Star200+

Speak Human Tw

STRONG · 88
Community indexed

「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。

Downloads0
Stars691
Version1.0.0
Quality100/100 · Excellent
Trust88/100 · Review then install
Audit95/100 · Safe to try

Supply asset profile

Coding and developer agents

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

Browse track

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agent fit

Claude Code + OpenAI Agents + Cursor

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add Raymondhou0917/speak-human-tw

Maintenance

fresh

4d since push

Risk

Safe to try

No major risk signals from available metadata

GitHub quality

691

100/100 quality · 91/100 trust

Coverage tags

CodingGitHub automationutilitytraditional-chineseai-detox

Review notes

No major risk signals from available metadata

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Excellent
100

High-confidence pick with strong adoption and healthy maintenance signals.

Trust

Review then install
88

Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.

Audit

Safe to try
95

Install readiness, security metadata, maintenance, and adoption risk.

Trust Score v5

Agent install candidate

Use as the primary candidate after human or sandbox review.

PythonCodexClaude CodeCursorOpenAgentSkill CLI

Stars

691 GitHub stars

Repo activity

691 stars, 79 forks

Maintenance

4d since push

License

MIT

Install

npx skills add Raymondhou0917/speak-human-tw

Install safety

standard package or runtime install path

Permission surface

no high-risk permission surface in public metadata

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Low metadata risk

  • No major trust warnings detected from available metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • GitHub automation workflows
  • Claude Code teams
  • teams that value GitHub adoption signals
  • Inspect repository metadata

Suited agents

PythonCodexClaude CodeCursorOpenAgentSkill CLIOpenAI AgentsCLI

Install decision

Command
npx skills add Raymondhou0917/speak-human-tw
Policy
allow
Human review
no

Trust and risk

Trust
88/100
Audit
95/100
Risk level
Safe to try

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add Raymondhou0917/speak-human-tw
Public auditEval reportResolve APIInstall handoff

Do not use when

  • teams that need a vendor-supported SLA
  • high-compliance environments without internal security review
  • No major risk signals from current metadata
  • No major trust warnings detected from available metadata
  • Production credentials, payments, or irreversible account changes without explicit human review

Alternative

Claude Scientific Skills

31.2K stars

npx skills add K-Dense-AI/claude-scientific-skills

Alternative

Awesome Claude Skills

65.9K stars

npx skills add ComposioHQ/awesome-claude-skills

Alternative

Khazix Skills

17.8K stars

npx skills add KKKKhazix/khazix-skills

Agent safety v2

87/100 · Safe to install with normal review

Verifiedallow

Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Resolve via API

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

Install targets

Install this skill in your agent workflow

Copy the registry command or an agent-specific install prompt for Codex, Claude Code, and Cursor.

skill install

OpenAgentSkill CLI

Use the registry command when your workflow supports the OpenAgentSkill installer.

$ npx skills add Raymondhou0917/speak-human-tw

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Resolve JSON

/api/agent/resolve?task=Use%20Speak%20Human%20Tw%20for%20an%20agent%20workflow&agent=codex&max_risk=medium

Resolve text

/api/agent/resolve?task=Use%20Speak%20Human%20Tw%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text

Install handoff

/api/skills/raymondhou0917-speak-human-tw/install

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use Speak Human Tw in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Speak%20Human%20Tw%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/raymondhou0917-speak-human-tw/install
Install command: npx skills add Raymondhou0917/speak-human-tw
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Install handoff

/api/skills/raymondhou0917-speak-human-tw/install

LLM text format

/api/skills/raymondhou0917-speak-human-tw/install?format=text

Find alternatives

/api/skills/search?q=Speak%20Human%20Tw&limit=3

Agent prompt

Use Speak Human Tw for this task. Review https://www.openagentskill.com/api/skills/raymondhou0917-speak-human-tw/install, then install with: npx skills add Raymondhou0917/speak-human-tw

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Manifest

/api/registry/manifest/raymondhou0917-speak-human-tw

LLM text

/api/registry/manifest/raymondhou0917-speak-human-tw?format=text

Install alias

/api/registry/install/raymondhou0917-speak-human-tw

Recommend

/api/registry/recommend?task=Use%20Speak%20Human%20Tw%20in%20an%20agent%20workflow&limit=3

Agent fit

100/100

GitHub automation

Use-case tags

GitHub automationContent automationCoding agents

Platforms

Python, Claude Code, OpenAI Agents, Cursor

Audit report

Safe to try · 95/100

Review install readiness, maintenance, trust, quality, and metadata warnings before adding this skill to an agent workflow.

View audit reportView eval report

Agent decision cockpit

Primary pick for GitHub automation

Use this as a leading candidate, then validate the README and install path in your own agent stack.

100
Readiness
Adopt
Stage

Role in stack

Primary pick

Primary fit

GitHub automation

Trust label

Production-ready

Install path

Command ready

Use when

  • GitHub automation workflows
  • Claude Code teams
  • teams that value GitHub adoption signals

Evidence

  • 691 GitHub stars
  • recent repository activity
  • install command or GitHub repo available
  • 100/100 quality profile
  • 1 OpenAgentSkill engagement events

Review first

  • No major risk signals from current metadata

Implementation path

  1. 1Install it in a sandbox agent and run one GitHub automation task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Review then install

Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.

88
Trust score

GitHub adoption

INFO

691 GitHub stars

Stars/forks activity

INFO

691 stars, 79 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

4d since push

License clarity

PASS

MIT

Good signals

  • Manually verified listing
  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Meaningful GitHub adoption signal
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Use as the primary candidate after human or sandbox review.

Quality profile

Excellent candidate for agent workflows

High-confidence pick with strong adoption and healthy maintenance signals.

100
GitHub stars
691
Freshness
4d ago
Install ready
Yes
License
MIT

Workflow fit

Use this skill in these scenarios

Manage repositories

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Publish consistently

Content automation

I need my agent to turn research and product updates into useful content drafts.

Build and ship code

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Workflow fit

Add it to a complete workflow

Inspect, patch, and verify code

Coding review agent

A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.

Turn skills into distribution

Content growth agent

A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.

Find, compare, and synthesize

Research report agent

A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.

Alternative shortlist

Compare before you install

Similar skills in this category, ranked with the same readiness and quality signals.

Compare all

Claude Scientific Skills

A comprehensive collection of ready-to-use scientific and research skills for AI agents.

Adopt
Ready100
Quality100
Stars31.2K

Awesome Claude Skills

A curated list of resources and tools for enhancing Claude AI workflows.

Adopt
Ready100
Quality100
Stars65.9K

Khazix Skills

A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.

Adopt
Ready100
Quality100
Stars17.8K

Overview

<div align="center">

# 說人話 speak-human-tw

### *字都對，卻不像人講的話？那就是 AI 味。*

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Version](https://img.shields.io/badge/version-1.4.0-brightgreen.svg)](CHANGELOG.md) [![Benchmark](https://img.shields.io/badge/benchmark-42_cases-blue.svg)](evals/benchmark.md) [![zh-TW](https://img.shields.io/badge/zh--TW-Taiwan-e4002b.svg)](references/taiwan-localization.md) [![GitHub stars](https://img.shields.io/github/stars/Raymondhou0917/speak-human-tw?style=social)](https://github.com/Raymondhou0917/speak-human-tw/stargazers)

<br>

<img src="assets/readme/speak-human-tw-light-visuals-banner-v1.png" alt="說人話 speak-human-tw：繁體中文的去 AI 味改寫 skill" width="820">

<br>

<table> <tr><td align="left">

🤖 &nbsp;AI 幫你把稿子寫好了，你自己讀一遍卻覺得哪裡怪，但又說不出來哪裡怪？<br> 📮 &nbsp;電子報資訊全對，讀起來卻像新聞稿，不像你在跟讀者講話？<br> 😮‍💨 &nbsp;每次都要一句一句抓「這句好 AI 味」，叫它重寫，改到最後比自己從頭寫還累？

</td></tr> </table>

### ✨ 這些，`說人話.skill` 都能解決。

<br>

一個專門校對繁體中文的 skill：抓出 35+ 種 AI 中文寫作痕跡，順手把中國用語和半形標點改成台灣的寫法，改寫成讀起來像人寫的版本，還附一份交稿前能自己打分數的檢核表。

給 Claude Code、Codex、Cursor 和任何能讀 Markdown 的 AI agent 用。

**內容創作 · 行銷文案 · 日常辦公** —— 電子報 · 社群貼文 · 銷售頁 · 客服回信 · 簡報 · 公告 · Email

<br>

**先保住事實 → 再清掉 AI 味 → 最後才加人味**

不是把你的稿子洗成機器人，是把 AI 味洗掉、把你洗回來。

</div>

<div align="center">

---

### 應用說明：真人手寫 vs. AI 代寫辨識

<table width="100%"> <tr> <td width="50%" valign="top" align="center">

**案例一：2024 年手寫電子報 → 那年根本沒有 AI 幫忙。丟進去使用 /speak-human-tw，它說沒有 AI 痕跡，感動。**

<img src="assets/readme/speak-human-tw-case-real-newsletter-2024.jpg" alt="說人話 skill 檢查 2024 年真人手寫的雷蒙週報，判定不用改" width="100%">

</td> <td width="50%" valign="top" align="center">

**案例二：AI 代寫的回覆 → 抓到 6 處 AI 味＆提供建議修改方向**

<img src="assets/readme/speak-human-tw-case-ai-comment-reply.jpg" alt="說人話 skill 檢查 AI 代寫的 YouTube 留言回覆，逐條列出 6 處 AI 味" width="100%">

</td> </tr> </table>

</div>

**這個對比只能證明一件事：同一份 skill，能助你分得出 AI 味，它不代表你可以拿來當「萬用內容寫作」skill 用。**

它做的是校對，不是創作：拿一篇你已經寫好的稿子，抓出裡面的 AI 常見寫作模式，列出「哪裡可以怎麼改」的建議，要不要採用、怎麼改，還是你自己拍板。

**正確應用是先用你自己的風格寫初稿 → 用說人

Platform Compatibility

pythonFULL

Technical Details

Version
1.0.0
License
MIT
Last Updated
7/24/2026
Published
7/24/2026

Frameworks & Tools

Python

Decision snapshot

Primary pick

100
Ready
Adopt
Stage

691 GitHub stars

Audit snapshot

Install review

Install and adoption review

95
Safe to try
Security
91/100
Maintenance
100/100
Install
92/100
Open full auditOpen eval report

Agent-proven evidence

Agent Proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
—
Recent failure
—
Outcomes
0
Output quality
—
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Agent-Proven rankingOutcome contract

Install

Add to agent workflow

Free and open source. Review the audit before production use.

Compare AlternativesAuto-resolve PlanView on GitHubDocumentation

Growth loop

Share kit

X

Scenario-led draft for Speak Human Tw, ready for a manual X post.

Curator note
Most coding agents don't fail from lack of model power. They fail when repo context disappears.

Speak Human Tw gives coding agents a repeatable way to plan, patch, review, or ship.

691 stars

https://www.openagentskill.com/skills/raymondhou0917-speak-human-tw?ref=x
#AIAgents
Open X draft
Optional reply with install command
Listing + install path for Speak Human Tw:
https://www.openagentskill.com/skills/raymondhou0917-speak-human-tw?ref=x

Install: npx skills add Raymondhou0917/speak-human-tw
Open reply draft

Listing source

Community indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This community indexed listing is attributed to Raymondhou0917 but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/raymondhou0917-speak-human-tw?metric=listed&label=Listed)](https://www.openagentskill.com/skills/raymondhou0917-speak-human-tw)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/raymondhou0917-speak-human-tw?metric=trust&label=Trust)](https://www.openagentskill.com/skills/raymondhou0917-speak-human-tw)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/raymondhou0917-speak-human-tw?metric=audit&label=Audit)](https://www.openagentskill.com/skills/raymondhou0917-speak-human-tw/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/raymondhou0917-speak-human-tw?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/raymondhou0917-speak-human-tw)
Preview badge Open audit Creator Kit

Author

R

Raymondhou0917✓

@raymondhou0917

Tags

traditional-chineseai-detoxwriting-assistantclaude-codecursor

Platform Fit

Claude CodeOpenAI AgentsCursor

Health Signals

GitHub stars
691
Quality score
63/100
Last GitHub push
Jul 24, 2026
Framework hints
1
OpenAgentSkill views
1
Install copies
0
Outbound clicks
0

Community Signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & Safety

Review then install

88
  • GitHub adoption691 GitHub starsINFO
  • Stars/forks activity691 stars, 79 forks; issue activity unavailable in current metadataINFO
  • Recent maintenance4d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskno major dependency risk hints in public metadataPASS

Related Skills

Claude Scientific Skills

A comprehensive collection of ready-to-use scientific and research skills for AI agents.

31.2K stars · 0 installs

Awesome Claude Skills

A curated list of resources and tools for enhancing Claude AI workflows.

65.9K stars · 0 installs

Khazix Skills

A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.

17.8K stars · 0 installs