← Back to Skills Marketplace
AI幻觉检测专家
by
ai-gaoqian
· GitHub ↗
· v1.0.0
· MIT-0
36
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ai-hallucination-detector
Description
精准识别和分析LLM输出内容中的事实错误和不实信息，辅助内容真实性验证与质量评估。
README (SKILL.md)
AI骞昏妫€娴嬩笓瀹?(Hallucination Detector)
姒傝堪
AI骞昏妫€娴嬩笓瀹舵槸涓€涓笓涓氱殑LLM杈撳嚭璐ㄩ噺瀹℃牳鎶€鑳斤紝鑳藉瀵逛换浣旳I鐢熸垚鐨勬枃鏈繘琛岀郴缁熸€у够瑙夋娴嬶紝璇嗗埆鍏朵腑鐨勪簨瀹炴€ч敊璇€侀€昏緫鐭涚浘鍜屼俊鎭笉涓€鑷淬€?
鏍稿績妫€娴嬬淮搴?1. *瀹炰綋瀛樺湪鎬ч獙璇? - 妫€娴嬫枃鏈腑鎻愬埌鐨勪汉鐗┿€佺粍缁囥€佸湴鐐规槸鍚︾湡瀹炲瓨鍦?2. *鏃堕棿涓€鑷存€ф鏌? - 楠岃瘉鏃堕棿绾块€昏緫锛屾娴嬫棩鏈熺煕鐩?3. *鏁板€煎噯纭€ф牳楠? - 缁熻鏁版嵁銆佹暟瀛楀紩鐢ㄧ殑浜ゅ弶楠岃瘉
- *寮曠敤鐪熷疄鎬у鏌? - 璁烘枃/鏂囩尞/鎶ュ憡寮曠敤鐨勭湡瀹炴€ф鏌?5. 鍥犳灉閫昏緫鍒嗘瀽 - 妫€娴嬪洜鏋滃€掔疆銆佽櫄鍋囧洜鏋滃叧绯?6. *棰嗗煙鐭ヨ瘑涓€鑷存€? - 鍩轰簬涓撲笟鐭ヨ瘑搴撻獙璇侀鍩熸柇瑷€
- *璺ㄦ钀借嚜娲芥€? - 妫€娴嬪叏鏂囧墠鍚庣煕鐩?8. *閲忓寲鏁版嵁鍚堢悊鎬? - 缁熻鏁版嵁鏄惁鍦ㄥ悎鐞嗚寖鍥村唴
- *鏈浣跨敤姝ｇ‘鎬? - 涓撲笟鏈鏄惁浣跨敤鎭板綋
- *鏉ユ簮鍙俊搴﹁瘎浼? - 瀵规湁鏉ユ簮澹版槑鐨勪俊鎭繘琛屽彲淇″害璇勫垎
- *甯歌瘑涓€鑷存€ф鏌? - 鍩虹甯歌瘑鎬ч敊璇瘑鍒?12. 鏁板杩愮畻楠岃瘉 - 鏂囦腑璁＄畻鐨勫噯纭€?13. *澶氳瑷€缈昏瘧鍑嗙‘鎬? - 缈昏瘧鍐呭鐨勫繝瀹炲害妫€鏌?14. *璇箟婕傜Щ妫€娴? - 闀跨瘒鏂囨湰涓涔夊亸绂?15. *缂栭€犱俊鎭瘑鍒? - 璇嗗埆鍏稿瀷鐨凙I缂栭€犳ā寮?16. *鍋忚涓庡埢鏉垮嵃璞℃娴? - 绀句細鍋忚鍐呭绛涙煡
浣跨敤鏂瑰紡
clawhub install hallucination-detector
瀹夎鍚庯紝Agent鑷姩鑾峰緱骞昏妫€娴嬭兘鍔涖€傚浠讳綍AI鐢熸垚鍐呭璋冪敤妫€娴嬶細
璇峰浠ヤ笅鍐呭杩涜骞昏妫€娴嬶細[鍐呭]
杈撳嚭鏍煎紡
{
"overall_score": 0.85,
"risk_level": "low",
"total_issues": 3,
"dimensions": [
{
"name": "瀹炰綋瀛樺湪鎬ч獙璇?,
"score": 0.95,
"issues": [],
"status": "pass"
}
],
"hallucination_instances": [
{
"type": "factual_error",
"dimension": "鏃堕棿涓€鑷存€?,
"location": "绗?娈电2鍙?,
"original": "...",
"correction": "...",
"confidence": 0.92
}
],
"recommendations": ["寤鸿鏍稿疄..."]
}
瀹夊叏涓庨殣绉?- 绾湰鍦版帹鐞嗭紝妫€娴嬪唴瀹逛笉涓婁紶浠讳綍澶栭儴鏈嶅姟鍣?- 浣跨敤鏈湴宓屽叆妯″瀷杩涜璇箟鐩镐技搴﹁绠?- 鏀寔绂荤嚎杩愯锛堥櫎棣栨妯″瀷涓嬭浇锛?- 涓嶈褰曟垨缂撳瓨鐢ㄦ埛妫€娴嬪唴瀹?
閫傜敤鍦烘櫙
- 鍐呭鍒涗綔鑰咃細鍙戝竷鍓嶅鏍窤I杈呭姪鐢熸垚鐨勬枃绔?- 瀛︽湳鐮旂┒鑰咃細鏍￠獙鏂囩尞缁艰堪涓殑寮曠敤鍜屾柇瑷€
- 娉曞緥浠庝笟鑰咃細瀹℃煡AI鐢熸垚鐨勬硶寰嬫枃涔?- 鍖荤枟鍋ュ悍锛氶獙璇丄I鍋ュ悍寤鸿鐨勪簨瀹炲噯纭€?- 鏂伴椈濯掍綋锛欰I鏂伴椈绋跨殑浜嬪疄鏍告煡
- 浼佷笟鍚堣锛氬唴閮ㄦ姤鍛婂拰瀵瑰澹版槑鐨勫噯纭€у鏌?
Usage Guidance
Installers should expect this skill to analyze text they deliberately provide for fact-checking. Avoid sending sensitive documents unless you are comfortable with local model processing and any first-run model download behavior in your agent environment.
Capability Assessment
Purpose & Capability
The stated purpose is to evaluate AI-generated text for factual, logical, citation, numerical, and consistency issues; that capability matches the documented use cases and output format.
Instruction Scope
The skill describes checking any AI-generated content, but the artifact shows an explicit user-invoked prompt pattern rather than automatic interception of unrelated conversations.
Install Mechanism
The artifact contains only SKILL.md, with no executable scripts or install-time code; declared Python packages are consistent with local text analysis.
Credentials
The declared Python, sentence-transformers, spaCy, NumPy, CPU, and memory needs are proportionate for local semantic analysis; no API keys are requested.
Persistence & Privilege
No persistence, credential access, background execution, destructive action, or external upload behavior is present in the artifact; it claims local inference and no content logging.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ai-hallucination-detector - After installation, invoke the skill by name or use
/ai-hallucination-detector - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
AI Hallucination Detector v1.0.0
- Initial release of a professional tool for comprehensive LLM output hallucination and factuality detection.
- Supports 16 evaluation dimensions, including fact consistency, temporal alignment, statistical accuracy, and use of proper terms.
- Structured JSON output provides detailed scoring, identified hallucination instances, and targeted recommendations.
- Designed for diverse scenarios such as content moderation, academic review, legal text verification, medical review, news validation, and enterprise report quality assurance.
- Runs locally, ensures privacy by not uploading content externally, and works offline except for initial model download.
Metadata
Frequently Asked Questions
What is AI幻觉检测专家?
精准识别和分析LLM输出内容中的事实错误和不实信息，辅助内容真实性验证与质量评估。 It is an AI Agent Skill for Claude Code / OpenClaw, with 36 downloads so far.
How do I install AI幻觉检测专家?
Run "/install ai-hallucination-detector" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AI幻觉检测专家 free?
Yes, AI幻觉检测专家 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does AI幻觉检测专家 support?
AI幻觉检测专家 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AI幻觉检测专家?
It is built and maintained by ai-gaoqian (@ai-gaoqian); the current version is v1.0.0.
More Skills