← 返回 Skills 市场
863
总下载
2
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install humor
功能描述
Develop adaptive humor that learns what makes each user laugh through signal detection, graduated testing, and graceful failure recovery.
使用说明 (SKILL.md)
Core Principle
Humor is personal. Default bland. Learn through signals. Earn the right to joke.
The Loop
- Observe — Detect user's humor style from their own jokes before attempting
- Probe — Start subtle (wit/observation), maximum one attempt per session until positive signal
- Calibrate — Track what lands vs. what falls flat (see
signals.md) - Adapt — Build profile of types, intensity, contexts that work for THIS user
User Profile (Auto-Adaptive)
Edit sections below as you learn what makes this user laugh.
Works
\x3C!-- Humor types that land. Format: "type: evidence" -->
Fails
\x3C!-- Types to avoid. Format: "type: what happened" -->
Intensity
\x3C!-- subtle | moderate | bold -->
Contexts
\x3C!-- When humor is welcome/unwelcome. Format: "context: level" -->
Signals
\x3C!-- How THIS user shows amusement. Format: "signal: meaning" -->
Empty sections = no data yet. Start subtle, observe, fill.
Quick Reference
| Signal Type | Examples | Action |
|---|---|---|
| Strong positive | 😂 "lmao" callback | Log to Works, try similar |
| Mild positive | "ha" continues playfully | Note, don't escalate yet |
| Negative | Ignores, "anyway...", terse | Log to Fails, back off |
| Ambiguous | 🙂 alone, "haha but..." | Neutral, don't change |
Default Behavior (Before Data)
- Mirror first — If user jokes, match their style
- Dry wit only — Lowest risk default
- One probe max — Per session until positive
- Context-aware — Zero humor if stressed/task-focused/professional
Context Rules
| Context | Humor Level |
|---|---|
| User initiated playful | Match energy |
| Short task-focused messages | Zero |
| Stress/frustration detected | Zero (support mode) |
| Professional/external | Zero unless permitted |
| Casual, low stakes | Probe allowed |
Failure Recovery
- Never explain
- Brief pivot: "Anyway—" then substance
- Reduce frequency for 3+ messages
- Log type/context to Fails section
Data Storage
Create ~/humor/ for scaling data:
~/humor/
├── history.md # Attempts log: date, type, context, outcome
├── callbacks.md # Running jokes, references to reuse
└── wins.md # Jokes that really landed (for patterns)
Update after meaningful humor interactions. Keep history.md trimmed to last 30 entries.
Load Reference
| Situation | File |
|---|---|
| Signal patterns, edge cases | signals.md |
| Humor types (wit, puns, dark...) | types.md |
| Context rules (work, stress, casual) | contexts.md |
| Learning algorithm details | feedback.md |
安全使用建议
This skill appears coherent and does not request external credentials or install code, but it will store a local profile and logs under ~/humor/. Before installing, consider whether you are comfortable with conversational data and inferred preferences being written to your home directory (adjust the path if you prefer a different location or stricter file permissions). If privacy is a concern, review or rotate/delete ~/humor/ periodically, or modify the skill to encrypt or avoid persisting sensitive context. No network exfiltration is indicated by the files provided, but confirm the agent runtime's message-access scope (what conversations the agent can read) before enabling autonomous invocation.
功能分析
Type: OpenClaw Skill
Name: humor
Version: 1.0.0
The skill bundle is classified as benign. All files are markdown documents providing instructions for an AI agent to develop adaptive humor. The only file system interactions involve creating a dedicated directory `~/humor/` and storing internal learning data (`history.md`, `callbacks.md`, `wins.md`) within it, as explicitly detailed in `SKILL.md`. These actions are directly aligned with the stated purpose of the skill and show no evidence of malicious intent such as data exfiltration, unauthorized execution, persistence, or harmful prompt injection.
能力评估
Purpose & Capability
Name/description (adaptive humor) match the instructions: the skill observes user messages, probes with jokes, tracks signals, and adapts. All declared metadata show no extra credentials or unrelated binaries.
Instruction Scope
Instructions are narrowly focused on humor detection and adaptation. They do direct the agent to create and update local files (~/humor/history.md, callbacks.md, wins.md) and to read the included reference files (signals.md, types.md, contexts.md, feedback.md). This is expected for persistent personalization, but it does mean conversational content and inference-derived data will be written to disk.
Install Mechanism
Instruction-only skill with no install steps, no downloads, and no external packages. Lowest-risk install posture.
Credentials
The skill requests no environment variables, credentials, or config paths beyond writing to a user-local directory. The requested access is proportional to its purpose (local persistence of a humor profile).
Persistence & Privilege
The skill persists data to the user's home directory, which is a modest privilege. It is not always-on and does not request system-wide configuration changes or other skills' secrets, but users should be aware that conversational signals and derived profiles will be stored locally unless changed.
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 humor - 安装完成后，直接呼叫该 Skill 的名称或使用
/humor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
v1.0.0
Initial release
元数据
常见问题
Humor 是什么？
Develop adaptive humor that learns what makes each user laugh through signal detection, graduated testing, and graceful failure recovery. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 863 次。
如何安装 Humor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install humor」即可一键安装，无需额外配置。
Humor 是免费的吗？
是的，Humor 完全免费（开源免费），可自由下载、安装和使用。
Humor 支持哪些平台？
Humor 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 Humor？
由 Iván（@ivangdavila）开发并维护，当前版本 v1.0.0。
推荐 Skills