← Back to Skills Marketplace
record a dream
by
Juno Studio
· GitHub ↗
· v1.0.0
· MIT-0
245
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install dream-journal
Description
梦境记录与解析工具。触发条件:(1) 用户发送 /记录梦 或描述一个梦境要求记录;(2) 用户发送 /解梦 或要求解析/分析某个梦;(3) 用户询问历史梦境记录("我上周梦过什么"、"查询梦境"等)。
README (SKILL.md)
\r \r
Dream Journal\r
\r
梦境记录与解析。数据存储于 ~/.openclaw/memory/dreams/,每条记录为一个 Markdown 文件,命名格式 YYYY-MM-DD-NNN.md。\r
\r
命令\r
\r
/记录梦\r
\r 用户口述梦境内容后执行:\r \r
- 请用户描述梦境(如尚未描述)\r
- 整理为结构化叙述:清晰的时间线、场景、人物、情绪\r
- 提取 3-5 个标签(场景、情绪、意象,用中文)\r
- 生成简短标题(10 字以内)\r
- 调用脚本保存:\r \r
echo '{\r
"title": "梦境标题",\r
"raw": "用户原始描述",\r
"structured": "整理后的叙述",\r
"tags": ["标签1", "标签2"]\r
}' | python3 ~/.openclaw/workspace/skills/dream-journal/scripts/save_dream.py\r
```\r
\r
6. 回复:已记录「标题」,询问是否需要当场解梦\r
\r
### /解梦\r
\r
解析当前对话中的梦境,或用户指定的历史梦境:\r
\r
1. 确认要解析的梦境内容(当前描述或查询历史)\r
2. 按以下维度分析:\r
- **核心意象**:梦中突出的人/物/场景及其象征含义\r
- **情绪基调**:梦境整体情绪及其可能反映的内心状态\r
- **潜在关联**:与近期生活压力、愿望或未处理情绪的可能联系\r
- **整体解读**:综合性解读(不要过度确定,保持开放性)\r
3. 语气:温和、好奇、不武断,避免"你一定是……"式断言\r
\r
### 查询历史\r
\r
用户问"我最近梦过什么"、"查梦境记录"等:\r
\r
```bash\r
# 最近20条\r
echo '{"limit": 20}' | python3 ~/.openclaw/workspace/skills/dream-journal/scripts/list_dreams.py\r
\r
# 按关键词\r
echo '{"keyword": "飞翔"}' | python3 ~/.openclaw/workspace/skills/dream-journal/scripts/list_dreams.py\r
\r
# 指定日期范围(since 为 YYYY-MM-DD)\r
echo '{"since": "2026-03-01"}' | python3 ~/.openclaw/workspace/skills/dream-journal/scripts/list_dreams.py\r
```\r
\r
查询后,读取相关文件内容后向用户汇报。\r
\r
## 存储格式\r
\r
```\r
~/.openclaw/memory/dreams/\r
├── 2026-03-11-001.md\r
├── 2026-03-11-002.md\r
└── ...\r
```\r
\r
每个文件结构:\r
```markdown\r
---\r
date: 2026-03-11 08:30\r
title: 梦境标题\r
tags: [飞翔, 焦虑, 学校]\r
---\r
\r
## 原始描述\r
用户口述的原始内容\r
\r
## 整理版本\r
AI整理后的结构化叙述\r
```\r
\r
## 注意事项\r
\r
- 记录时不评判梦境内容,如实保存\r
- 解梦时区分"可能"与"确定",避免过度解读\r
- 若用户只想记录不想解梦,尊重意愿,不主动解析\r
Usage Guidance
This skill appears to do what it says: it stores dream entries locally and can list/parse them. Before installing, verify the script file locations (SKILL.md references a scripts/ subfolder but files are at the package root) so the runtime calls will work. Be aware that the tool saves potentially sensitive personal content in ~/.openclaw/memory/dreams/ — consider setting filesystem permissions, backups, or encrypting that directory if you want stronger privacy. If you want additional assurance, open the two Python files and confirm there are no network calls (they contain none) and run the scripts locally with sample input to test behavior.
Capability Analysis
Type: OpenClaw Skill
Name: dream-journal
Version: 1.0.0
The dream-journal skill is a legitimate tool for recording and analyzing dreams, storing data locally in Markdown files within the user's home directory (~/.openclaw/memory/dreams/). The Python scripts (save_dream.py and list_dreams.py) perform basic file I/O and JSON parsing using standard libraries, with no network access, data exfiltration, or obfuscation. The instructions in SKILL.md are well-defined and include safety-oriented guidelines for the AI agent, such as respecting user privacy and avoiding over-interpretation.
Capability Assessment
Purpose & Capability
Name/description (recording and interpreting dreams) matches the included code and instructions: scripts save and list Markdown dream records under ~/.openclaw/memory/dreams/. No unrelated credentials, binaries, or packages are requested.
Instruction Scope
Runtime instructions stay within the stated purpose (prompt user, structure content, save and later list/parse records). Minor inconsistency: SKILL.md examples call python scripts at ~/.openclaw/workspace/skills/dream-journal/scripts/*.py, but the shipped files are top-level (save_dream.py, list_dreams.py) — the referenced scripts/ path may not exist, which is an operational bug but not a malicious action.
Install Mechanism
No install spec; this is instruction-only with two small local Python scripts. Nothing is downloaded from external URLs and no archives are extracted. Risk from install mechanism is low.
Credentials
The skill requires no environment variables, credentials, or config paths beyond the local dreams directory it creates/uses (~/.openclaw/memory/dreams/). This access is proportionate to its purpose of storing local records.
Persistence & Privilege
always is false and the skill does not request elevated or system-wide privileges. It creates and writes only to its own data directory and does not modify other skills or global agent configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install dream-journal - After installation, invoke the skill by name or use
/dream-journal - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the dream-journal skill, enabling dream recording, analysis, and history queries.
- Supports recording dreams with user prompts, structured summaries, tagging, and titling.
- Provides dream analysis by core imagery, emotion, life context, and holistic interpretation with gentle tone.
- Lets users search and review their dream history by date, keyword, or recent records.
- Stores each dream as a structured Markdown file in a dedicated folder.
Metadata
Frequently Asked Questions
What is record a dream?
梦境记录与解析工具。触发条件:(1) 用户发送 /记录梦 或描述一个梦境要求记录;(2) 用户发送 /解梦 或要求解析/分析某个梦;(3) 用户询问历史梦境记录("我上周梦过什么"、"查询梦境"等)。 It is an AI Agent Skill for Claude Code / OpenClaw, with 245 downloads so far.
How do I install record a dream?
Run "/install dream-journal" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is record a dream free?
Yes, record a dream is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does record a dream support?
record a dream is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created record a dream?
It is built and maintained by Juno Studio (@abycloudcn-jpg); the current version is v1.0.0.
More Skills