diff --git a/.claude/commands/memory/compact.md b/.claude/commands/memory/compact.md
deleted file mode 100644
index 2146bbf2..00000000
--- a/.claude/commands/memory/compact.md
+++ /dev/null
@@ -1,383 +0,0 @@
----
-name: compact
-description: Compact current session memory into structured text for session recovery, extracting objective/plan/files/decisions/constraints/state, and save via MCP core_memory tool
-argument-hint: "[optional: session description]"
-allowed-tools: mcp__ccw-tools__core_memory(*), Read(*)
-examples:
- - /memory:compact
- - /memory:compact "completed core-memory module"
----
-
-# Memory Compact Command (/memory:compact)
-
-## 1. Overview
-
-The `memory:compact` command **compresses current session working memory** into structured text optimized for **session recovery**, extracts critical information, and saves it to persistent storage via MCP `core_memory` tool.
-
-**Core Philosophy**:
-- **Session Recovery First**: Capture everything needed to resume work seamlessly
-- **Minimize Re-exploration**: Include file paths, decisions, and state to avoid redundant analysis
-- **Preserve Train of Thought**: Keep notes and hypotheses for complex debugging
-- **Actionable State**: Record last action result and known issues
-
-## 2. Parameters
-
-- `"session description"` (Optional): Session description to supplement objective
- - Example: "completed core-memory module"
- - Example: "debugging JWT refresh - suspected memory leak"
-
-## 3. Structured Output Format
-
-```markdown
-## Session ID
-[WFS-ID if workflow session active, otherwise (none)]
-
-## Project Root
-[Absolute path to project root, e.g., D:\Claude_dms3]
-
-## Objective
-[High-level goal - the "North Star" of this session]
-
-## Execution Plan
-[CRITICAL: Embed the LATEST plan in its COMPLETE and DETAILED form]
-
-### Source: [workflow | todo | user-stated | inferred]
-
-
-Full Execution Plan (Click to expand)
-
-[PRESERVE COMPLETE PLAN VERBATIM - DO NOT SUMMARIZE]
-- ALL phases, tasks, subtasks
-- ALL file paths (absolute)
-- ALL dependencies and prerequisites
-- ALL acceptance criteria
-- ALL status markers ([x] done, [ ] pending)
-- ALL notes and context
-
-Example:
-## Phase 1: Setup
-- [x] Initialize project structure
- - Created D:\Claude_dms3\src\core\index.ts
- - Added dependencies: lodash, zod
-- [ ] Configure TypeScript
- - Update tsconfig.json for strict mode
-
-## Phase 2: Implementation
-- [ ] Implement core API
- - Target: D:\Claude_dms3\src\api\handler.ts
- - Dependencies: Phase 1 complete
- - Acceptance: All tests pass
-
-
-
-## Working Files (Modified)
-[Absolute paths to actively modified files]
-- D:\Claude_dms3\src\file1.ts (role: main implementation)
-- D:\Claude_dms3\tests\file1.test.ts (role: unit tests)
-
-## Reference Files (Read-Only)
-[Absolute paths to context files - NOT modified but essential for understanding]
-- D:\Claude_dms3\.claude\CLAUDE.md (role: project instructions)
-- D:\Claude_dms3\src\types\index.ts (role: type definitions)
-- D:\Claude_dms3\package.json (role: dependencies)
-
-## Last Action
-[Last significant action and its result/status]
-
-## Decisions
-- [Decision]: [Reasoning]
-- [Decision]: [Reasoning]
-
-## Constraints
-- [User-specified limitation or preference]
-
-## Dependencies
-- [Added/changed packages or environment requirements]
-
-## Known Issues
-- [Deferred bug or edge case]
-
-## Changes Made
-- [Completed modification]
-
-## Pending
-- [Next step] or (none)
-
-## Notes
-[Unstructured thoughts, hypotheses, debugging trails]
-```
-
-## 4. Field Definitions
-
-| Field | Purpose | Recovery Value |
-|-------|---------|----------------|
-| **Session ID** | Workflow session identifier (WFS-*) | Links memory to specific stateful task execution |
-| **Project Root** | Absolute path to project directory | Enables correct path resolution in new sessions |
-| **Objective** | Ultimate goal of the session | Prevents losing track of broader feature |
-| **Execution Plan** | Complete plan from any source (verbatim) | Preserves full planning context, avoids re-planning |
-| **Working Files** | Actively modified files (absolute paths) | Immediately identifies where work was happening |
-| **Reference Files** | Read-only context files (absolute paths) | Eliminates re-exploration for critical context |
-| **Last Action** | Final tool output/status | Immediate state awareness (success/failure) |
-| **Decisions** | Architectural choices + reasoning | Prevents re-litigating settled decisions |
-| **Constraints** | User-imposed limitations | Maintains personalized coding style |
-| **Dependencies** | Package/environment changes | Prevents missing dependency errors |
-| **Known Issues** | Deferred bugs/edge cases | Ensures issues aren't forgotten |
-| **Changes Made** | Completed modifications | Clear record of what was done |
-| **Pending** | Next steps | Immediate action items |
-| **Notes** | Hypotheses, debugging trails | Preserves "train of thought" |
-
-## 5. Execution Flow
-
-### Step 1: Analyze Current Session
-
-Extract the following from conversation history:
-
-```javascript
-const sessionAnalysis = {
- sessionId: "", // WFS-* if workflow session active, null otherwise
- projectRoot: "", // Absolute path: D:\Claude_dms3
- objective: "", // High-level goal (1-2 sentences)
- executionPlan: {
- source: "workflow" | "todo" | "user-stated" | "inferred",
- content: "" // Full plan content - ALWAYS preserve COMPLETE and DETAILED form
- },
- workingFiles: [], // {absolutePath, role} - modified files
- referenceFiles: [], // {absolutePath, role} - read-only context files
- lastAction: "", // Last significant action + result
- decisions: [], // {decision, reasoning}
- constraints: [], // User-specified limitations
- dependencies: [], // Added/changed packages
- knownIssues: [], // Deferred bugs
- changesMade: [], // Completed modifications
- pending: [], // Next steps
- notes: "" // Unstructured thoughts
-}
-```
-
-### Step 2: Generate Structured Text
-
-```javascript
-// Helper: Generate execution plan section
-const generateExecutionPlan = (plan) => {
- const sourceLabels = {
- 'workflow': 'workflow (IMPL_PLAN.md)',
- 'todo': 'todo (TodoWrite)',
- 'user-stated': 'user-stated',
- 'inferred': 'inferred'
- };
-
- // CRITICAL: Preserve complete plan content verbatim - DO NOT summarize
- return `### Source: ${sourceLabels[plan.source] || plan.source}
-
-
-Full Execution Plan (Click to expand)
-
-${plan.content}
-
- `;
-};
-
-const structuredText = `## Session ID
-${sessionAnalysis.sessionId || '(none)'}
-
-## Project Root
-${sessionAnalysis.projectRoot}
-
-## Objective
-${sessionAnalysis.objective}
-
-## Execution Plan
-${generateExecutionPlan(sessionAnalysis.executionPlan)}
-
-## Working Files (Modified)
-${sessionAnalysis.workingFiles.map(f => `- ${f.absolutePath} (role: ${f.role})`).join('\n') || '(none)'}
-
-## Reference Files (Read-Only)
-${sessionAnalysis.referenceFiles.map(f => `- ${f.absolutePath} (role: ${f.role})`).join('\n') || '(none)'}
-
-## Last Action
-${sessionAnalysis.lastAction}
-
-## Decisions
-${sessionAnalysis.decisions.map(d => `- ${d.decision}: ${d.reasoning}`).join('\n') || '(none)'}
-
-## Constraints
-${sessionAnalysis.constraints.map(c => `- ${c}`).join('\n') || '(none)'}
-
-## Dependencies
-${sessionAnalysis.dependencies.map(d => `- ${d}`).join('\n') || '(none)'}
-
-## Known Issues
-${sessionAnalysis.knownIssues.map(i => `- ${i}`).join('\n') || '(none)'}
-
-## Changes Made
-${sessionAnalysis.changesMade.map(c => `- ${c}`).join('\n') || '(none)'}
-
-## Pending
-${sessionAnalysis.pending.length > 0
- ? sessionAnalysis.pending.map(p => `- ${p}`).join('\n')
- : '(none)'}
-
-## Notes
-${sessionAnalysis.notes || '(none)'}`
-```
-
-### Step 3: Import to Core Memory via MCP
-
-Use the MCP `core_memory` tool to save the structured text:
-
-```javascript
-mcp__ccw-tools__core_memory({
- operation: "import",
- text: structuredText
-})
-```
-
-Or via CLI (pipe structured text to import):
-
-```bash
-# Write structured text to temp file, then import
-echo "$structuredText" | ccw core-memory import
-
-# Or from a file
-ccw core-memory import --file /path/to/session-memory.md
-```
-
-**Response Format**:
-```json
-{
- "operation": "import",
- "id": "CMEM-YYYYMMDD-HHMMSS",
- "message": "Created memory: CMEM-YYYYMMDD-HHMMSS"
-}
-```
-
-### Step 4: Report Recovery ID
-
-After successful import, **clearly display the Recovery ID** to the user:
-
-```
-╔════════════════════════════════════════════════════════════════════════════╗
-║ ✓ Session Memory Saved ║
-║ ║
-║ Recovery ID: CMEM-YYYYMMDD-HHMMSS ║
-║ ║
-║ To restore: "Please import memory " ║
-║ (MCP: core_memory export | CLI: ccw core-memory export --id ) ║
-╚════════════════════════════════════════════════════════════════════════════╝
-```
-
-## 6. Quality Checklist
-
-Before generating:
-- [ ] Session ID captured if workflow session active (WFS-*)
-- [ ] Project Root is absolute path (e.g., D:\Claude_dms3)
-- [ ] Objective clearly states the "North Star" goal
-- [ ] Execution Plan: COMPLETE plan preserved VERBATIM (no summarization)
-- [ ] Plan Source: Clearly identified (workflow | todo | user-stated | inferred)
-- [ ] Plan Details: ALL phases, tasks, file paths, dependencies, status markers included
-- [ ] All file paths are ABSOLUTE (not relative)
-- [ ] Working Files: 3-8 modified files with roles
-- [ ] Reference Files: Key context files (CLAUDE.md, types, configs)
-- [ ] Last Action captures final state (success/failure)
-- [ ] Decisions include reasoning, not just choices
-- [ ] Known Issues separates deferred from forgotten bugs
-- [ ] Notes preserve debugging hypotheses if any
-
-## 7. Path Resolution Rules
-
-### Project Root Detection
-1. Check current working directory from environment
-2. Look for project markers: `.git/`, `package.json`, `.claude/`
-3. Use the topmost directory containing these markers
-
-### Absolute Path Conversion
-```javascript
-// Convert relative to absolute
-const toAbsolutePath = (relativePath, projectRoot) => {
- if (path.isAbsolute(relativePath)) return relativePath;
- return path.join(projectRoot, relativePath);
-};
-
-// Example: "src/api/auth.ts" → "D:\Claude_dms3\src\api\auth.ts"
-```
-
-### Reference File Categories
-| Category | Examples | Priority |
-|----------|----------|----------|
-| Project Config | `.claude/CLAUDE.md`, `package.json`, `tsconfig.json` | High |
-| Type Definitions | `src/types/*.ts`, `*.d.ts` | High |
-| Related Modules | Parent/sibling modules with shared interfaces | Medium |
-| Test Files | Corresponding test files for modified code | Medium |
-| Documentation | `README.md`, `ARCHITECTURE.md` | Low |
-
-## 8. Plan Detection (Priority Order)
-
-### Priority 1: Workflow Session (IMPL_PLAN.md)
-```javascript
-// Check for active workflow session
-const manifest = await mcp__ccw-tools__session_manager({
- operation: "list",
- location: "active"
-});
-
-if (manifest.sessions?.length > 0) {
- const session = manifest.sessions[0];
- const plan = await mcp__ccw-tools__session_manager({
- operation: "read",
- session_id: session.id,
- content_type: "plan"
- });
- sessionAnalysis.sessionId = session.id;
- sessionAnalysis.executionPlan.source = "workflow";
- sessionAnalysis.executionPlan.content = plan.content;
-}
-```
-
-### Priority 2: TodoWrite (Current Session Todos)
-```javascript
-// Extract from conversation - look for TodoWrite tool calls
-// Preserve COMPLETE todo list with all details
-const todos = extractTodosFromConversation();
-if (todos.length > 0) {
- sessionAnalysis.executionPlan.source = "todo";
- // Format todos with full context - preserve status markers
- sessionAnalysis.executionPlan.content = todos.map(t =>
- `- [${t.status === 'completed' ? 'x' : t.status === 'in_progress' ? '>' : ' '}] ${t.content}`
- ).join('\n');
-}
-```
-
-### Priority 3: User-Stated Plan
-```javascript
-// Look for explicit plan statements in user messages:
-// - "Here's my plan: 1. ... 2. ... 3. ..."
-// - "I want to: first..., then..., finally..."
-// - Numbered or bulleted lists describing steps
-const userPlan = extractUserStatedPlan();
-if (userPlan) {
- sessionAnalysis.executionPlan.source = "user-stated";
- sessionAnalysis.executionPlan.content = userPlan;
-}
-```
-
-### Priority 4: Inferred Plan
-```javascript
-// If no explicit plan, infer from:
-// - Task description and breakdown discussion
-// - Sequence of actions taken
-// - Outstanding work mentioned
-const inferredPlan = inferPlanFromDiscussion();
-if (inferredPlan) {
- sessionAnalysis.executionPlan.source = "inferred";
- sessionAnalysis.executionPlan.content = inferredPlan;
-}
-```
-
-## 9. Notes
-
-- **Timing**: Execute at task completion or before context switch
-- **Frequency**: Once per independent task or milestone
-- **Recovery**: New session can immediately continue with full context
-- **Knowledge Graph**: Entity relationships auto-extracted for visualization
-- **Absolute Paths**: Critical for cross-session recovery on different machines
diff --git a/.claude/commands/memory/tips.md b/.claude/commands/memory/tips.md
deleted file mode 100644
index 52082a81..00000000
--- a/.claude/commands/memory/tips.md
+++ /dev/null
@@ -1,332 +0,0 @@
----
-name: tips
-description: Quick note-taking command to capture ideas, snippets, reminders, and insights for later reference
-argument-hint: " [--tag ] [--context ]"
-allowed-tools: mcp__ccw-tools__core_memory(*), Read(*)
-examples:
- - /memory:tips "Remember to use Redis for rate limiting"
- - /memory:tips "Auth pattern: JWT with refresh tokens" --tag architecture,auth
- - /memory:tips "Bug: memory leak in WebSocket handler after 24h" --context websocket-service
- - /memory:tips "Performance: lazy loading reduced bundle by 40%" --tag performance
----
-
-# Memory Tips Command (/memory:tips)
-
-## 1. Overview
-
-The `memory:tips` command provides **quick note-taking** for capturing:
-- Quick ideas and insights
-- Code snippets and patterns
-- Reminders and follow-ups
-- Bug notes and debugging hints
-- Performance observations
-- Architecture decisions
-- Library/tool recommendations
-
-**Core Philosophy**:
-- **Speed First**: Minimal friction for capturing thoughts
-- **Searchable**: Tagged for easy retrieval
-- **Context-Aware**: Optional context linking
-- **Lightweight**: No complex session analysis
-
-## 2. Parameters
-
-- `` (Required): The tip/note content to save
-- `--tag ` (Optional): Comma-separated tags for categorization
-- `--context ` (Optional): Related context (file, module, feature)
-
-**Examples**:
-```bash
-/memory:tips "Use Zod for runtime validation - better DX than class-validator"
-/memory:tips "Redis connection pool: max 10, min 2" --tag config,redis
-/memory:tips "Fix needed: race condition in payment processor" --tag bug,payment --context src/payments
-```
-
-## 3. Structured Output Format
-
-```markdown
-## Tip ID
-TIP-YYYYMMDD-HHMMSS
-
-## Timestamp
-YYYY-MM-DD HH:MM:SS
-
-## Project Root
-[Absolute path to project root, e.g., D:\Claude_dms3]
-
-## Content
-[The tip/note content exactly as provided]
-
-## Tags
-[Comma-separated tags, or (none)]
-
-## Context
-[Optional context linking - file, module, or feature reference]
-
-## Session Link
-[WFS-ID if workflow session active, otherwise (none)]
-
-## Auto-Detected Context
-[Files/topics from current conversation if relevant]
-```
-
-## 4. Field Definitions
-
-| Field | Purpose | Example |
-|-------|---------|---------|
-| **Tip ID** | Unique identifier with timestamp | TIP-20260128-143052 |
-| **Timestamp** | When tip was created | 2026-01-28 14:30:52 |
-| **Project Root** | Current project path | D:\Claude_dms3 |
-| **Content** | The actual tip/note | "Use Redis for rate limiting" |
-| **Tags** | Categorization labels | architecture, auth, performance |
-| **Context** | Related code/feature | src/auth/**, payment-module |
-| **Session Link** | Link to workflow session | WFS-auth-20260128 |
-| **Auto-Detected Context** | Files from conversation | src/api/handler.ts |
-
-## 5. Execution Flow
-
-### Step 1: Parse Arguments
-
-```javascript
-const parseTipsCommand = (input) => {
- // Extract note content (everything before flags)
- const contentMatch = input.match(/^"([^"]+)"|^([^\s-]+)/);
- const content = contentMatch ? (contentMatch[1] || contentMatch[2]) : '';
-
- // Extract tags
- const tagsMatch = input.match(/--tag\s+([^\s-]+)/);
- const tags = tagsMatch ? tagsMatch[1].split(',').map(t => t.trim()) : [];
-
- // Extract context
- const contextMatch = input.match(/--context\s+([^\s-]+)/);
- const context = contextMatch ? contextMatch[1] : '';
-
- return { content, tags, context };
-};
-```
-
-### Step 2: Gather Context
-
-```javascript
-const gatherTipContext = async () => {
- // Get project root
- const projectRoot = process.cwd(); // or detect from environment
-
- // Get current session if active
- const manifest = await mcp__ccw-tools__session_manager({
- operation: "list",
- location: "active"
- });
- const sessionId = manifest.sessions?.[0]?.id || null;
-
- // Auto-detect files from recent conversation
- const recentFiles = extractRecentFilesFromConversation(); // Last 5 messages
-
- return {
- projectRoot,
- sessionId,
- autoDetectedContext: recentFiles
- };
-};
-```
-
-### Step 3: Generate Structured Text
-
-```javascript
-const generateTipText = (parsed, context) => {
- const timestamp = new Date().toISOString().replace('T', ' ').slice(0, 19);
- const tipId = `TIP-${new Date().toISOString().slice(0,10).replace(/-/g, '')}-${new Date().toTimeString().slice(0,8).replace(/:/g, '')}`;
-
- return `## Tip ID
-${tipId}
-
-## Timestamp
-${timestamp}
-
-## Project Root
-${context.projectRoot}
-
-## Content
-${parsed.content}
-
-## Tags
-${parsed.tags.length > 0 ? parsed.tags.join(', ') : '(none)'}
-
-## Context
-${parsed.context || '(none)'}
-
-## Session Link
-${context.sessionId || '(none)'}
-
-## Auto-Detected Context
-${context.autoDetectedContext.length > 0
- ? context.autoDetectedContext.map(f => `- ${f}`).join('\n')
- : '(none)'}`;
-};
-```
-
-### Step 4: Save to Core Memory
-
-```javascript
-mcp__ccw-tools__core_memory({
- operation: "import",
- text: structuredText
-})
-```
-
-**Response Format**:
-```json
-{
- "operation": "import",
- "id": "CMEM-YYYYMMDD-HHMMSS",
- "message": "Created memory: CMEM-YYYYMMDD-HHMMSS"
-}
-```
-
-### Step 5: Confirm to User
-
-```
-✓ Tip saved successfully
-
- ID: CMEM-YYYYMMDD-HHMMSS
- Tags: architecture, auth
- Context: src/auth/**
-
- To retrieve: /memory:search "auth patterns"
- Or via MCP: core_memory(operation="search", query="auth")
-```
-
-## 6. Tag Categories (Suggested)
-
-**Technical**:
-- `architecture` - Design decisions and patterns
-- `performance` - Optimization insights
-- `security` - Security considerations
-- `bug` - Bug notes and fixes
-- `config` - Configuration settings
-- `api` - API design patterns
-
-**Development**:
-- `testing` - Test strategies and patterns
-- `debugging` - Debugging techniques
-- `refactoring` - Refactoring notes
-- `documentation` - Doc improvements
-
-**Domain Specific**:
-- `auth` - Authentication/authorization
-- `database` - Database patterns
-- `frontend` - UI/UX patterns
-- `backend` - Backend logic
-- `devops` - Infrastructure and deployment
-
-**Organizational**:
-- `reminder` - Follow-up items
-- `research` - Research findings
-- `idea` - Feature ideas
-- `review` - Code review notes
-
-## 7. Search Integration
-
-Tips can be retrieved using:
-
-```bash
-# Via command (if /memory:search exists)
-/memory:search "rate limiting"
-
-# Via MCP tool
-mcp__ccw-tools__core_memory({
- operation: "search",
- query: "rate limiting",
- source_type: "core_memory",
- top_k: 10
-})
-
-# Via CLI
-ccw core-memory search --query "rate limiting" --top-k 10
-```
-
-## 8. Quality Checklist
-
-Before saving:
-- [ ] Content is clear and actionable
-- [ ] Tags are relevant and consistent
-- [ ] Context provides enough reference
-- [ ] Auto-detected context is accurate
-- [ ] Project root is absolute path
-- [ ] Timestamp is properly formatted
-
-## 9. Best Practices
-
-### Good Tips Examples
-
-✅ **Specific and Actionable**:
-```
-"Use connection pooling for Redis: { max: 10, min: 2, acquireTimeoutMillis: 30000 }"
---tag config,redis
-```
-
-✅ **With Context**:
-```
-"Auth middleware must validate both access and refresh tokens"
---tag security,auth --context src/middleware/auth.ts
-```
-
-✅ **Problem + Solution**:
-```
-"Memory leak fixed by unsubscribing event listeners in componentWillUnmount"
---tag bug,react --context src/components/Chat.tsx
-```
-
-### Poor Tips Examples
-
-❌ **Too Vague**:
-```
-"Fix the bug" --tag bug
-```
-
-❌ **Too Long** (use /memory:compact instead):
-```
-"Here's the complete implementation plan for the entire auth system... [3 paragraphs]"
-```
-
-❌ **No Context**:
-```
-"Remember to update this later"
-```
-
-## 10. Use Cases
-
-### During Development
-```bash
-/memory:tips "JWT secret must be 256-bit minimum" --tag security,auth
-/memory:tips "Use debounce (300ms) for search input" --tag performance,ux
-```
-
-### After Bug Fixes
-```bash
-/memory:tips "Race condition in payment: lock with Redis SETNX" --tag bug,payment
-```
-
-### Code Review Insights
-```bash
-/memory:tips "Prefer early returns over nested ifs" --tag style,readability
-```
-
-### Architecture Decisions
-```bash
-/memory:tips "Chose PostgreSQL over MongoDB for ACID compliance" --tag architecture,database
-```
-
-### Library Recommendations
-```bash
-/memory:tips "Zod > Yup for TypeScript validation - better type inference" --tag library,typescript
-```
-
-## 11. Notes
-
-- **Frequency**: Use liberally - capture all valuable insights
-- **Retrieval**: Search by tags, content, or context
-- **Lifecycle**: Tips persist across sessions
-- **Organization**: Tags enable filtering and categorization
-- **Integration**: Can reference tips in later workflows
-- **Lightweight**: No complex session analysis required
diff --git a/.claude/skills/memory-capture/SKILL.md b/.claude/skills/memory-capture/SKILL.md
new file mode 100644
index 00000000..57a5281c
--- /dev/null
+++ b/.claude/skills/memory-capture/SKILL.md
@@ -0,0 +1,129 @@
+---
+name: memory-capture
+description: Unified memory capture with routing - session compact or quick tips. Triggers on "memory capture", "compact session", "save session", "quick tip", "memory tips", "记录", "压缩会话".
+allowed-tools: mcp__ccw-tools__core_memory(*), Read(*), AskUserQuestion
+---
+
+# Memory Capture Skill
+
+Unified memory capture skill that routes to two execution modes:
+- **Compact**: Compress full session memory into structured text for recovery
+- **Tips**: Quick note-taking for ideas, snippets, and insights
+
+## Architecture Overview
+
+```
+┌─────────────────────────────────────────────────────┐
+│ Memory Capture (Router) │
+│ → Parse input → Detect mode → Route to phase │
+└───────────────┬─────────────────────────────────────┘
+ │
+ ┌───────┴───────┐
+ ↓ ↓
+ ┌───────────┐ ┌───────────┐
+ │ Compact │ │ Tips │
+ │ (Phase1) │ │ (Phase2) │
+ │ Full │ │ Quick │
+ │ Session │ │ Note │
+ └─────┬─────┘ └─────┬─────┘
+ │ │
+ └───────┬───────┘
+ ↓
+ ┌───────────────┐
+ │ core_memory │
+ │ (import) │
+ └───────────────┘
+```
+
+## Execution Flow
+
+### Step 1: Parse Input & Route
+
+Detect execution mode from user input:
+
+**Auto-Route Rules** (priority order):
+
+| Signal | Route | Examples |
+|--------|-------|---------|
+| Keyword: compact, session, 压缩, recovery, 保存会话 | → Compact | "compact current session" |
+| Keyword: tip, note, 记录, 快速 | → Tips | "记录一个想法" |
+| Has `--tag` or `--context` flags | → Tips | `"note content" --tag bug` |
+| Short text (<100 chars) + no session keywords | → Tips | "Remember to use Redis" |
+| Ambiguous or no arguments | → **AskUserQuestion** | `/memory-capture` |
+
+**When ambiguous**, use AskUserQuestion:
+
+```
+Question: "选择记忆捕获模式"
+Options:
+ 1. Compact - 压缩当前完整会话记忆（用于会话恢复）
+ 2. Tips - 快速记录一条笔记/想法/提示
+```
+
+### Step 2: Execute Selected Phase
+
+Based on routing result, read and execute the corresponding phase:
+
+- **Compact mode** → Ref: [phases/01-compact.md](phases/01-compact.md)
+- **Tips mode** → Ref: [phases/02-tips.md](phases/02-tips.md)
+
+**Phase Reference Documents** (read on-demand when phase executes):
+
+| Mode | Document | Purpose |
+|------|----------|---------|
+| Compact | [phases/01-compact.md](phases/01-compact.md) | Full session memory compression and structured export |
+| Tips | [phases/02-tips.md](phases/02-tips.md) | Quick note-taking with tags and context |
+
+### Step 3: Save via core_memory
+
+Both phases converge on the same storage mechanism:
+
+```javascript
+mcp__ccw-tools__core_memory({
+ operation: "import",
+ text: structuredText // Generated by the selected phase
+})
+```
+
+## Core Rules
+
+1. **Single Phase Execution**: Only ONE phase executes per invocation - never both
+2. **Content Faithful**: Phase files contain full execution detail - follow them verbatim
+3. **Absolute Paths**: All file paths in output must be absolute
+4. **No Summarization**: Compact mode preserves complete plan verbatim - never abbreviate
+5. **Speed Priority**: Tips mode should be fast - minimal analysis overhead
+
+## Input Processing
+
+### Compact Mode Input
+- Optional: `"session description"` as supplementary context
+- Example: `/memory-capture compact` or `/memory-capture "completed auth module"`
+
+### Tips Mode Input
+- Required: `` - the tip/note text
+- Optional: `--tag ` for categorization
+- Optional: `--context ` for related code/feature reference
+- Example: `/memory-capture tip "Use Redis for rate limiting" --tag config`
+
+## Data Flow
+
+```
+User Input
+ │
+ ├─ [compact detected] → Read phases/01-compact.md
+ │ → Analyze session → Generate structured text
+ │ → core_memory import → Report Recovery ID
+ │
+ └─ [tips detected] → Read phases/02-tips.md
+ → Parse args → Gather context → Generate tip text
+ → core_memory import → Confirm with ID + tags
+```
+
+## Error Handling
+
+| Error | Action |
+|-------|--------|
+| core_memory import fails | Retry once, then report error with structured text for manual save |
+| No session context (compact) | Warn user, generate with available info |
+| Empty note content (tips) | Ask user to provide content via AskUserQuestion |
+| Ambiguous routing | Default to AskUserQuestion - never guess |
diff --git a/.claude/skills/memory-capture/phases/01-compact.md b/.claude/skills/memory-capture/phases/01-compact.md
new file mode 100644
index 00000000..7862bf40
--- /dev/null
+++ b/.claude/skills/memory-capture/phases/01-compact.md
@@ -0,0 +1,254 @@
+# Phase 1: Compact - Session Memory Compression
+
+Compress current session working memory into structured text optimized for session recovery, extract critical information, and save to persistent storage via MCP `core_memory` tool.
+
+## Objective
+
+- Capture everything needed to resume work seamlessly in a new session
+- Minimize re-exploration by including file paths, decisions, and state
+- Preserve train of thought for complex debugging
+- Record actionable state (last action, known issues, pending)
+
+## Input
+
+- `sessionDescription` (Optional): User-provided session description string
+ - Example: `"completed core-memory module"`
+ - Example: `"debugging JWT refresh - suspected memory leak"`
+
+## Execution
+
+### Step 1.1: Analyze Current Session
+
+Extract the following from conversation history:
+
+```javascript
+const sessionAnalysis = {
+ sessionId: "", // WFS-* if workflow session active, null otherwise
+ projectRoot: "", // Absolute path: D:\Claude_dms3
+ objective: "", // High-level goal (1-2 sentences)
+ executionPlan: {
+ source: "workflow" | "todo" | "user-stated" | "inferred",
+ content: "" // Full plan content - ALWAYS preserve COMPLETE and DETAILED form
+ },
+ workingFiles: [], // {absolutePath, role} - modified files
+ referenceFiles: [], // {absolutePath, role} - read-only context files
+ lastAction: "", // Last significant action + result
+ decisions: [], // {decision, reasoning}
+ constraints: [], // User-specified limitations
+ dependencies: [], // Added/changed packages
+ knownIssues: [], // Deferred bugs
+ changesMade: [], // Completed modifications
+ pending: [], // Next steps
+ notes: "" // Unstructured thoughts
+}
+```
+
+**Core Philosophy**:
+- **Session Recovery First**: Capture everything needed to resume work seamlessly
+- **Minimize Re-exploration**: Include file paths, decisions, and state to avoid redundant analysis
+- **Preserve Train of Thought**: Keep notes and hypotheses for complex debugging
+- **Actionable State**: Record last action result and known issues
+
+### Step 1.2: Plan Detection (Priority Order)
+
+**Priority 1: Workflow Session (IMPL_PLAN.md)**
+```javascript
+// Check for active workflow session
+const manifest = await mcp__ccw-tools__session_manager({
+ operation: "list",
+ location: "active"
+});
+
+if (manifest.sessions?.length > 0) {
+ const session = manifest.sessions[0];
+ const plan = await mcp__ccw-tools__session_manager({
+ operation: "read",
+ session_id: session.id,
+ content_type: "plan"
+ });
+ sessionAnalysis.sessionId = session.id;
+ sessionAnalysis.executionPlan.source = "workflow";
+ sessionAnalysis.executionPlan.content = plan.content;
+}
+```
+
+**Priority 2: TodoWrite (Current Session Todos)**
+```javascript
+// Extract from conversation - look for TodoWrite tool calls
+// Preserve COMPLETE todo list with all details
+const todos = extractTodosFromConversation();
+if (todos.length > 0) {
+ sessionAnalysis.executionPlan.source = "todo";
+ sessionAnalysis.executionPlan.content = todos.map(t =>
+ `- [${t.status === 'completed' ? 'x' : t.status === 'in_progress' ? '>' : ' '}] ${t.content}`
+ ).join('\n');
+}
+```
+
+**Priority 3: User-Stated Plan**
+```javascript
+// Look for explicit plan statements in user messages:
+// - "Here's my plan: 1. ... 2. ... 3. ..."
+// - "I want to: first..., then..., finally..."
+// - Numbered or bulleted lists describing steps
+const userPlan = extractUserStatedPlan();
+if (userPlan) {
+ sessionAnalysis.executionPlan.source = "user-stated";
+ sessionAnalysis.executionPlan.content = userPlan;
+}
+```
+
+**Priority 4: Inferred Plan**
+```javascript
+// If no explicit plan, infer from:
+// - Task description and breakdown discussion
+// - Sequence of actions taken
+// - Outstanding work mentioned
+const inferredPlan = inferPlanFromDiscussion();
+if (inferredPlan) {
+ sessionAnalysis.executionPlan.source = "inferred";
+ sessionAnalysis.executionPlan.content = inferredPlan;
+}
+```
+
+### Step 1.3: Generate Structured Text
+
+```javascript
+const generateExecutionPlan = (plan) => {
+ const sourceLabels = {
+ 'workflow': 'workflow (IMPL_PLAN.md)',
+ 'todo': 'todo (TodoWrite)',
+ 'user-stated': 'user-stated',
+ 'inferred': 'inferred'
+ };
+
+ // CRITICAL: Preserve complete plan content verbatim - DO NOT summarize
+ return `### Source: ${sourceLabels[plan.source] || plan.source}
+
+
+Full Execution Plan (Click to expand)
+
+${plan.content}
+
+ `;
+};
+
+const structuredText = `## Session ID
+${sessionAnalysis.sessionId || '(none)'}
+
+## Project Root
+${sessionAnalysis.projectRoot}
+
+## Objective
+${sessionAnalysis.objective}
+
+## Execution Plan
+${generateExecutionPlan(sessionAnalysis.executionPlan)}
+
+## Working Files (Modified)
+${sessionAnalysis.workingFiles.map(f => `- ${f.absolutePath} (role: ${f.role})`).join('\n') || '(none)'}
+
+## Reference Files (Read-Only)
+${sessionAnalysis.referenceFiles.map(f => `- ${f.absolutePath} (role: ${f.role})`).join('\n') || '(none)'}
+
+## Last Action
+${sessionAnalysis.lastAction}
+
+## Decisions
+${sessionAnalysis.decisions.map(d => `- ${d.decision}: ${d.reasoning}`).join('\n') || '(none)'}
+
+## Constraints
+${sessionAnalysis.constraints.map(c => `- ${c}`).join('\n') || '(none)'}
+
+## Dependencies
+${sessionAnalysis.dependencies.map(d => `- ${d}`).join('\n') || '(none)'}
+
+## Known Issues
+${sessionAnalysis.knownIssues.map(i => `- ${i}`).join('\n') || '(none)'}
+
+## Changes Made
+${sessionAnalysis.changesMade.map(c => `- ${c}`).join('\n') || '(none)'}
+
+## Pending
+${sessionAnalysis.pending.length > 0
+ ? sessionAnalysis.pending.map(p => `- ${p}`).join('\n')
+ : '(none)'}
+
+## Notes
+${sessionAnalysis.notes || '(none)'}`;
+```
+
+### Step 1.4: Import to Core Memory
+
+```javascript
+mcp__ccw-tools__core_memory({
+ operation: "import",
+ text: structuredText
+})
+```
+
+### Step 1.5: Report Recovery ID
+
+After successful import, display the Recovery ID:
+
+```
++============================================================================+
+| Session Memory Saved |
+| |
+| Recovery ID: CMEM-YYYYMMDD-HHMMSS |
+| |
+| To restore: "Please import memory " |
+| (MCP: core_memory export | CLI: ccw core-memory export --id ) |
++============================================================================+
+```
+
+## Path Resolution Rules
+
+### Project Root Detection
+1. Check current working directory from environment
+2. Look for project markers: `.git/`, `package.json`, `.claude/`
+3. Use the topmost directory containing these markers
+
+### Absolute Path Conversion
+```javascript
+const toAbsolutePath = (relativePath, projectRoot) => {
+ if (path.isAbsolute(relativePath)) return relativePath;
+ return path.join(projectRoot, relativePath);
+};
+```
+
+### Reference File Categories
+| Category | Examples | Priority |
+|----------|----------|----------|
+| Project Config | `.claude/CLAUDE.md`, `package.json`, `tsconfig.json` | High |
+| Type Definitions | `src/types/*.ts`, `*.d.ts` | High |
+| Related Modules | Parent/sibling modules with shared interfaces | Medium |
+| Test Files | Corresponding test files for modified code | Medium |
+| Documentation | `README.md`, `ARCHITECTURE.md` | Low |
+
+## Quality Checklist
+
+Before generating:
+- [ ] Session ID captured if workflow session active (WFS-*)
+- [ ] Project Root is absolute path (e.g., D:\Claude_dms3)
+- [ ] Objective clearly states the "North Star" goal
+- [ ] Execution Plan: COMPLETE plan preserved VERBATIM (no summarization)
+- [ ] Plan Source: Clearly identified (workflow | todo | user-stated | inferred)
+- [ ] Plan Details: ALL phases, tasks, file paths, dependencies, status markers included
+- [ ] All file paths are ABSOLUTE (not relative)
+- [ ] Working Files: 3-8 modified files with roles
+- [ ] Reference Files: Key context files (CLAUDE.md, types, configs)
+- [ ] Last Action captures final state (success/failure)
+- [ ] Decisions include reasoning, not just choices
+- [ ] Known Issues separates deferred from forgotten bugs
+- [ ] Notes preserve debugging hypotheses if any
+
+## Output
+
+- **Variable**: `structuredText` - the generated markdown string
+- **MCP Result**: `{ operation: "import", id: "CMEM-YYYYMMDD-HHMMSS" }`
+- **User Display**: Recovery ID banner with restore instructions
+
+## Next Phase
+
+N/A - Compact is a terminal phase. Return to SKILL.md orchestrator.
diff --git a/.claude/skills/memory-capture/phases/02-tips.md b/.claude/skills/memory-capture/phases/02-tips.md
new file mode 100644
index 00000000..c40c5d1d
--- /dev/null
+++ b/.claude/skills/memory-capture/phases/02-tips.md
@@ -0,0 +1,206 @@
+# Phase 2: Tips - Quick Note Taking
+
+Quick note-taking for capturing ideas, snippets, reminders, and insights with optional tagging and context linking.
+
+## Objective
+
+- Provide minimal-friction note capture
+- Support tagging for categorization and search
+- Auto-detect context from current conversation
+- Save to core_memory for persistent retrieval
+
+## Input
+
+- `noteContent` (Required): The tip/note content to save
+- `tags` (Optional): Comma-separated tags for categorization
+- `context` (Optional): Related context (file, module, feature)
+
+**Examples**:
+```bash
+"Use Zod for runtime validation - better DX than class-validator"
+"Redis connection pool: max 10, min 2" --tag config,redis
+"Fix needed: race condition in payment processor" --tag bug,payment --context src/payments
+```
+
+## Execution
+
+### Step 2.1: Parse Arguments
+
+```javascript
+const parseTipsCommand = (input) => {
+ // Extract note content (everything before flags)
+ const contentMatch = input.match(/^"([^"]+)"|^([^\s-]+)/);
+ const content = contentMatch ? (contentMatch[1] || contentMatch[2]) : '';
+
+ // Extract tags
+ const tagsMatch = input.match(/--tag\s+([^\s-]+)/);
+ const tags = tagsMatch ? tagsMatch[1].split(',').map(t => t.trim()) : [];
+
+ // Extract context
+ const contextMatch = input.match(/--context\s+([^\s-]+)/);
+ const context = contextMatch ? contextMatch[1] : '';
+
+ return { content, tags, context };
+};
+```
+
+### Step 2.2: Gather Context
+
+```javascript
+const gatherTipContext = async () => {
+ // Get project root
+ const projectRoot = process.cwd(); // or detect from environment
+
+ // Get current session if active
+ const manifest = await mcp__ccw-tools__session_manager({
+ operation: "list",
+ location: "active"
+ });
+ const sessionId = manifest.sessions?.[0]?.id || null;
+
+ // Auto-detect files from recent conversation
+ const recentFiles = extractRecentFilesFromConversation(); // Last 5 messages
+
+ return {
+ projectRoot,
+ sessionId,
+ autoDetectedContext: recentFiles
+ };
+};
+```
+
+### Step 2.3: Generate Structured Text
+
+```javascript
+const generateTipText = (parsed, context) => {
+ const timestamp = new Date().toISOString().replace('T', ' ').slice(0, 19);
+ const tipId = `TIP-${new Date().toISOString().slice(0,10).replace(/-/g, '')}-${new Date().toTimeString().slice(0,8).replace(/:/g, '')}`;
+
+ return `## Tip ID
+${tipId}
+
+## Timestamp
+${timestamp}
+
+## Project Root
+${context.projectRoot}
+
+## Content
+${parsed.content}
+
+## Tags
+${parsed.tags.length > 0 ? parsed.tags.join(', ') : '(none)'}
+
+## Context
+${parsed.context || '(none)'}
+
+## Session Link
+${context.sessionId || '(none)'}
+
+## Auto-Detected Context
+${context.autoDetectedContext.length > 0
+ ? context.autoDetectedContext.map(f => `- ${f}`).join('\n')
+ : '(none)'}`;
+};
+```
+
+### Step 2.4: Save to Core Memory
+
+```javascript
+mcp__ccw-tools__core_memory({
+ operation: "import",
+ text: structuredText
+})
+```
+
+### Step 2.5: Confirm to User
+
+```
+Tip saved successfully
+
+ ID: CMEM-YYYYMMDD-HHMMSS
+ Tags: architecture, auth
+ Context: src/auth/**
+
+ To retrieve: core_memory(operation="search", query="")
+```
+
+## Tag Categories (Suggested)
+
+**Technical**:
+- `architecture` - Design decisions and patterns
+- `performance` - Optimization insights
+- `security` - Security considerations
+- `bug` - Bug notes and fixes
+- `config` - Configuration settings
+- `api` - API design patterns
+
+**Development**:
+- `testing` - Test strategies and patterns
+- `debugging` - Debugging techniques
+- `refactoring` - Refactoring notes
+- `documentation` - Doc improvements
+
+**Domain Specific**:
+- `auth` - Authentication/authorization
+- `database` - Database patterns
+- `frontend` - UI/UX patterns
+- `backend` - Backend logic
+- `devops` - Infrastructure and deployment
+
+**Organizational**:
+- `reminder` - Follow-up items
+- `research` - Research findings
+- `idea` - Feature ideas
+- `review` - Code review notes
+
+## Search Integration
+
+Tips can be retrieved using:
+
+```javascript
+// Via MCP tool
+mcp__ccw-tools__core_memory({
+ operation: "search",
+ query: "rate limiting",
+ source_type: "core_memory",
+ top_k: 10
+})
+
+// Via CLI
+// ccw core-memory search --query "rate limiting" --top-k 10
+```
+
+## Quality Checklist
+
+Before saving:
+- [ ] Content is clear and actionable
+- [ ] Tags are relevant and consistent
+- [ ] Context provides enough reference
+- [ ] Auto-detected context is accurate
+- [ ] Project root is absolute path
+- [ ] Timestamp is properly formatted
+
+## Best Practices
+
+### Good Tips
+
+- **Specific and Actionable**: `"Use connection pooling for Redis: { max: 10, min: 2, acquireTimeoutMillis: 30000 }" --tag config,redis`
+- **With Context**: `"Auth middleware must validate both access and refresh tokens" --tag security,auth --context src/middleware/auth.ts`
+- **Problem + Solution**: `"Memory leak fixed by unsubscribing event listeners in componentWillUnmount" --tag bug,react --context src/components/Chat.tsx`
+
+### Poor Tips (Avoid)
+
+- Too Vague: `"Fix the bug" --tag bug`
+- Too Long (use Compact instead): Multi-paragraph implementation plans
+- No Context: `"Remember to update this later"`
+
+## Output
+
+- **Variable**: `structuredText` - the generated tip markdown string
+- **MCP Result**: `{ operation: "import", id: "CMEM-YYYYMMDD-HHMMSS" }`
+- **User Display**: Confirmation with ID, tags, and retrieval hint
+
+## Next Phase
+
+N/A - Tips is a terminal phase. Return to SKILL.md orchestrator.