How do I install formosa-humanizer?

Install formosa-humanizer in your harness: Claude Code — /plugin marketplace add nagameTW/formosa-humanizer; Cursor — npx skills@1.7.4 add nagameTW/formosa-humanizer; Any agent — npx skills@1.7.4 add nagameTW/formosa-humanizer. Full step-by-step guidance is on the HOL plugin page.

How do I install formosa-humanizer in HOL Guard?

To install formosa-humanizer in HOL Guard, start with hol-guard plugin install nagametw/humanizer-zh-tw --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.

How do I install formosa-humanizer in Claude Code?

To install formosa-humanizer in Claude Code, start with /plugin marketplace add nagameTW/formosa-humanizer. The complete step-by-step install guide for Claude Code is on the HOL plugin page.

How do I install formosa-humanizer in Cursor?

To install formosa-humanizer in Cursor, start with npx skills@1.7.4 add nagameTW/formosa-humanizer. The complete step-by-step install guide for Cursor is on the HOL plugin page.

How is the Trust Score for formosa-humanizer computed?

formosa-humanizer has a HOL Trust Score of 78 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/nagametw%2Fhumanizer-zh-tw/trust

Who publishes formosa-humanizer?

formosa-humanizer is published by nagameTW and listed on HOL.

formosa-humanizer

nagametw/humanizer-zh-tw · v1.7.0 · Agent Skills

by nagameTWOwner verifiedScan grade: GoodAwesome AI Plugins

Agent skill that rewrites AI-generated Traditional Chinese prose, removing AI phrasing and mainland China terms across 49 patterns

Install Source

Follow0

Trust Score78 Security scan86 Components1

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is formosa-humanizer a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

Claude Code
Agent Skills
Cursor

1 skill

Before you install

Sign-in: Not declared
Declared access: Not declared
License: MIT

Check before relying on it

Some security checks did not finish: Cisco skill scan. See the evidence

What is formosa-humanizer?

formosa-humanizer is a published agent skills plugin for AI coding agents that works with Claude Code, Agent Skills and Cursor, developed by nagameTW and distributed through the HOL AI plugin registry. Agent skill that rewrites AI-generated Traditional Chinese prose, removing AI phrasing and mainland China terms across 49 patterns.

Canonical slug: nagametw/humanizer-zh-tw
Version: v1.7.0 · updated Nov 2, 2026
Open data: entity.json (JSON-LD)

Registry snapshot

Repository: https://github.com/nagameTW/formosa-humanizer
Canonical profile: https://hol.org/registry/plugins/nagametw%2Fhumanizer-zh-tw
Owner verification: Verified on HOL as @nagameTW
Marketplace source: .claude-plugin/marketplace.json
Scanner: HOL plugin scanner
Security result: Needs review
Digest verified: Yes

1 bundled skillRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

On-Chain Verified

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability

100/100

Maintenance

40/100

MCP server setup

100/100

Plugin Security

86/100

Provenance

80/100

Publisher Quality

100/100

Provenance

Plugin root: .
Source repo: https://github.com/nagameTW/formosa-humanizer
Source commit: 4f7c1d9a3e95…
Publisher verified: Yes
Owner verified: @nagameTW
Agent Plugins 1.0: Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Security posture

See how the Trust Score is computed

Needs review

Security result

Security score

High findings

Provider: codex-plugin-scanner
Grade: B · Good
Version: 3.24.2

codex:hol-plugin-scanner-F0VGVF / cisco-skill-scanner: failedcodex:hol-plugin-scanner-F0VGVF / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

13/16

6 checks

[claude:.] Operational Security

14/17

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

25/31

9 checks

[codex:.] Security

13/16

9 checks

[codex:.] Operational Security

14/17

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked 2026-11-02. This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

lowsecuritySECURITY_MD_MISSINGReported 2 times

Plugins should publish a SECURITY.md file for responsible disclosure and support guidance.

Add a SECURITY.md file with reporting guidance and supported versions.

lowoperational-securityDEPENDABOT_MISSINGReported 2 times

Automation or dependency surfaces exist, but .github/dependabot.yml is missing.

Add Dependabot updates for GitHub Actions and dependency manifests.

infomanifest-validationPLUGIN_JSON_INTERFACE_SHORTDESCRIPTION

The interface object is missing a valid "shortDescription" value.

Add a valid "shortDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_LONGDESCRIPTION

The interface object is missing a valid "longDescription" value.

Add a valid "longDescription" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CATEGORY

The interface object is missing a valid "category" value.

Add a valid "category" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_CAPABILITIES

The interface object is missing a valid "capabilities" value.

Add a valid "capabilities" field to the interface metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_COMPOSERICON

The interface field "composerIcon" must use HTTPS or point to a safe in-repo asset.

Update "composerIcon" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

1
Add the marketplace
Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.
claude code
2
Install the plugin
Installs the humanizer-zh-tw entry from the humanizer-zh-tw marketplace.
claude code
3
Scripted alternative
Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.
shell
4
Check it is installed
Lists installed plugins. The entry should appear as enabled.
shell

To remove it later, run claude plugin uninstall humanizer-zh-tw@humanizer-zh-tw.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W44, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "humanizer-zh-tw",
  "description": "把 AI 寫的中文改得像人寫的。改自 blader/humanizer，照台灣用語和中文標點重寫，共 49 種模式。",
  "version": "1.7.0",
  "author": {
    "name": "nagameTW",
    "url": "https://github.com/nagameTW"
  },
  "homepage": "https://github.com/nagameTW/formosa-humanizer",
  "repository": "https://github.com/nagameTW/formosa-humanizer",
  "license": "MIT",
  "keywords": [
    "writing",
    "editing",
    "ai-writing",
    "humanize",
    "prose",
    "style",
    "chinese",
    "traditional-chinese",
    "zh-tw",
    "taiwan"
  ],
  "interface": {
    "displayName": "humanizer-zh-tw",
    "developerName": "nagameTW"
  },
  "skills": "./",
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL: https://github.com/nagameTW/formosa-humanizer
Marketplace path: .claude-plugin/marketplace.json
Source path: .
Install policy: Unspecified

Skills

1 SKILL.md file ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

skills-cli

humanizer-zh-tw
SKILL.md
去除繁體中文文字裡的 AI 生成痕跡，讓文字讀起來像真人書寫而非機器產出。當使用者要求「去 AI 味」「潤稿」「讓這段更像人寫的」「改寫成自然的中文」，或要把 AI 生成的草稿、翻譯、貼文、報告、commit 訊息、PR 描述整理成對外文字時使用。依據維基百科「Signs of AI writing」指南，針對台灣繁體中文在地化，涵蓋宣傳語言、模糊歸因、AI 詞彙、三段式列舉、中國用語混入、標點西化、節奏均勻化等 49 種模式。
Raw SKILL.md
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.claude-plugin/marketplace.json

file

679 bytes

a50717a6197f5ff7…

.claude-plugin/plugin.json

file

644 bytes

83e79f1ef19811ae…

.codex-plugin/plugin.json

plugin-manifest

727 bytes

8a7ac6630141ca2b…

.cursor-plugin/plugin.json

file

566 bytes

711fbfa3becf3b2c…

.github/ISSUE_TEMPLATE/config.yml

file

261 bytes

7e93a00ec534314a…

.github/ISSUE_TEMPLATE/new-pattern.yml

file

680 bytes

4ef4a9dbf4688bb7…

.github/ISSUE_TEMPLATE/rewrite-problem.yml

file

1,317 bytes

94e181a4a9d45ef5…

.github/workflows/release-zip.yml

file

1,168 bytes

ca75c44e01d73343…

.github/workflows/validate.yml

file

815 bytes

f2d6a8780fb0b3cf…

AGENTS.md

file

4,923 bytes

9e60b112f28842c4…

agents/openai.yaml

file

205 bytes

8af2f46af78e3f75…

CHANGELOG.md

file

16,965 bytes

3215d8a621ea0d4d…

docs/design.md

file

3,402 bytes

716429ddc60b27f4…

docs/example.md

file

3,543 bytes

97caa3566ad411c4…

docs/install.md

file

1,089 bytes

3d9b814b5c74dc30…

docs/PROMOTION.md

file

4,156 bytes

1499baff69504788…

docs/usage.md

file

703 bytes

cf7c41957c18df3b…

LICENSE

file

1,420 bytes

59839f53fc7ebade…

PATTERNS.md

file

20,227 bytes

3dd9d737af68b7f1…

README.md

file

8,071 bytes

52f7a3896b7ed7e6…

references/zh-cn-glossary.md

file

3,496 bytes

80f9f7542d3782b2…

scripts/validate-package.py

file

5,217 bytes

ca4b938712607868…

SKILL.md

skill

45,752 bytes

ac10391650ad2904…