Real Skill packageSource verifiedClawHub registry

anti-ai-foolish

Pre-publish AI-flavor gatekeeper for Chinese long-form articles (公众号/自媒体评论). Detects and removes AI-writing tells using 1,108 rules that were A/B-validated on 52 real Tencent Zhuque detector-labeled fragments. Use whenever the user asks to 去AI味, 去AI, 降AI率, 终检/检查一篇文章 before publishing, or mentions an article was flagged or rejected by WeChat (微信打回) or Zhuque (朱雀) as AI-generated — even if they only say "这篇文章帮我看看".

Identity and source

Publisher attributionzsdregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 57% rule confidence
Package forminstruction with code26 recorded files
Canonical sourceClawHub registryclawhub:forrestneo:anti-ai-foolish
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 · 9/19/2026.claude/skills/anti-ai-foolish

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 · 9/19/2026.agents/skills/anti-ai-foolish

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 · 9/19/2026skills/anti-ai-foolish

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 @forrestneo/anti-ai-foolish
clawhub inspect @forrestneo/anti-ai-foolish --version 0.1.0

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
26 / 26 inspected as text
Checked
9/19/2026, 3:55:41 PM
Scanner
0.1.3
Policy
1.0.3
3 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
1 dependency and API indicators
  • api: github.com
External clawhub result: suspicious

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
9/19/2026, 12:06:28 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

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

Package content hashsha256:eeac63cb779bc3cbf988ef53f4454043498158b5abc5ee431858716b87bf0f82
Show up to 26 recorded paths
  • .gitignore
  • README.en.md
  • README.md
  • references/PROJECT_HISTORY.md
  • references/ROADMAP.md
  • references/方法论与证据链.md
  • references/评测报告.md
  • rules/INDEX.json
  • rules/R_内容在场.json
  • rules/R_句法.json
  • rules/R_工程纪律文体.json
  • rules/R_标点.json
  • rules/R_词表libai.json
  • rules/R_词表书面腔.json
  • rules/R_词表人味指南.json
  • rules/R_词表模板词.json
  • rules/R_词表综合.json
  • rules/R_词表网文.json
  • rules/R_词表网文程式.json
  • rules/R_词表踩雷.json
  • rules/R_豁免用户指纹.json
  • scripts/abtest.py
  • scripts/preflight.py
  • scripts/scanner.py
  • SKILL.md
  • validation/results/abtest_results.json

Source changelog

- Initial release of anti-ai-foolish, a pre-publish gatekeeper for Chinese long-form articles to detect and remove AI-writing indicators. - Uses 1,108 evidence-backed, A/B-validated rules tested against 52 Tencent Zhuque detector-labeled fragments. - Introduces a two-step workflow: mechanical gates (punctuation, quoting, Z-score) and human judgment checks. - Provides clear workflow for detection, repair ("七刀手术"), and final platform testing. - Designed for Chinese commentary genres, not for fiction, academic, or English-language texts.