前更新

Testing

codewithmukesh

Testing strategy for .NET 10 applications. Covers xUnit v3, WebApplicationFactory for integration tests, Testcontainers for real database testing, Verify for snapshot testing, and the AAA pattern. Load this skill when writing tests, setting up test infrastructure, reviewing test coverage, or when the user mentions "test", "xUnit", "WebApplicationFactory", "Testcontainers", "integration test", "unit test", "bUnit", "snapshot test", "Verify", "test coverage", "AAA pattern", "WireMock", or "FakeTimeProvider".

待分類7542 個月前更新

Tdd

codewithmukesh

Guided test-driven development workflow for .NET 10 using xUnit v3, WebApplicationFactory, Testcontainers, and Verify snapshots. Follows the strict red-green-refactor cycle. Use when: "TDD", "test-driven", "let's TDD this", "red green refactor", "write the test first", or when building a feature with clear acceptance criteria.

待分類7542 個月前更新

Spec

codewithmukesh

透過結構化提問,把模糊的功能想法轉化為雙方確認並持久化的規格文件。

Productivity & Workflow7542 個月前更新

Serilog

codewithmukesh

Structured logging with Serilog for .NET 10 applications. Covers two-stage bootstrap, appsettings configuration, enrichers, sinks, request logging, destructuring, and Serilog.Expressions. Load this skill when setting up Serilog, configuring log sinks, enrichers, or structured logging, or when the user mentions "Serilog", "structured logging", "log enrichment", "Seq", "LogContext", "UseSerilog", "WriteTo", "message template", "Serilog.Expressions", "request logging", "log sink", "rolling file", or "audit log".

待分類7542 個月前更新