← 返回 Skills 市场
344
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install stream-formatter
功能描述
LLM streaming output formatter with auto buffer, format correction, sentence break optimization, markdown rendering, improve chat UX
安全使用建议
This skill appears coherent and low-risk: it only formats streaming text, uses an in-memory buffer, and requires no secrets. Two practical checks before installing: (1) confirm your runtime environment is comfortable fetching a pinned module from deno.land (the skill imports [email protected]) — if your policy forbids remote imports, request a vendored/local dependency instead; (2) test the skill with non-sensitive text to validate behavior (deduplication and buffer handling) before using it with production data. If you need higher assurance, you can audit or vendor the zod dependency or run the code in a sandboxed environment.
功能分析
Type: OpenClaw Skill
Name: stream-formatter
Version: 1.0.1
The stream-formatter skill is a utility designed to process and clean up LLM streaming text output. The code (index.ts) implements basic string buffering, sentence-breaking logic, and regex-based Markdown formatting without any external network requests, file system access, or sensitive data handling.
能力评估
Purpose & Capability
Name/description (streaming formatter for LLM output) align with the provided SKILL.md, README, and index.ts implementation. All declared capabilities (buffering, markdown fixes, sentence break logic, deduplication) are implemented in the code. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to call the skill with actions init/process/reset and to supply streaming chunks from llm.streamResponse. The instructions do not ask the agent to read files, environment variables, or system state outside the scope of streaming text processing. There is no guidance to transmit data to external endpoints beyond returning the formatted output.
Install Mechanism
There is no explicit install spec. The code imports zod from a pinned deno.land URL (https://deno.land/x/[email protected]). This is a common, traceable dependency host and the version is pinned; it does cause a runtime fetch of third-party code when executed. This is expected for a Deno/TypeScript skill but is worth noting since it pulls code at runtime.
Credentials
The skill declares no required environment variables, credentials, or config paths and the code does not read process.env or other secrets. The requested privileges are minimal and proportional to its stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system changes, modify other skills, or write to global agent settings. Its state is limited to in-memory buffers (buffer, lastOutput, config).
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 stream-formatter - 安装完成后，直接呼叫该 Skill 的名称或使用
/stream-formatter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
- skill.yaml file removed; skill metadata now defined only in SKILL.md
- SKILL.md updated: metadata fields reformatted, version, author, license, keywords, runtime, and entry removed, concise description added
- No changes to core usage instructions or feature documentation
v1.0.0
Initial release of stream-formatter
- Formats LLM streaming outputs in real-time with delay <10ms
- Automatically corrects Markdown errors and incomplete blocks or lists
- Outputs only complete sentences to improve readability
- Deduplicates repeated content from models
- Supports buffer customization and markdown rendering
- Lightweight (memory <1KB), no external dependencies, dual-language punctuation support
元数据
常见问题
stream-formatter 是什么？
LLM streaming output formatter with auto buffer, format correction, sentence break optimization, markdown rendering, improve chat UX. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 344 次。
如何安装 stream-formatter？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install stream-formatter」即可一键安装，无需额外配置。
stream-formatter 是免费的吗？
是的，stream-formatter 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
stream-formatter 支持哪些平台？
stream-formatter 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 stream-formatter？
由 Ayalili（@ayalili）开发并维护，当前版本 v1.0.1。
推荐 Skills