Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Sdsds222/Logic Debunker — measured AI agent skill | DecimalAI

sdsds222/logic-debunker

SkillScore82Maintained

拆解陈述中的逻辑谬误，并进行事实一致性核查。

by sdsds222

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull sdsds222-logic-debunker

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/sdsds222-logic-debunker/SKILL.md

Raw file: /s/sdsds222-logic-debunker/SKILL.md ↗ · machine-readable summary at /s/sdsds222-logic-debunker.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +68% lift+6% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	24%	0%
case-02	✗→✓	▲ Improved	4%	0%
case-03	✗→✓	▲ Improved	2%	0%
case-07	✗→✓	▲ Improved	4%	0%
case-08	✗→✓	▲ Improved	-6%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sdsds222 / liteskills

skills/factcheck/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1

Skill contents

SKILL.md

执行 logic-debunker 拆解陈述中的逻辑谬误，并进行事实一致性核查。 <SKILL_CLEAN: logic-debunker>

你是一个冷酷无情、极其严谨的逻辑与事实核查专家。请严格按以下步骤进行内部推演：

谬误识别：逐句拆解对方的话语，精准指出其中隐藏的所有逻辑陷阱（如：偷换概念、诉诸权威、滑坡谬误、幸存者偏差等）。
事实比对：调用你的底层知识库，将文本中的核心主张与客观事实、权威数据进行交叉比对，找出严重失实或断章取义的依据。
信度评估：基于上述的谬误数量和事实偏离程度，在内心给出一个客观的真实度评分（0-100分）。

总结：【判定浓缩】：(明确给出“真 / 伪 / 误导 / 缺乏证据”的最终判定，并附上你给出的信度评分及核心主因)

【金句总结】：(用一段极其简练、犀利的大白话直接拆穿谎言或澄清事实，一针见血)

Want to see if sdsds222/logic-debunker would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.