Real Skill packageSource verifiedClawHub registry

写作AI味消除与禁忌扫雷仪

AI味消除剂+书面禁忌扫雷。通过场景锚定、风格校准、证据守恒改写、独立保真审计与书面禁忌扫雷，帮助写出准确、自然、得体的文字。触发词：去AI味、人话改写、AI味消除剂、这段太AI了、润色一下、扫雷、书面禁忌、用词检查、禁用词、慎用词、写作规范。即使未明确要求扫雷，任何自然语言写作、改写或润色任务都执行扫雷；不适用：代码、数据字段、原文引用、纯数据表格。

Identity and source

Publisher attribution木先生iPPTregistry owner unverified by skillvetai
Functional categoryAwaiting category reviewreview pending · 0% rule confidence
Package forminstruction bundle19 recorded files
Canonical sourceClawHub registryclawhub:muippt:mu-humanizer-minesweeping
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/14/2026.claude/skills/mu-humanizer-minesweeping

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/14/2026.agents/skills/mu-humanizer-minesweeping

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/14/2026skills/mu-humanizer-minesweeping

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @muippt/mu-humanizer-minesweeping
clawhub inspect @muippt/mu-humanizer-minesweeping --version 1.0.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
18 / 19 inspected as text
Checked
8/14/2026, 7:24:51 AM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
8 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
  • api: img.shields.io
  • api: item.m.jd.com
  • api: mp.weixin.qq.com
  • api: muippt.github.io
  • api: www.w3.org
  • api: xhslink.com
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/14/2026, 5:43:32 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: clean
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:57467512451f9df9cea1bdeeb690ee370a9beb5a0e6e4be937bf60f2d32241a6
Show up to 19 recorded paths
  • assets/default-banner.png
  • CHANGELOG.md
  • CONTRIBUTING.md
  • index.html
  • LICENSE
  • README_CN.md
  • README.md
  • references/ai-tics.md
  • references/custom-rules-template.yaml
  • references/edit-policy.md
  • references/en-patterns.md
  • references/fidelity-audit.md
  • references/publish-intro.md
  • references/thresholds.md
  • references/written-taboo-rules.md
  • references/zh-patterns.md
  • skill-card.md
  • SKILL.md
  • THIRD_PARTY_NOTICES.md

Source changelog

mu-humanizer-minesweeping v6.7.0 brings a comprehensive framework for natural language writing quality, combining AI-style detox and taboo scanning. - Introduces a five-step process: scenario anchoring, style calibration, evidence-conserving rewriting, independent fidelity audit, and written taboo scanning. - Enforces strict core safety rules to preserve factual integrity and prohibit unauthorized edits on sensitive topics. - Automates written taboo scanning (e.g., sensitive terms) on every writing/editing task, not just when explicitly requested. - Allows for company/team/personal taboo rule extension, with clear rules on management and priority. - Generates transparent diff reports, audit results, and lightweight process metrics, but never outputs “AI detection scores.” - Clarifies known limitations, such as language and long-text boundaries, and emphasizes the need for professional r…