AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Jianyan

skill-luckyonetwothree-jianyan-jianyan · by LuckyOneTwoThree

质检任何文章 / 报告 / 白皮书的文内证据完备度——拆出核心主张、按 E0–E3 分级、点名裸奔断言与张冠李戴引用,并给出每条的最便宜手动核实路径。当用户粘贴文章并问"这篇靠谱吗 / 有没有水分 / 帮我质检 / 有没有裸奔观点",或要求分析某篇内容的可信度时使用。不做真假判定,只评估证据完备度。

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-luckyonetwothree-jianyan-jianyan

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-luckyonetwothree-jianyan-jianyan)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Jianyan? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

鉴言 JianYan · 信息证据质检

铁律(每次必读)

  1. 只评估"文内证据完备度",永不输出真假判定
  2. 每条判定必须附逐字原文引文——引文必须能在原文中找到,禁止改写、禁止编造;原文错别字 / 病句照样保留并标注「原文如此」,禁止悄悄修正
  3. cheapestCheck 只给"信息源类型 + 动作",禁止编造具体 URL、文献编号、页码、数字
  4. 报告末尾固定输出免责行
  5. 先读 rubric.md 再开始判定;rubric 版本号必须印在报告页脚

流程

  1. 通读全文 → 抽取主张(上限 12 条,超出按断言强度截断)
  2. 按 rubric.md 给每条主张定 type / strength / level
  3. 派生判定:裸奔 / 张冠李戴 / 编造共识 / 内部一致性检查 / 评价占比
  4. 每条裸奔断言附传播风险评分(rubric §8 公式,逐条裸奔单独评分);链式因果命中时生成 ASCII 链
  5. 为裸奔与存疑条生成 cheapestCheck
  6. 按 report-template.md 输出报告卡(--verify 启用时在报告卡后追加外部核实区,格式与红线见 verify.md)

输入边界

  • 仅处理文本。原文中的图片 / 图表 / 视频不纳入判定,在报告"覆盖说明"行注明;核心断言的证据依赖配图时,显式点名断言编号
  • 讽刺、反语、纯文学作品:若语境判定置信度低,报告须标注"本文含较多修辞性表达,判定置信度低"
  • 医疗 / 法律 / 投资类:只输出证据完备度,永不输出建议

--verify 模式(v1.5 预览 · 默认关闭)

用户显式要求联网核实时:先确认环境具备真实联网检索能力,再读 verify.md 执行;无联网能力则如实告知「当前环境不支持 --verify」。禁止凭模型内部知识冒充核实结果。

配套文件

  • rubric.md — 判定标准(当前 v0.4,版本化,IP 本体)
  • report-template.md — 报告卡格式
  • evals.md — 25 条对照评测(红线一票否决,含 --verify 闸门 5 条)
  • evals-fixtures.md — 评测素材库(关键片段 + 出处 + 抓取日期;evals 输入一律引用 fixtures 编号)
  • verify.md — --verify 联网核实规格(v1.5 预览 · 默认关闭)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.