← 返回 Skills 市场
j3ffyang

blog-polish-zhcn

作者 Jeff Yang · GitHub ↗ · v1.0.13 · MIT-0
cross-platform ✓ 安全检测通过
321
总下载
0
收藏
1
当前安装
7
版本数
在 OpenClaw 中安装
/install blog-polish-zhcn
功能描述
Polish and translate a technical blog draft into a 1200–1400 word, 4-5 section Markdown article in Simplified Chinese (zh-CN), preserving technical terms and...
使用说明 (SKILL.md)

Blog Polish (zh-CN)

This skill polishes a technical blog draft and translates it to Simplified Chinese while preserving technical accuracy.

When to Use

Use when the user asks to polish/translate a technical blog draft to zh-CN without images. Triggers: "polish my draft", "translate blog to Chinese", "enhance latestDraft.md".

Defaults

  • draftPath: ~/.openclaw/workspace/contentDraft/latestDraft.md
  • outputDir: ~/.openclaw/workspace/contentPolished/
  • Output filename: ${ts}_${titleSlug}.md

Workflow Summary

  1. Resolve paths + create timestamp (date +"%y%m%d%H%M")
  2. Read draft from draftPath
  3. Polish English: Fix grammar/spelling, improve clarity, structure into 4-5 sections, target 1000-1200 words
  4. Translate to zh-CN: Preserve code blocks, inline code, technical terms (openclaw, skill, cli)
  5. Save polished markdown to ${outputDir}/${ts}_${titleSlug}.md
  6. Return: { outputPath: "/full/path/to/file.md" }

Output

The skill returns a JSON object with a single property:

  • outputPath: path to the generated polished article.

Example

Input: ~/.openclaw/workspace/contentDraft/latestDraft.md
Example Output

{ "outputPath": "~/.openclaw/workspace/contentPolished/2603142134-openclawSkills.md" }
安全使用建议
This skill appears to do what it says: read a single markdown draft, send it to the platform LLM to be polished and translated, then save the result. Before installing or running it: 1) Confirm whether your environment has 'jq' installed (SKILL.md lists jq as required); if not, either install jq or update the skill/finalize step. 2) Verify the draftPath and outputDir defaults point only to locations you expect (avoid pointing draftPath at sensitive files). 3) Remember that the 'llm: true' step will transmit the draft text to whatever model/provider your OpenClaw agent is configured to use — do not use this skill on content you do not want sent to that model. 4) Consider resolving the word-count inconsistency (1200–1400 vs 1000–1200) so outputs meet your expectations.
功能分析
Type: OpenClaw Skill Name: blog-polish-zhcn Version: 1.0.13 The skill is designed to polish and translate technical blog drafts into Simplified Chinese. The workflow in SKILL.md uses standard shell commands (cat, mkdir, printf, jq) and LLM processing to handle files within a designated workspace (~/.openclaw/workspace/). There are no indicators of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
The skill's stated purpose (polish and translate a markdown draft to Simplified Chinese) matches what the workflow does: it reads a draft file, sends the text to the platform LLM step, and writes a polished markdown file. Minor inconsistencies exist in the metadata: SKILL.md lists jq as a required tool in its internal metadata, but the registry-level 'Required binaries' field was empty. Also the description says 1200–1400 words while the workflow summary mentions 1000–1200 words — clarify desired target.
Instruction Scope
Runtime instructions only read the specified draftPath and write the polished file to outputDir, which is appropriate. The workflow uses an 'llm: true' step — the draft text will be sent to the configured LLM provider for processing, so any sensitive content in the draft will be transmitted according to your platform's model provider settings. The skill does not instruct reading other files or environment variables.
Install Mechanism
There is no install spec and no code files (instruction-only), so nothing is written to disk beyond the output file the skill creates. This is low-risk. Note: SKILL.md's embedded metadata declares a dependency on 'jq' but there is no install step to fetch it; the platform should already provide jq or the finalize step will fail.
Credentials
The skill requests no environment variables or credentials. It reads a user-specified file path (defaulting to a workspace path) and writes to a user-specified output directory — these are proportionate to the task. Users should ensure the draftPath points only to the intended draft (don’t point it at sensitive system files).
Persistence & Privilege
The skill does not request persistent/always-on privileges (always: false). It uses save_state/load_state calls to store transient workflow state (timestamp, paths, titleSlug), which is normal for a skill run and limited in scope.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install blog-polish-zhcn
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /blog-polish-zhcn 触发
  4. 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
v1.0.13
- Increased target article length to 1200–1400 words. - Output filename now includes a title slug for better clarity (e.g., `${ts}_${titleSlug}.md`). - Improved workflow: extracts a slugified title and separates file writing from content generation. - Updated metadata for schema version 1.1. - Removed unnecessary files to streamline the skill directory.
v1.0.12
blog-polish-zhcn 1.0.12 - Initial version of the zh-CN specific blog polish skill. - Polishes and translates a technical blog draft to Simplified Chinese (zh-CN), preserving technical terms and code blocks. - Provides a simplified workflow focused on Chinese output (no Astro/English output). - Adds metadata and documentation tailored for Chinese blog polishing and translation use cases.
v1.0.11
- Fixed output directory variable to expand environment variables correctly in workflows. - Version bump to 1.0.11. - No changes to features, workflow, or outputs.
v1.0.10
- Major update: The skill now supports polishing and translating technical blog drafts into both English and Simplified Chinese, and outputs an Astro markdown compatible version. - Adds workflow steps for generating an Astro-compatible slug, preparing Astro frontmatter, and creating both English and Chinese outputs. - Output now includes separate English, Simplified Chinese, and Astro markdown paths. - New documentation files added for multilingual and Astro markdown support.
v1.0.9
- Changed timestamp format in the workflow from `%Y%m%d%H%M` to `%y%m%d%H%M` for output filenames. - No other changes detected.
v1.0.8
- Added entrypoint metadata field for improved integration and skill discovery. - Fixed init step to ensure proper date formatting and state saving. - Added set_output: outputPath to polish_and_translate step for consistent output handling. - Version bump to 1.0.8.
v1.0.7
Initial release of blog-polish-zhcn: - Polishes and translates technical blog drafts into Simplified Chinese (zh-CN) Markdown articles (1000–1200 words, 4–5 sections). - Preserves technical terms and code blocks. - Supports default draft and output paths; outputs polished file path. - Designed for technical content enhancement and translation workflows.
元数据
Slug blog-polish-zhcn
版本 1.0.13
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 7
常见问题

blog-polish-zhcn 是什么?

Polish and translate a technical blog draft into a 1200–1400 word, 4-5 section Markdown article in Simplified Chinese (zh-CN), preserving technical terms and... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 321 次。

如何安装 blog-polish-zhcn?

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

blog-polish-zhcn 是免费的吗?

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

blog-polish-zhcn 支持哪些平台?

blog-polish-zhcn 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 blog-polish-zhcn?

由 Jeff Yang(@j3ffyang)开发并维护,当前版本 v1.0.13。

💬 留言讨论