speak-human-tw
「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。
No outside reports on file
This tool is mainly a writing filter with low security risk if used locally, but it can unexpectedly change your text quality or accuracy, so always review its changes before publishing.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (Raymondhou0917/speak-human-tw)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/Raymondhou0917/speak-human-tw ↗
About Speak Human Tw
This is a rewriting tool for Traditional Chinese that removes AI-like patterns from text. It detects 38 types of AI writing markers (like repetitive phrases or formal structures) and replaces them with more natural human language. It also corrects simplified Chinese terms to Traditional Chinese and fixes punctuation.
Who it’s for
Developers and content creators who use Claude, Codex, or Cursor and want to make AI-generated Traditional Chinese text sound more naturally human. It's meant for people working with these specific AI coding tools.
Alternatives
- Traditional writing style guides and checklists for manual review
- Other text-rewriting tools like Hemingway Editor (English-focused)
- Language-specific linters or formatters for Chinese text (if available)
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README on GitHub for installation and integration instructions with your preferred code editor or AI tool.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.1k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-30).
Risks to watch for
- Text rewriting changes meaning: The tool modifies content automatically, which could alter your intended message or technical accuracy without your review.
- False positives on legitimate text: Natural human writing might get flagged and changed incorrectly, breaking your original voice.
- No security review shown: The tool's code quality and whether it safely processes sensitive content is unclear from public information.
- Local processing only: If integrated into an editor, it may need read access to all your open files and project folders.
- Chinese-language specific: Detection patterns for one language may not work reliably across mixed-language content.
How to lower the risk
Least-privilege permissions
- Only grant file access to the folders where you actually write content
- Disable auto-rewriting; always review changes manually before accepting them
Network isolation
- Verify it runs entirely offline on your machine
- Check that it doesn't send text to external servers for processing
Monitoring
- Keep a version history of your files so you can undo bad rewrites
- Test it on non-critical content first to see what it changes
Red flags to watch for
- Rewrites that change technical terms or code-related language
- Sudden changes to proper nouns or brand names in your text
Questions
How do I install Speak Human Tw?
Speak Human Tw does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/Raymondhou0917/speak-human-tw.
Are there security reports about Speak Human Tw?
No reports found for this package in our research (last checked 2026-10-30). Speak Human Tw currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include text rewriting changes meaning, false positives on legitimate text, no security review shown.
Is Speak Human Tw actively maintained?
Speak Human Tw has 1.1k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/Raymondhou0917/speak-human-tw before pinning it in production.
What are alternatives to Speak Human Tw?
Compare Speak Human Tw side by side with similar skills in the Related tools section on this page, or browse all skills on AgentArmorHQ.
README badge and team notes
Maintain or use Speak Human Tw? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/raymondhou0917-speak-human-tw)HTML embed:
<a href="https://agentarmorhq.com/skills/raymondhou0917-speak-human-tw"><img src="https://agentarmorhq.com/api/badge/raymondhou0917-speak-human-tw" alt="AgentArmorHQ Risk Grade for Speak Human Tw" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "raymondhou0917-speak-human-tw"Share with your security lead
Need sign-off to use speak-human-tw? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: speak-human-tw
- **Listing URL:** https://agentarmorhq.com/skills/raymondhou0917-speak-human-tw
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.1k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (Raymondhou0917/speak-human-tw)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/Raymondhou0917/speak-human-tw
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- Raymondhou0917
- Source code
- github.com/Raymondhou0917/speak-human-tw
- Est. context load
- ~50 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 1.1k GitHub stars
- Last updated
- 2026-10-29
- Last graded
- 2026-10-23
Community
Discussions for Speak Human Tw
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude