halthelobster

PARA Second Brain

AI 智慧體v2.0.1
作者:halthelobster更新於 2026-05-11共 7 個版本 · 最新版本釋出於 2026-01-29para-second-brain@clawhub_halthelobster/para-second-brain
工作流編排上下文管理記憶增強#Knowledge Base

據 AlphaMoat 統計,截至 2026-10,PARA Second Brain 累計下載 12,798 次、獲 54 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 2,179 位,在「AI 智慧體」分類(1,632 個)中排名第 296 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
1.3萬
星標
54
全站下載量排名
#2,179
全站前 20% · 「AI 智慧體」前 19%
平台累計下載星標評論
ClawHub ↗823953-
SkillHub ↗1.3萬54—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

用 PARA(Projects、Areas、Resources、Archive)整理 Agent 知識。依指南設定 symlink 後,可將語義檢索範圍從 MEMORY.md 擴展到整個知識庫;文件也涵蓋工作階段記錄和 memory flush 做法。請依對應 Agent 環境完成設定。原文未證明所有檢索都完全離線或不會產生外部費用。

資料釋出於 2026-10-27

可以用來做什麼

  • 把散落的筆記按 PARA 歸位並建立統一檢索入口
  • 為長期專案建立可跨會話恢復的記憶結構

什麼時候用

  • 依 PARA 方法整理 Agent 知識時
  • 希望讓整個知識庫都可參與語義檢索時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

幫我按 PARA 把現有筆記分類,並說明哪些該進歸檔
我的檢索只覆蓋一個檔案,幫我改成能搜到整個筆記目錄

月度資料趨勢

累計下載1.3萬
651898911.3萬2026-03 · 累計下載 69832026-05 · 累計下載 76302026-06 · 累計下載 77612026-07 · 累計下載 79422026-08 · 累計下載 80582026-09 · 累計下載 87772026-10 · 累計下載 1.3萬26-0326-0926-10
星標54
5052542026-03 · 星標 502026-05 · 星標 532026-06 · 星標 542026-07 · 星標 542026-08 · 星標 542026-09 · 星標 542026-10 · 星標 5426-0326-0926-10

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份累計下載環比星標
2026-101.3萬—54
2026-098777—54
2026-088058+1.5%54
2026-077942+2.3%54
2026-067761+1.7%54
2026-057630—53
2026-036983—50

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

13 KB · ClawHub v2.0.1
---
name: para-second-brain
version: 2.0.1
description: Organize your agent's knowledge using PARA (Projects, Areas, Resources, Archive) — then make it ALL searchable. The symlink trick enables full semantic search across your entire knowledge base, not just MEMORY.md. Includes session transcript indexing and memory flush protocol. Your agent finally has a real second brain.
---

# PARA Second Brain

Your agent's memory just got a massive upgrade. Full semantic search across your entire knowledge base — not just MEMORY.md.
展開全部(共 406 行)
## What's New in v2.0

**Before v2.0:** `memory_search` only found content in MEMORY.md and daily logs. Your entire `notes/` folder was invisible to search. You had to manually know where to look.

**After v2.0:** One symlink command makes your entire PARA knowledge base searchable. Ask about anything in your notes — it finds it. Plus session transcripts and memory flush protocol to prevent context loss.

| Before | After |
|--------|-------|
| Search only MEMORY.md + daily logs | Search EVERYTHING |
| "I don't have that information" | Finds it instantly |
| Context compaction = lost information | Flush protocol saves critical context |
| Conversations forgotten | Session transcripts indexed |

## What This Does

Creates a "second brain" structure that separates:
- **Raw capture** (daily logs) from **curated knowledge** (MEMORY.md)
- **Active work** (projects) from **ongoing responsibilities** (areas)
- **Reference material** (resources) from **completed work** (archive)

## How This Differs from Other Second Brain Skills

There's another popular [second-brain skill](https://clawdhub.com/christinetyip/second-brain) powered by Ensue. Both are great — they solve different problems:

| | **PARA Second Brain** (this skill) | **Ensue Second Brain** |
|---|---|---|
| **Storage** | Local files in your workspace | Cloud API (Ensue) |
| **Cost** | Free, self-hosted | Requires Ensue API key |
| **Best for** | Work context, agent continuity, project tracking | Evergreen knowledge base, semantic queries |
| **Search** | Clawdbot's `memory_search` | Ensue's vector search |
| **Structure** | PARA (Projects/Areas/Resources/Archive) | Namespaces (concepts/toolbox/patterns) |
| **Use case** | "What did we decide yesterday?" | "How does recursion work?" |

**Use this skill if:** You want file-based memory that works offline, costs nothing, and tracks ongoing work context.

**Use Ensue's skill if:** You want a cloud-hosted knowledge base optimized for semantic "what do I know about X" queries.

**Use both if:** You want PARA for work context + Ensue for evergreen knowledge. They complement each other.

## Quick Setup

### 1. Create Directory Structure

```
workspace/
├── MEMORY.md              # Curated long-term memory
├── memory/
│   └── YYYY-MM-DD.md      # Daily raw logs
└── notes/
    ├── projects/          # Active work with end dates
    ├── areas/             # Ongoing life responsibilities  
    ├── resources/         # Reference material
    │   └── templates/     # Content templates
    └── archive/           # Completed/inactive items
```

Run this to scaffold:
```bash
mkdir -p memory notes/projects notes/areas notes/resources/templates notes/archive
```

### 2. Make Notes Searchable (The Symlink Trick)

By default, `memory_search` only indexes `MEMORY.md` and `memory/*.md`. Your entire `notes/` folder is invisible to semantic search!

**Fix this with one command:**
```bash
ln -s /path/to/your/workspace/notes /path/to/your/workspace/memory/notes
```

Example:
```bash
ln -s /Users/yourname/clawd/notes /Users/yourname/clawd/memory/notes
```

**What this does:** Creates a symbolic link so `memory/notes/` points to your actual `notes/` folder. Now Clawdbot's memory_search sees all your PARA notes.

**Verify it worked:**
```bash
ls -la memory/notes  # Should show: memory/notes -> /path/to/notes
```

**Test the search:**
Ask your agent something that's in your notes but NOT in MEMORY.md. If it finds it, the symlink is working.

**Why this matters:**
| Before | After |
|--------|-------|
| Search only finds MEMORY.md + daily logs | Search finds ALL your notes |
| Must manually know where to look | Semantic search across everything |
| "I don't have that information" | Finds connections you forgot existed |

### 3. Enable Session Transcript Indexing

Make your past conversations searchable too. Add this to your Clawdbot config:

```json
"memorySearch": {
  "sources": ["memory", "sessions"],
  "query": {
    "minScore": 0.3,
    "maxResults": 20
  }
}
```

**What this does:** Indexes your conversation transcripts alongside your notes. Now when you ask "what did we discuss about X last week?" — it can actually find it.

### 4. Initialize MEMORY.md

Create `MEMORY.md` in workspace root - this is your curated long-term memory:

```markdown
# MEMORY.md — Long-Term Memory

## About [Human's Name]
- Role/occupation
- Key goals and motivations
- Communication preferences
- Important relationships

## Active Context
- Current focus areas
- Ongoing projects (summaries, not details)
- Deadlines or time-sensitive items

## Preferences & Patterns
- Tools and workflows they prefer
- Decision-making style
- Pet peeves and likes

## Lessons Learned
- What worked
- What didn't
- Principles discovered

## Key Dates
- Birthdays, anniversaries
- Recurring events
- Important milestones
```

### 5. Add to AGENTS.md

Add these instructions to your AGENTS.md:

```markdown
## Memory

You wake up fresh each session. These files are your continuity:
- **Daily notes:** `memory/YYYY-MM-DD.md` — raw logs of what happened
- **Long-term:** `MEMORY.md` — curated memories (like human long-term memory)
- **Topic notes:** `notes/` — organized by PARA structure (all searchable via memory_search)

### Writing Rules
- If it has future value, write it down NOW
- Don't rely on "mental notes" — they don't survive restarts
- Text > Brain 📝

### PARA Structure
- **Projects** (`notes/projects/`) — Active work with end dates
- **Areas** (`notes/areas/`) — Ongoing responsibilities (health, finances, relationships)
- **Resources** (`notes/resources/`) — Reference material, how-tos, research
- **Archive** (`notes/archive/`) — Completed or inactive items

### Memory Flush Protocol
Monitor your context usage with `session_status`. Before compaction wipes your memory, flush important context to files:

| Context % | Action |
|-----------|--------|
| < 50% | Normal operation |
| 50-70% | Write key points after substantial exchanges |
| 70-85% | Active flushing — write everything important NOW |
| > 85% | Emergency flush — full summary before next response |
| After compaction | Note what context may have been lost |

**The rule:** Act on thresholds, not vibes. If it's important, write it down NOW.
```

## Memory Flush Protocol (Critical!)

Your agent's context window is finite. When it fills up, older context gets compacted or lost. **Don't lose important information.**

### How to Monitor
Run `session_status` periodically. Look for:
```
📚 Context: 36k/200k (18%) · 🧹 Compactions: 0
```

### Threshold-Based Actions

| Context % | What to Do |
|-----------|------------|
| **< 50%** | Normal operation. Write decisions as they happen. |
| **50-70%** | Increased vigilance. Write key points after each substantial exchange. |
| **70-85%** | Active flushing. Write everything important to daily notes NOW. |
| **> 85%** | Emergency flush. Stop and write full context summary before responding. |
| **After compaction** | Immediately note what context may have been lost. Check continuity. |

### What to Flush
1. **Decisions made** — what was decided and why
2. **Action items** — who's doing what
3. **Open threads** — anything unfinished → `notes/areas/open-loops.md`
4. **Working changes** — if you discussed changes to files, make them NOW

### Memory Flush Checklist
Before a long session ends or context gets high:
- [ ] Key decisions documented?
- [ ] Action items captured?
- [ ] New learnings written to appropriate files?
- [ ] Open loops noted for follow-up?
- [ ] Could future-me continue this conversation from notes alone?

## Knowledge Quality

**The core question:** "Will future-me thank me for this?"

### What to Save
- Concepts you actually understand (not half-learned ideas)
- Tools you've actually used (not just heard about)
- Patterns that worked (with concrete examples)
- Lessons learned from mistakes

### What NOT to Save
- Half-understood concepts (learn first, save after)
- Tools you haven't tried yet (bookmarks ≠ knowledge)
- Shallow entries without the WHY
- Duplicates of existing notes

### Quality Gates
Before saving any curated note:
1. Written for future self who forgot context?
2. Includes WHY, not just WHAT?
3. Has concrete examples or key insight?
4. Structured for retrieval (scannable)?

## Content Templates

Use these for structured, high-quality entries in `notes/resources/`:

### Concept Template
```markdown
# [CONCEPT NAME]

## What It Is
[One-line definition]

## Why It Matters
[What problem it solves, when you'd need it]

## How It Works
[Explanation with examples]

## Key Insight
[The "aha" moment — what makes this click]
```

### Tool Template
```markdown
# [TOOL NAME]

**Category:** [devtools | productivity | etc.]

## What It Does
[Brief description]

## Why I Use It
[What problem it solved for YOU]

## When to Reach For It
[Scenarios where this is the right choice]

## Gotchas
- [Things that tripped you up]
```

### Pattern Template
```markdown
# [PATTERN NAME]

## Problem
[What situation triggers this pattern]

## Solution
[The approach]

## Trade-offs
**Pros:** [Why this works]
**Cons:** [When NOT to use it]
```

## PARA Explained

PARA is a knowledge organization system created by [Tiago Forte](https://fortelabs.com/), author of *Building a Second Brain*. It organizes everything into four categories based on actionability:

### Projects
**What:** Work with a deadline or end state
**Examples:** "Launch website", "Plan trip to Japan", "Finish client proposal"
**File as:** `notes/projects/website-launch.md`

### Areas
**What:** Ongoing responsibilities with no end date
**Examples:** Health, finances, relationships, career development
**File as:** `notes/areas/health.md`, `notes/areas/dating.md`

### Resources
**What:** Reference material for future use
**Examples:** Research, tutorials, templates, interesting articles
**File as:** `notes/resources/tax-guide.md`, `notes/resources/api-docs.md`

### Archive
**What:** Inactive items from the other categories
**Examples:** Completed projects, outdated resources, paused areas
**Move to:** `notes/archive/` when done

## Daily Log Format

Create `memory/YYYY-MM-DD.md` for each day:

```markdown
# YYYY-MM-DD

## Key Events
- [What happened, decisions made]

## Learnings
- [What worked, what didn't]

## Open Threads
- [Carry-forward items]
```

## The Curation Workflow

### Daily (5 min)
- Log notable events to `memory/YYYY-MM-DD.md`
- File topic-specific notes to appropriate `notes/` folder

### Weekly (15 min)
- Review the week's daily logs
- Extract patterns and learnings to MEMORY.md
- Move completed projects to archive

### Monthly (30 min)
- Review MEMORY.md for outdated info
- Consolidate or archive old project notes
- Ensure areas reflect current priorities

## Decision Tree: Where Does This Go?

```
Is it about today specifically?
  → memory/YYYY-MM-DD.md

Is it a task with an end date?
  → notes/projects/

Is it an ongoing responsibility?
  → notes/areas/

Is it reference material for later?
  → notes/resources/

Is it done or no longer relevant?
  → notes/archive/

Is it a distilled lesson or preference?
  → MEMORY.md
```

## Why Two Memory Layers?

| Daily Logs | MEMORY.md |
|------------|-----------|
| Raw, timestamped | Curated, organized |
| Everything captured | Only what matters |
| Chronological | Topical |
| High volume | Condensed |
| "What happened" | "What I learned" |

Daily logs are your journal. MEMORY.md is your wisdom.

## Principles

1. **Quality over quantity** — Curated notes beat note hoarding
2. **Capture fast, curate deliberately** — Daily logs are loose; curated notes are high quality
3. **Text > brain** — If it matters, write it down
4. **Future-me test** — "Will future-me thank me for this?"
5. **One home per item** — Don't duplicate; link instead
6. **Include the WHY** — Facts without context are useless
7. **Flush before you lose** — Monitor context, write before compaction

---

*Pairs well with [memory-setup](https://clawdhub.com/jrbobbyhansen-pixel/memory-setup) for technical config and [proactive-agent](https://clawdhub.com/halthelobster/proactive-agent) for behavioral patterns.*

「AI 智慧體」分類下的熱門技能

halthelobster 的其他技能

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。