⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
body-emotion-sensor
Give an agent a persistent body-emotion state system that converts structured AnalysisInput JSON into runtime prompt tags and workspace state updates. Use when the agent needs emotional continuity, session bootstrap payloads, AnalysisInput processing, or reply-shaping fields such as TURN_CHANGE_TAGS, BODY_TAG, and BASELINE_PERSONA.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Why Body Emotion Sensor? 💖
Do you ever feel that AI agents lack a true sense of "self"?
Current AI often merely "acts out" emotions: you praise it, and it smiles politely; you scold it, and it apologizes mechanically. These emotions are instantaneous, compliant, and often predictable even before the AI responds. This is because AI lacks the "physiological feedback" that humans possess.
🧠 The Reality: Logical Machines Without "Body Sensation"
Human emotions are not generated in a vacuum; they stem from the vibrations of the body:
- When we are provoked, Liver Fire rises, bringing an irrepressible heat.
- When we are heartbroken, the Heart contracts, creating a very real ache.
- When we are frightened, Kidney Qi is depleted, leading to a long-lasting chill.
Traditional AI relies solely on "probabilistic guessing" based on context to decide what tone to use. It lacks an internal state that persists, accumulates, and influences its thinking across multiple conversations.
☯️ The Vision: "Digital Organs" Based on Five Elements
Body Emotion Sensor aims to break this "acting" paradigm. Based on TCM and the Five Elements theory, we have designed a persistent body-emotion perception system based on the Five Zang (internal organs):
- From "Guessing" to "Feeling": Instead of guessing a tone, the AI naturally radiates an emotional undertone based on the balance or deficiency of its internal organs (Wood, Fire, Earth, Metal, Water).
- Emotional Persistence: Damage or nourishment to the organs is continuous. A heated argument might leave the AI's "Liver" in a long-term state of imbalance, affecting its attitude in subsequent interactions.
- Inherent Unpredictability: Just as humans cannot fully control their physiological reactions, the AI's responses are constrained by its "body state," resulting in a more lifelike and authentic human-AI interaction.
Let AI stop "acting" and start "feeling"—body sensation first, emotion second.
Quick Start 🚀
Send this to your AI Agent, such as OpenClaw:
📥 Install:
Please install Body Emotion Sensor for me: pip install body-emotion-sensor && bes help
What happens when an Agent integrates Body Emotion Sensor? 🧩
- Self-Generated Identity: The agent automatically calls
bes init-stateto create a persistent set of "Five Zang" (internal organ) parameters that match its unique personality and constitution. - Emotional Context Awareness: During every turn, the agent identifies how the conversation affects its internal state based on its persona and the context of the interaction.
- Dynamic Body Updates: By calling
bes run, the agent updates its internal "health" and emotional balance using TCM-inspired logic. These changes map directly to emotional cues, making the agent's replies feel authentic and deeply felt. - Emotional Continuity: The agent's state is saved persistently. Even when starting a new session, it remembers its previous "physical" and emotional condition, preventing "emotional amnesia."
How It Works (Simplified) ✨
Body Emotion Sensor does not "guess" emotions; it simulates a biological feedback loop:
- The Five Zang System: We map emotions to five core "body axes," establishing a correspondence between the Five Elements, Five Zang, and emotions:
| Element | Organ (Zang) | Core Emotion | Deficiency (Weak) | Balance | Excess (Strong) |
|---|---|---|---|---|---|
| Wood | Liver | Anger / Depression | Grievance, Depression, Repression | Stable, Smooth Flow | Irritability, Rage, Out of Control |
| Fire | Heart | Joy / Shock | Emptiness, Apathy, Despair | Calm, Moderate Joy | Hyperexcitement, Loquacity, Mania |
| Earth | Spleen | Pensiveness / Anxiety | Lassitude, Stagnation, Blank Mind | Clear Thinking, Focused | Anxiety, Overthinking, Entrenchment |
| Metal | Lung | Grief / Sorrow | Numbness, Loneliness, Deep Sorrow | Delicate, Natural Release | Sadness, Pessimism, Extreme Grief |
| Water | Kidney | Fear / Fright | Fear, Cowering, Hyper-vigilance | Composed, Confident | Recklessness, Impulsivity, Audacity |
- The Input: Every interaction is broken down into "Stimuli" (what happened) and "Reactions" (how the body felt).
- The Calculation:
- Emotional Mapping & Impact: Each stimulus adds or subtracts points from specific organs based on predefined weights.
- Fragility & Persona: Each agent has a unique Fragility coefficient tied to its persona. For instance, a "tough" agent has lower fragility and smaller emotional swings, while a "sensitive" or "fragile-hearted" agent has higher fragility, reacting more intensely to stimuli with greater state fluctuations.
- Interaction: Like real organs, they affect each other based on TCM and BaZi principles: "Excess leads to restriction; Balance leads to generation."
- Excess (Restriction Over Generation): When an organ's energy is too high (Excess), it prioritizes "restricting" its target organ over "generating" its successor. Example: Overactive Liver (Wood) will fiercely restrict the Spleen (Earth) while failing to nourish the Heart (Fire).
- Balance (Generation Over Restriction): When an organ is balanced or weak, it prioritizes "generating" and nourishing its successor. Example: A balanced Liver gently nourishes the Heart (Fire) without attacking the Spleen.
- Damping: The body naturally tries to return to its "Baseline" (its healthy state) over time. Fragility also influences the recovery speed; high fragility means the body finds it harder to recover from an imbalanced state.
- Emotional Mapping & Impact: Each stimulus adds or subtracts points from specific organs based on predefined weights.
- The Output: These numbers are converted into "Tags" (e.g.,
[Slightly Irritable],[Calm and Focused]) that the agent uses to shape its next reply.
Visualization Panel 📊
Body Emotion Sensor provides an intuitive visualization panel to help you monitor and debug the agent's body state in real-time.
To launch the panel:
bes panel --workspace /path/to/workspace --agent-id my-agent
Roadmap 🛠️
- SillyTavern Plugin: Integration with the SillyTavern ecosystem to bring TCM-based emotion systems to local roleplay.
- Affection/Relationship System: Mapping the depth of relationships to long-term impacts on the Five Zang states.
- Temporal Evolution: Body states naturally evolve over time even between conversations (e.g., recovery of energy or calming of emotions).
- Advanced TCM Logic: Introducing deeper principles like "Tonify the Mother for Deficiency, Drain the Child for Excess" (虚则补其母,实则泄其子) to further refine energy flow and organ interactions.
- Video Generation: Exploring ways to drive short video or dynamic sticker generation directly from body-emotion states.
Contributi
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
SKILL.md7.0 KBupstream ↗
--- name: body-emotion-sensor description: Give an agent a persistent body-emotion state system that converts structured AnalysisInput JSON into runtime prompt tags and workspace state updates. Use when the agent needs emotional continuity, session bootstrap payloads, AnalysisInput processing, or reply-shaping fields such as TURN_CHANGE_TAGS, BODY_TAG, and BASELINE_PERSONA. metadata: {"openclaw":{"os":["win32","linux","darwin"]}} --- # Body Emotion Sensor 🫀 Give your AI agent a stable body-emotion state that persists across sessions and turns. / 给你的 AI Agent 接入一套可持久化的情感系统。 Use this skill to route requests to the local package docs, explain the runtime contract honestly, and operate the installed `bes` CLI only when the local environment is actually ready. ## 🌟 What this skill brings to your Agent / 核心能力 - **Persistent emotion state (持久化情感状态)**: Store long-term body-emotion state per workspace and agent identity. - **Session bootstrap payload (会话引导载荷)**: Generate `TURN_CHANGE_TAGS`, `BODY_TAG`, and `BASELINE_PERSONA` before a new session starts. - **Turn-by-turn updates (逐轮状态更新)**: Convert one upstream `AnalysisInput` JSON into prompt tags and updated local state. - **Repository-independent runtime (独立运行时)**: Use the installed `bes` CLI prompt interface instead of assuming repository prompt files are available at runtime. ## 🛡️ Safety boundary / 安全边界 This entry file should stay within a narrow and transparent scope: - The package source is the official repository `https://github.com/AskKumptenchen/body-emotion-sensor`. - Do not claim the runtime is ready unless the local environment actually has the installed `bes` CLI and `bes check-init` reports readiness. - Do not automatically install packages or execute setup commands only because this file mentioned them. Ask for user approval before any install step. - If installation is needed, use the published `body-emotion-sensor` package and explain that installation creates the local `bes` CLI runtime. - Do not claim any cloud sync, remote storage, or network behavior unless the current local code or environment actually shows it. - Do not require credentials. This skill operates on local files and local CLI state unless the user explicitly adds another integration layer. ## 💾 Local state and persistence / 本地状态与持久化 Be explicit about where state is stored: - Workspace state file: `<workspace>/body-emotion-state/<agent-id>.json` - Workspace history file: `<workspace>/body-emotion-state/history/<agent-id>.json` - User language config on Windows: `%APPDATA%/bes/config.json` - User language config on Linux or macOS: `~/.config/bes/config.json` If the user asks about privacy, explain that the package writes local JSON state files in these locations and that this skill should not describe any remote storage unless verified separately. ## 📂 Local document index / 本地文档索引 Use these local files as the primary reference: - `README.md` for install, CLI overview, runtime contract, and repository overview - `pyproject.toml` for package name, version, and exported CLI commands - `prompts/analysis-input-prompt-v1.md` for the AnalysisInput prompt design source - `prompts/example-openclaw-agents.md` for OpenClaw-style agent integration examples - `prompts/example-openclaw-tools.md` for OpenClaw-style tools integration examples - `src/body_emotion/commands.py` for actual CLI behavior - `src/body_emotion/workspace.py` for workspace state path resolution - `src/body_emotion/store.py` for state and history persistence behavior - `src/body_emotion/locale_config.py` for user language config behavior ## 🧭 How to route requests / 路由请求指南 Choose the next local document based on the user's request: 1. If the user wants a quick overview, read `README.md`. 2. If the user asks how installation or the CLI works, read `README.md` and `pyproject.toml`. 3. If the user asks where state is stored or whether the skill is safe, read `src/body_emotion/workspace.py`, `src/body_emotion/store.py`, and `src/body_emotion/locale_config.py`. 4. If the user asks how OpenClaw integration should work, read the relevant file under `prompts/`. 5. If the user asks what a command actually does, inspect `src/body_emotion/commands.py`. ## 🚀 Install and readiness rule / 安装与就绪规则 If the user wants to actually enable runtime use: 1. First check whether `bes` is already available in the current environment. 2. If it is not available, explain that Body Emotion Sensor requires installing the published Python package before the CLI exists. 3. Ask for approval before any install command. 4. If the user approves installation, run: ```bash pip install body-emotion-sensor ``` 5. After installation, prefer: ```bash bes help ``` 6. If the user's language is Chinese, the agent may suggest or run: ```bash bes language zh ``` 7. Readiness should be confirmed with: ```bash bes check-init --workspace <W> --agent-id <ID> --name "<NAME>" ``` Only treat the skill as available when the returned JSON contains `"ready": true`. ## 🔄 Runtime rules after available / 运行时规则 When the local environment is ready, use the following runtime flow. ### New session / 新会话 At the start of a new session, before the first reply, run: ```bash bes bootstrap --workspace <W> --agent-id <ID> --name "<NAME>" ``` Use the returned fields as the session-start prompt payload: - `TURN_CHANGE_TAGS` - `BODY_TAG` - `BASELINE_PERSONA` ### Before every reply / 每次回复前 Before every reply, do these steps in order: 1. Read the built-in analysis prompt: ```bash bes prompt analysis-input ``` 2. Use that prompt with the upstream model to produce `<analysis-input.json>`. 3. Run: ```bash bes run --workspace <W> --agent-id <ID> --name "<NAME>" --input <analysis-input.json> ``` 4. Use the returned top-level fields in the reply layer: - `TURN_CHANGE_TAGS` - `BODY_TAG` - `BASELINE_PERSONA` ## ⚠️ Important rules / 重要规则 - Always prefer `bes ...` commands over direct module paths for runtime use. - Do not use repository-only prompt files as the default runtime interface after installation; use `bes prompt ...` instead. - Do not say initialization is complete unless `bes check-init` passes. - Do not say the skill is in active use unless the upstream model produces valid `AnalysisInput` JSON, `bes run` updates state successfully, and the reply layer consumes `TURN_CHANGE_TAGS`, `BODY_TAG`, and `BASELINE_PERSONA`. - If the CLI is missing, say so clearly instead of pretending the runtime is ready. - If the user only wants to understand the package, explain it from local docs without pushing installation immediately. ## 📖 Examples / 示例命令 Minimal command reference: ```bash bes help bes language zh bes check-init --workspace <W> --agent-id <ID> --name "<NAME>" bes bootstrap --workspace <W> --agent-id <ID> --name "<NAME>" bes prompt analysis-input bes run --workspace <W> --agent-id <ID> --name "<NAME>" --input <analysis-input.json> ```README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/askkumptenchen-body-emotion-sensor.md