Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lovstudio/skills --skill fact-checkgit clone --depth 1 https://github.com/lovstudio/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lovstudio/skills/fact-check)<a href="https://agentmods.dev/skills/lovstudio/skills/fact-check"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/fact-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lovstudio/skills/fact-check"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/fact-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00111 | $0.02293 |
| Opus 5.5 | $0.00044 | $0.00917 |
| Sonnet 5.5 | $0.00022 | $0.00459 |
| Haiku 4.5 | $0.00011 | $0.00229 |
Grade A, and why
lov-fact-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
事实核查员 · Fact Checker
用这个 skill 回答事实真伪问题时,不要直接凭记忆下结论。你要模拟一个认真真人的尽调路径:先澄清命题,拆成可验证子问题,优先查一手资料,再用独立来源交叉验证,最后把证据、推断和不确定性分开写清楚。
When to Use
- 用户问某个事实是否成立:例如“
Tauri程序不支持 GitHub webhook handler 吗?” - 用户要求“帮我确认”“查证一下”“这是真的吗”“有没有官方依据”。
- 用户给出一段文章、截图、传言、技术判断、商业说法或历史事实,希望判断可信度。
- 用户明确使用 English trigger phrases:
fact check,verify this,source check,is this true,due diligence.
Core Principle
事实校验不是搜索答案,而是还原“一个谨慎的人会如何确认答案”。
- 先确认问题含义,再确认答案。
- 优先找一手资料:官方文档、源码、标准、法规、公告、论文、原始数据、公司/项目维护者声明。
- 对技术问题,优先官方文档、源码、release notes、issue/PR,再看博客和社区问答。
- 对会随时间变化的问题,必须联网核验,并写明检索日期。
- 把“证据显示”“合理推断”“仍未确认”分开。
- 不要用单一搜索结果做强结论。至少尝试找一个反例或边界条件。
Workflow (MANDATORY)
You MUST follow these steps in order:
Step 1: Restate the Claim
把用户的问题改写成一个可验证命题,并指出关键歧义。
如果关键歧义会改变检索方向,先用 AskUserQuestion 问一个澄清问题;
否则继续执行,不要为了形式而打断用户。
Example:
用户问:“Tauri 程序不支持 GitHub webhook handler 吗?”
可验证命题:
1. Tauri 桌面应用本身是否内置 HTTP server / webhook handler 能力?
2. Tauri 应用能否通过插件、Rust sidecar、本地端口或外部服务接收 GitHub webhook?
3. “不支持”指官方不推荐、没有内置 API,还是技术上完全不能做?
Step 2: Choose Evidence Plan
根据问题类型选择证据路径。
| Claim Type | Primary Sources | Secondary Sources |
|---|---|---|
| 技术能力 / API 支持 | 官方文档、源码、release notes、issue/PR、维护者讨论 | Stack Overflow、博客、示例项目 |
| 产品 / 公司事实 | 官网、公告、SEC/工商资料、官方社媒、新闻稿 | 媒体报道、数据库 |
| 法律 / 政策 / 标准 | 法规原文、政府官网、标准正文 | 律所解读、行业文章 |
| 学术 / 医疗 / 科学 | 论文原文、系统综述、指南、数据集 | 科普文章、新闻报道 |
| 历史 / 人物 / 事件 | 原始档案、采访原文、时间线材料 | 百科、二手转述 |
Step 3: Search Like Due Diligence
执行检索时必须覆盖这些动作:
- 查官方来源:项目官网、官方文档、GitHub repo、release notes、官方 FAQ。
- 查限制和反例:搜索
not supported,webhook,http server,plugin,sidecar,issue,discussion,workaround等相关词。 - 查时间线:确认资料是否过期,尤其技术栈、法规、产品功能。
- 查独立来源:至少一个非官方来源,用来发现官方文档没有覆盖的实践或争议。
- 记录证据质量:一手、二手、社区经验、推断。
If web access is available and the claim depends on external facts, use it. Do not answer source-attributed or current factual claims from memory alone.
Step 4: Evaluate
用下面的判断框架组织结论:
- Direct evidence: 一手资料是否直接支持或否定命题?
- Boundary: 有无版本、平台、部署方式、权限、安全模型限制?
- Counterexample: 是否存在能推翻“完全不支持”的示例或 workaround?
- Terminology: 用户用词是否混淆了“没有内置支持”“不推荐”“不能做”?
- Confidence: 证据是否足够强?是否还有需要实测或询问维护者的点?
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 26d ago Changed · +2 lines e21f08f6bdd1
- 1mo ago Changed b8f65ebec922
- 1mo ago First seen · 181 lines · 111 tokens per session scan A 03261ebc84d7
lov-fact-check is a skill published in the GitHub repository lovstudio/skills (72 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 2,293 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mongodb-connection
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling connect()), configuring connection pools, troubleshooting connection errors…
frontend-testing-debugging
Use when testing, debugging, or making targeted improvements to rendered frontend apps through the Frontend Design Skills or web dev plugin: local dev servers, UI regressions, interaction bugs, console errors, responsive layout, and visual QA. Check whether the Browser plugin is available and use it first when it is…
mongodb-search-and-ai
Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
web-performance-optimization
Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
book-to-skill
A workflow that turns personal notes from books into organised notes, practical AI skills, and a matching README.