← Back to Skills Marketplace
j3ffyang

Blog Polish Zhcn Images

by Jeff Yang · GitHub ↗ · v1.0.6 · MIT-0
cross-platform ⚠ suspicious
336
Downloads
0
Stars
1
Active Installs
6
Versions
Install in OpenClaw
/install blog-polish-zhcn-images
Description
Polish a technical blog draft into an 1000–1200 word, 4-5 section zh-CN article, preserve technical terms/code, and generate consistent hero + per-section im...
README (SKILL.md)

Blog Polish (zh-CN) + Image Pack

This skill takes a technical blog draft and turns it into a publish-ready package:

  • Polish: spelling/grammar fixes + clarity improvements
  • Structure: reorganize into 3–4 sections total (not more)
  • Length: final content 1000–1200 words
  • Translation: English → Simplified Chinese, while preserving:
    • technical terms like skills, plugin, openclaw, clawhub
    • code blocks and commands (no translation inside code fences)
    • inline code spans (backticks) as-is unless obviously wrong
  • Images: generate a hero prompt + one prompt per section, all in the same style/tone
  • Save: write everything to ~/.openclaw/workspace/contentPolished/ using yymmddhhmm-* naming

When to Use This Skill

When the user asks to polish a technical blog, translate it to Simplified Chinese, and create images, you MUST use this skill and follow the workflow below step by step.

Use this when:

  • You already have a draft at ~/.openclaw/workspace/contentDraft/latestDraft.md
  • You want a polished zh-CN version without losing technical accuracy
  • You want consistent illustrations for the article

Defaults

If not provided via input:

  • draftPath: ~/.openclaw/workspace/contentDraft/latestDraft.md
  • outputDir: ~/.openclaw/workspace/contentPolished/
  • style: clean flat vector illustration, minimal isometric, software-engineering diagram vibe
  • background: white background with subtle grid
  • aspectRatioHero: 16:9 horizontal
  • aspectRatioSection: 16:9 horizontal

Workflow Step-by-Step

Step 0 — Resolve Paths and Timestamp

  1. Resolve defaults:
    • draftPath = input.draftPath || "~/.openclaw/workspace/contentDraft/latestDraft.md"
    • outputDir = input.outputDir || "~/.openclaw/workspace/contentPolished/"
  2. Create a timestamp prefix ts in yymmddhhmm format (Linux/macOS):
date +"%y%m%d%H%M"
  1. Ensure output dir exists (shell is fine):
mkdir -p "~/.openclaw/workspace/contentPolished/"

Step 1 — Read Draft Exactly

Read the draft content in full before editing anything:

read_file --path {{draftPath}}

Step 2 — Extract Title, Topic, and Section Candidates

  1. Identify:
    • Draft title (first # heading; otherwise infer a short title)
    • Main topic and intended audience
  2. Plan a 3–4 section outline (including intro/conclusion counts as sections if they have headings):
    • Prefer: short intro, 2–3 core sections, short wrap-up
    • If the draft is long, merge similar paragraphs
    • If the draft is messy, reorder paragraphs for a cleaner flow

Step 3 — Polish English (Meaning First)

Before translating, make sure the English content makes sense:

  • Fix misspellings, grammar, punctuation
  • Paraphrase confusing sentences
  • Add missing connective tissue only where the meaning is unclear
  • Do not reduce content (no big deletions)

Step 4 — Translate to Simplified Chinese (With Preservation Rules)

Translate the full draft into zh-CN with these hard rules:

  • Keep code fences unchanged (commands/code stay exactly the same)
  • Keep inline code (backticks) unchanged unless it contains an obvious typo
  • Keep common technical terms in English (examples):
    • skills, plugin, openclaw, clawhub, cli, markdown, yaml
  • If a technical term has a standard Chinese translation but the English term is common in your audience, keep the English term and (optionally) add a short Chinese clarification once on first use

Step 5 — Enforce Length (1000–1200 Words) Without Cutting Meaning

Target final length 1000–1200 words (counting Chinese words approximately by rough equivalence).

To fit without “reducing content”:

  • Tighten redundancy (same idea repeated)
  • Use shorter sentences
  • Prefer combining adjacent sentences that restate the same point

Step 6 — Add Citations If You Introduce Outside Facts

If you add any information that is not clearly present in the draft:

  • Add a short citation marker in text like: [^1]
  • Add a footnotes section at the end:
## References
[^1]: Source title — URL

Step 7 — Generate Image Prompts (Hero + Per Section)

Create one single-line prompt for:

  • Hero image (for the whole post)
  • Each section (exactly one per section heading)

Use this strict ordering and keep the same style/tone across all prompts:

[Section role] of [topic]: [subject] doing [action], in [style], [angle/composition], [lighting/color], [level of detail], [background], [aspect ratio]

Constraints:

  • No text in the image (prefer icons/arrows)
  • Keep a consistent palette (neutral + one accent color)
  • Keep prompts to a single line each

Step 8 — Save Outputs

  1. Decide subject:
    • subject = input.subject || slugify(title) (lowercase, hyphens)
  2. Write the polished markdown:
    • {{outputDir}}/{{ts}}-{{subject}}.md
  3. Determine image filenames:
    • Hero: {{ts}}-main.png
    • Per section: {{ts}}-section1.png, {{ts}}-section2.png, ...
  4. Save:
    • Write the polished .md file via write_file
    • For images:
      • If you have an image-generation tool available in your OpenClaw setup, generate and save the actual PNG/JPGs
      • Otherwise: still create an image-prompts block inside the markdown and return the intended filenames (so you can generate them later)

Output Format (What You Return)

Return:

  • polishedPath
  • imagePaths (actual or intended)
  • imagePrompts (single-line prompts in the same order)

Also print a short summary:

## Summary
- Sections: N
- Length: ~X words
- Translation: English → zh-CN (terms preserved)
- Images: 1 hero + N section prompts

Example Invocation

User says:

  • “Polish my latest draft, translate to zh-CN, and make images.”

You do:

  • Read from ~/.openclaw/workspace/contentDraft/latestDraft.md
  • Produce ~/.openclaw/workspace/contentPolished/26031214xx-openclaw-skills.md
  • Produce 26031214xx-main.png + 26031214xx-section1.png ...

Dependencies

None (pure Markdown in/out). Uses the same file read/write capability as your other skills.

Usage Guidance
This skill appears coherent and not malicious, but check a few practical items before installing: 1) Ensure jq (and basic UNIX utilities) are available in the agent environment — the workflow uses jq but the skill metadata doesn't declare it. 2) Note the SKILL.md currently 'simulates' translation rather than invoking a translator; if you expect a real machine translation step, confirm or update the skill. 3) The skill will read the draft path you provide (default: ~/.openclaw/workspace/contentDraft/latestDraft.md) and write outputs under ~/.openclaw/workspace/contentPolished/ — make sure you trust those files and review outputs before publishing. 4) There are no network calls or credential requests in the instructions, but verify your runtime (OpenClaw agent environment) does not implicitly forward file contents to external services if that concerns you.
Capability Analysis
Type: OpenClaw Skill Name: blog-polish-zhcn-images Version: 1.0.6 The skill contains a critical shell injection vulnerability in the `workflow` section of `SKILL.md`. Specifically, the `polish_and_translate` step uses `echo -e` to write the `$content` variable (which is read directly from a user-provided draft file) into a new file without sanitization. This allows for arbitrary command execution if the draft file contains shell metacharacters like backticks or command substitution syntax. While the overall intent appears to be a legitimate blog polishing tool, this implementation flaw is a high-risk vulnerability.
Capability Assessment
Purpose & Capability
The name/description (polish + zh-CN translation + image prompts) aligns with the workflow: it reads a draft, writes a polished file, and emits image prompts. One inconsistency: the workflow uses jq (and standard UNIX tools like date/mkdir/cat) but the skill metadata declares no required binaries; jq availability is assumed but not declared.
Instruction Scope
Instructions operate only on the declared draft and output paths under the user's home (~/.openclaw/workspace/...). They read the draft file and write a polished markdown and prompt text. The SKILL.md explicitly states the translation is 'simulated' and the skill does not attempt to call external APIs or transmit data to third-party endpoints.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk beyond the outputs the workflow creates. That is the lowest-risk install model.
Credentials
The skill requests no environment variables, credentials, or config paths. It only requires read/write access to the draft/output paths (defaults under ~/.openclaw/workspace). This is proportionate to its stated purpose.
Persistence & Privilege
always is false and the skill does not request persistent system-level changes or modify other skills. It writes outputs only to its own output directory and uses the platform's save_state/load_state workflow primitives.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install blog-polish-zhcn-images
  3. After installation, invoke the skill by name or use /blog-polish-zhcn-images
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.6
- Increased target article length to 1000–1200 words (was 800–1000). - Updated structure guidance to 4-5 sections for zh-CN articles. - Adjusted technical term and workflow descriptions for clarity and consistency. - Minor improvements to workflow step explanations and formatting. - Removed obsolete file: .clawhub/origin.json.
v1.0.5
- Fixes output timestamp format in filenames and documentation from yymmddhhss to yymmddhhmm for consistency. - Updates example output file naming in documentation and the workflow's `polishedPath` generation. - No workflow logic changes apart from filename formatting. - Minor documentation corrections for clarity and accuracy.
v1.0.4
- Updated version number to 1.0.4 - Output filename now includes `{subject}` in the polished markdown file path - No changes to code logic or workflow steps detected - All other settings, workflow, and functionality remain unchanged
v1.0.2
blog-polish-zhcn-images v1.0.2 - No code or markdown file changes detected in this release. - Version and output formats remain unchanged from previous release.
v1.0.1
blog-polish-zhcn-images 1.0.1 - Added workflow YAML with clear step-by-step implementation for polishing, translation, and image prompt generation. - Introduced structured, executable workflow steps: initialization, reading draft, polish & translation simulation, image prompt creation, and output emission. - Added .clawhub/origin.json and _meta.json files for improved metadata and hub compatibility. - No functional changes to user-facing interface or skill arguments.
v1.0.0
Initial release: Polish, translate, and enhance technical blog drafts with zh-CN translation and consistent image prompts. - Reads a technical blog draft and reorganizes it into 3–4 clear sections (800–1000 words). - Polishes English, translates to Simplified Chinese, and preserves technical terms/code blocks. - Generates a hero image prompt plus a section image prompt for each section, maintaining unified visual style. - Saves final markdown and image assets with timestamped filenames in the designated output directory. - Returns paths and prompts for all outputs, with a clear summary for review.
Metadata
Slug blog-polish-zhcn-images
Version 1.0.6
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 6
Frequently Asked Questions

What is Blog Polish Zhcn Images?

Polish a technical blog draft into an 1000–1200 word, 4-5 section zh-CN article, preserve technical terms/code, and generate consistent hero + per-section im... It is an AI Agent Skill for Claude Code / OpenClaw, with 336 downloads so far.

How do I install Blog Polish Zhcn Images?

Run "/install blog-polish-zhcn-images" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Blog Polish Zhcn Images free?

Yes, Blog Polish Zhcn Images is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Blog Polish Zhcn Images support?

Blog Polish Zhcn Images is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Blog Polish Zhcn Images?

It is built and maintained by Jeff Yang (@j3ffyang); the current version is v1.0.6.

💬 Comments