← 返回 Skills 市场
Tweet Humanizer
作者
Nissan Dookeran
· GitHub ↗
· v1.0.1
· MIT-0
365
总下载
1
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install tweet-humanizer
功能描述
Detect and fix AI-generated tweet patterns to make tweets sound like a real human typed them. Covers cadence uniformity, punchline addiction, missing casual...
安全使用建议
This skill appears coherent and low-risk: it only contains instructions for rewriting tweets and requests no credentials or installs. Before using it in production, test it with non-sensitive tweets to confirm it preserves hashtags and brand voice as promised. If provenance matters, verify the GitHub repo linked inside SKILL.md (the registry metadata initially showed no homepage) and confirm the author/ownership. Even though the skill cannot access your system or secrets, avoid passing private or sensitive content to any third-party skill and consider restricting autonomous invocation if you want to prevent the agent from calling this skill without explicit prompts.
功能分析
Type: OpenClaw Skill
Name: tweet-humanizer
Version: 1.0.1
The skill bundle consists of markdown instructions (SKILL.md) designed to guide an AI agent in rewriting tweets to sound more human. It contains no executable code, requests no sensitive permissions, and explicitly disables outbound network access in its metadata. The instructions are entirely consistent with the stated purpose of social media content auditing.
能力评估
Purpose & Capability
Name/description (tweet humanizer) match the SKILL.md runtime instructions: scan for AI tweet patterns and rewrite tweets to sound more human. The skill declares no binaries, env vars, or installs — which is proportionate for a text-only QA/rewrite utility.
Instruction Scope
SKILL.md provides explicit, bounded instructions (identify listed AI patterns, rewrite while preserving voice and hashtags, keep ≤280 chars). It does not instruct the agent to read system files, access credentials, or send data to external endpoints. It references internal playbooks (file paths) for voice guidance, but does not require reading them; that is a minor documentation reference rather than scope creep.
Install Mechanism
No install spec and no code files — this is an instruction-only skill. Nothing will be downloaded or written to disk by an installer.
Credentials
The skill declares no required env vars, credentials, or config paths. The instructions do not reference environment secrets or external service keys. The requested environment access is minimal and appropriate for the stated task.
Persistence & Privilege
Flags show always:false and normal model-invocation allowed (disable-model-invocation:false) — this is the platform default and appropriate for a user-invocable text-processing skill. No requests to modify other skills or agent-wide settings.
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 tweet-humanizer - 安装完成后，直接呼叫该 Skill 的名称或使用
/tweet-humanizer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
v1.0.1
Frontmatter fix: added metadata.openclaw block, network flag, cleaned up bins list
v1.0.0
Initial release of tweet-humanizer.
- Detects and fixes common AI tweet patterns (e.g., punchline addiction, uniform cadence, missing casual markers, over-polished phrasing)
- Supports single tweets or batches, applying specific batch variation rules
- Preserves author’s tone and user-specified hashtags
- Ensures tweets stay within 280 characters, trimming only as needed
- Returns original and rewritten versions with detected pattern flags
元数据
常见问题
Tweet Humanizer 是什么？
Detect and fix AI-generated tweet patterns to make tweets sound like a real human typed them. Covers cadence uniformity, punchline addiction, missing casual... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 365 次。
如何安装 Tweet Humanizer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install tweet-humanizer」即可一键安装，无需额外配置。
Tweet Humanizer 是免费的吗？
是的，Tweet Humanizer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Tweet Humanizer 支持哪些平台？
Tweet Humanizer 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 Tweet Humanizer？
由 Nissan Dookeran（@nissan）开发并维护，当前版本 v1.0.1。
推荐 Skills