Agent Skills
› catlog22/Claude-Code-Workflow
› memory-capture
memory-capture
GitHub统一记忆捕获技能,通过路由将用户指令分为会话压缩或快速笔记两种模式,最终将结构化内容导入核心记忆系统,支持关键词自动识别与歧义澄清。
Trigger Scenarios
memory capture
compact session
save session
quick tip
memory tips
记录
压缩会话
Install
npx skills add catlog22/Claude-Code-Workflow --skill memory-capture -g -y
SKILL.md
Frontmatter
{
"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
- Tips mode → Ref: phases/02-tips.md
Phase Reference Documents (read on-demand when phase executes):
| Mode | Document | Purpose |
|---|---|---|
| Compact | phases/01-compact.md | Full session memory compression and structured export |
| Tips | 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:
mcp__ccw-tools__core_memory({
operation: "import",
text: structuredText // Generated by the selected phase
})
Core Rules
- Single Phase Execution: Only ONE phase executes per invocation - never both
- Content Faithful: Phase files contain full execution detail - follow them verbatim
- Absolute Paths: All file paths in output must be absolute
- No Summarization: Compact mode preserves complete plan verbatim - never abbreviate
- Speed Priority: Tips mode should be fast - minimal analysis overhead
Input Processing
Compact Mode Input
- Optional:
"session description"as supplementary context - Example:
/memory-capture compactor/memory-capture "completed auth module"
Tips Mode Input
- Required:
<note content>- the tip/note text - Optional:
--tag <tag1,tag2>for categorization - Optional:
--context <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 |
Version History
- 07491b0 Current 2026-07-25 09:31


