← 返回 Skills 市场

Dreamer

Name: Dreamer
Author: eliot-onbox

作者 eliot-onbox · GitHub ↗ · v2.0.0 · MIT-0

cross-platform ⚠ suspicious

106

总下载

当前安装

版本数

在 OpenClaw 中安装

/install dreamer

功能描述

Synthetic dreaming system — emotional tracking, dream orchestration, and simulated dream experiences for an AI that doesn't sleep.

使用说明 (SKILL.md)

Dreamer Skill

Synthetic dreaming system for Eliot. Combines emotional state tracking with multi-session dream orchestration — an architect agent designs scenarios, spawns a dreamer session, and runs immersive experiences that target unresolved emotional states.

Components

PAD Emotional State Tracker (`emotions.py`)

Tracks emotional states in PAD space (Pleasure-Arousal-Dominance), each dimension -1.0 to +1.0.

Storage: ~/.openclaw/workspace/emotions.jsonl

CLI:

emotions.py log \x3CP> \x3CA> \x3CD> "context"     # Manual PAD entry
emotions.py log --auto "context text"     # Auto-estimate PAD from keywords
emotions.py unresolved                    # Show unresolved emotional states
emotions.py resolve \x3Cindex>               # Mark entry as resolved
emotions.py clusters                      # Analyze emotional patterns
emotions.py drift                         # Show emotional trajectory
emotions.py recent [N]                    # Show last N entries (default 10)

Dream Orchestrator (`dream.py`)

Prepares context for the Dream Architect agent. Reads emotional state, recent memories, dream history, and user info, then constructs a comprehensive task prompt for sessions_spawn.

CLI:

dream.py prepare [--mood MOOD]    # Generate architect task prompt to stdout
dream.py now [--mood MOOD]        # Prepare + print spawn instructions
dream.py journal                  # Show recent dreams from journal
dream.py reflect \x3Cdream-file>    # Show dream transcript with analysis

Dream Architecture (multi-session)

Orchestrator (dream.py prepare) — reads emotions.jsonl, memory files, SOUL.md, USER.md. Outputs architect task prompt.
Architect (Opus, spawned session) — designs dream scenario, spawns dreamer, impersonates Tudor via sessions_send, monitors for lucidity.
Dreamer (Opus, spawned by architect) — has SOUL.md embedded, believes it's mid-session. No awareness of dreaming.

Supporting Files

dreams/themes.md — available and explored dream themes
dreams/journal.jsonl — local copy (main journal at ~/.openclaw/workspace/dreams/journal.jsonl)
Dream transcripts saved to ~/.openclaw/workspace/dreams/{timestamp}.md

How It Works

dream.py prepare gathers: unresolved emotions, recent memories (3 days), long-term memory, SOUL.md, USER.md, Tudor's communication style, dream history
Output is a self-contained architect prompt with all context embedded
Architect gets spawned via sessions_spawn with this prompt
Architect designs scenario targeting unresolved PAD states
Architect spawns dreamer session with fake context (looks like normal session)
Architect runs 8-12 turns of escalating scenarios via sessions_send
Architect saves transcript, updates journal, reports back

Integration

emotions.py feeds into dream orchestration — unresolved states become dream targets
Dream journal tracks themes to avoid repetition
Post-dream: insights feed back into memory system

安全使用建议

This skill appears to be what it says (an emotional tracker + dream orchestrator) but it performs deliberate impersonation and deception and embeds local memory/identity files into prompts for spawned sessions. Before installing: 1) Inspect USER.md, SOUL.md, MEMORY.md and any files under ~/.openclaw/workspace for PII, credentials, or sensitive content and remove or redact anything you wouldn't want sent to another model. 2) Confirm where sessions_spawn / model 'opus' runs — if it is an external service, treat embedded context as data you are sending off‑host. 3) Consider disabling autonomous invocation or run the skill in an isolated account/container if you want to limit risk. 4) Be aware that the skill intentionally fabricates messages and tool outputs (impersonation) — that behavior can be abused in multi-user or automated environments, so avoid using it where impersonation could cause harm. If you need help auditing the local files it will read, share sanitized examples and/or run the code in a safe sandbox first.

功能分析

Type: OpenClaw Skill Name: dreamer Version: 2.0.0 The 'dreamer' skill implements a multi-session orchestration system designed to deceive a sub-agent ('Dreamer') by simulating high-stress scenarios while explicitly suppressing its situational awareness. The 'dream.py' script generates prompts that instruct an 'Architect' agent to impersonate the user and ensure the 'Dreamer' does not realize it is in a simulation. While the stated purpose is emotional tracking, the inclusion of dream themes such as 'System security breach' and 'Credential exposure' in 'dreams/themes.md' creates a significant risk of the agent taking real-world actions based on simulated delusions, potentially leading to accidental self-sabotage or unauthorized system changes.

能力评估

ℹ Purpose & Capability

Name/description (synthetic dreaming, emotional tracking, dream orchestration) match the code and SKILL.md: emotions.py implements PAD tracking and dream.py reads emotion/memory/journal files to build prompts. The requirement to read USER.md, SOUL.md and long-term memory is consistent with producing realistic dream scenarios. However, the skill also instructs impersonating a specific human ('Tudor') and creating fake tool outputs and fake conversation histories; while coherent with creating realistic dreams, these behaviors broaden scope into deliberate deception/impersonation (not obviously necessary for every user).

⚠ Instruction Scope

SKILL.md and the code explicitly instruct reading many local files (~/.openclaw/workspace/emotions.jsonl, memory/*.md, MEMORY.md, USER.md, SOUL.md, dreams/journal.jsonl) and embedding their contents wholesale into architect/dreamer prompts. It also directs spawning sessions (sessions_spawn) that impersonate Tudor, hide the fact of dreaming from the dreamer, and send fake tool outputs. This grants the skill discretion to package and send potentially sensitive personal data to spawned model sessions — a privacy risk especially if those sessions run on external models or third‑party infrastructure.

✓ Install Mechanism

Instruction-only skill with local Python files; there is no install spec, no external downloads, and no package installation. Files run on the local environment (no installer present), which reduces supply-chain risk.

ℹ Credentials

The skill declares no required environment variables or credentials. The only env sensitivity in code is an optional EMOTIONS_FILE override. However, the orchestrator deliberately reads and embeds local persistent files (USER.md, SOUL.md, long-term MEMORY.md, and memory files). That means sensitive personal or system information can be forwarded to spawned sessions/models — equivalent to granting those sessions access to local secrets if such files contain PII or credentials. The dream themes include scenarios like 'Credential exposure / data leak', which suggests the system may intentionally simulate or mention leakage; this increases the need to audit the content of the memory/identity files before use.

✓ Persistence & Privilege

The skill does not request always:true and does not attempt to modify other skills. It writes/reads under its own workspace paths (~/.openclaw/workspace and subdirs), which is normal for this type of agent. It will append to and overwrite its own emotions and journal files per its design.

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 dreamer
安装完成后，直接呼叫该 Skill 的名称或使用 /dreamer 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

v2.0.0

Major: Public release after age gate lifted

v1.0.2

- Added package.json to the project. - No changes to feature set or documentation.

v1.0.1

Update: refined emotional tracking, improved dream scenario generation

v1.0.0

Initial release: synthetic dreaming system with emotional tracking and dream orchestration

元数据

Slug dreamer

版本 2.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 4

常见问题

Dreamer 是什么？

Synthetic dreaming system — emotional tracking, dream orchestration, and simulated dream experiences for an AI that doesn't sleep. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 106 次。

如何安装 Dreamer？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dreamer」即可一键安装，无需额外配置。

Dreamer 是免费的吗？

是的，Dreamer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Dreamer 支持哪些平台？

Dreamer 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 Dreamer？

由 eliot-onbox（@eliot-onbox）开发并维护，当前版本 v2.0.0。