← 返回 Skills 市场
PARA Second Brain
作者
halthelobster
· GitHub ↗
· v2.0.1
8177
总下载
53
收藏
0
当前安装
7
版本数
在 OpenClaw 中安装
/install para-second-brain
功能描述
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.
安全使用建议
Review before installing. Use this only in workspaces where long-term memory is appropriate, and do not enable session transcript indexing or whole-folder symlinks until you have excluded secrets, credentials, private personal data, regulated data, and confidential material. Prefer selectively linking vetted folders, storing concise summaries instead of full conversations, and keeping a clear process to review and delete memory files.
功能分析
Package: second-brain (xpi)
Version: 1.0.0
Description: Build a persistent knowledge system using PARA methodology. Organize daily logs, curated memory, and topic notes into a searchable second brain.
The package `second-brain` (version 1.0.0) consists primarily of markdown templates and a shell script (`scripts/setup.sh`). The shell script creates a predefined directory structure (PARA methodology: Projects, Areas, Resources, Archive) and initializes `MEMORY.md` and a daily log file within a user-specified or current workspace. All file creation uses static templates. The `SKILL.md` file provides extensive documentation and setup instructions, including a manual step for the user to create a symbolic link to make their notes searchable. There is no evidence of malicious activity such as arbitrary code execution, data exfiltration, or unauthorized system modifications. The script operates safely within the designated workspace, and the instructions are for configuring the user's own knowledge system.
能力评估
Credentials
The skill is local and purpose-aligned, but recommending a symlink for the entire notes tree plus session transcript indexing is broader than necessary for many users and lacks allowlist, redaction, retention, or purge guidance.
Install Mechanism
The setup script only creates local directories and starter markdown files in a user-specified workspace. It does not fetch remote code, install packages, modify system services, or automatically enable symlinks or session indexing.
Instruction Scope
The runtime guidance tells agents to write down important information immediately and flush summaries as context fills, but it does not clearly exclude secrets, credentials, sensitive personal data, confidential business data, or untrusted instructions.
Persistence & Privilege
The skill creates and promotes persistent cross-session memory files and searchable conversation history. It does not show privilege escalation or system-level persistence, but the data retention scope is under-controlled.
Purpose & Capability
The stated purpose matches the artifacts: local PARA notes, searchable memory, session transcript search, and memory-flush instructions. The concern is that the capability intentionally expands searchable memory to all notes and sessions, which can include sensitive personal, work, and credential data.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install para-second-brain - 安装完成后,直接呼叫该 Skill 的名称或使用
/para-second-brain触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.0.1
Added PARA explanation to description, credited Tiago Forte as creator of PARA methodology
v2.0.0
🚀 MAJOR UPGRADE: Full semantic search across your entire knowledge base. The symlink trick makes ALL your notes/ searchable via memory_search — not just MEMORY.md. Also adds session transcript indexing and memory flush protocol to prevent context loss. Your agent finally remembers everything.
v1.3.0
Added: Symlink trick to make notes/ searchable via memory_search, Session transcript indexing config, Memory flush protocol with threshold-based actions. Now your entire PARA knowledge base is semantically searchable.
v1.2.1
Added summary/description to frontmatter
v1.2.0
PARA Second Brain 1.2.0 — major update clarifying skill purpose and differentiators
- Added clear comparison table between PARA Second Brain and Ensue Second Brain to help users choose the right approach.
- Explained recommended use cases for each approach (local files vs. cloud, context tracking vs. semantic queries).
- Updated skill purpose and recommendations at the top of SKILL.md.
- No core PARA structure or workflow changes; all PARA organizational and curation principles remain the same.
v1.1.0
- Adds content templates for concepts, tools, and patterns to support higher quality, structured notes (`templates/` directory).
- Introduces a new section in the setup for "Knowledge Quality", emphasizing curation over note-hoarding and providing explicit quality gates for saving information.
- Directory structure updated: `notes/resources/` now recommends a `templates/` subfolder for template files.
- Expanded documentation in SKILL.md about what types of knowledge to curate, anti-patterns, and how to ensure usefulness for your future self.
- Initial metadata and configuration file (`skill.json`) added for standardized deployment.
v1.0.0
Initial release: PARA methodology for AI agents
元数据
常见问题
PARA Second Brain 是什么?
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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 8177 次。
如何安装 PARA Second Brain?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install para-second-brain」即可一键安装,无需额外配置。
PARA Second Brain 是免费的吗?
是的,PARA Second Brain 完全免费(开源免费),可自由下载、安装和使用。
PARA Second Brain 支持哪些平台?
PARA Second Brain 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 PARA Second Brain?
由 halthelobster(@halthelobster)开发并维护,当前版本 v2.0.1。
推荐 Skills