← 返回 Skills 市场
marianachow0321

Fact Cross Check

作者 marianachow0321 · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ✓ 安全检测通过
172
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install fact-cross-check
功能描述
Multi-source verification with confidence ratings. Use for verifying factual claims, finding examples and verifying they match criteria, statistics, or resea...
使用说明 (SKILL.md)

\r \r

Cross Check\r

\r Multi-source verification for factual claims with confidence scoring and source links.\r \r

Workflow\r

\r

  1. Optimize query — see {baseDir}/references/query-optimization.md.\r
  2. Search first (REQUIRED) — ALWAYS use web_search as the primary tool. Never skip to web_fetch directly. Run web_search(query, count=10). If T1 found, stop. If only T2-3, run a second query. If contradictions, investigate.\r
  3. Evaluate sources — classify by tier. See {baseDir}/references/source-tiers.md.\r
  4. Direct verify (optional, only after search) — use web_fetch(url) only to verify specific URLs found via search. Never use web_fetch as a substitute for web_search.\r
  5. Present — MUST include clickable source URLs for every result:\r

    [Answer]\r Confidence: [T1-T5] ([%]) | Sources: name, ... | Verified: [date] | Note: [caveats]\r \r

Source URLs\r

\r CRITICAL: Every cited source MUST include a direct clickable URL. If URL unavailable: T1 → find alternative source, T2+ → downgrade one tier. Never list a source without its URL.\r \r

Error Handling\r

\r

  • Zero results → broaden query, retry once. Still empty → T1 confidence.\r
  • web_fetch fails → skip, note it, drop confidence one level.\r
  • All T4 sources → report T2, mark Uncertain.\r
  • Contradictions → see {baseDir}/references/research-patterns.md.\r \r

Security & Privacy\r

\r This skill uses only OpenClaw's built-in web_search and web_fetch tools. No data is sent to external services beyond what these tools do.\r \r External Endpoints:\r

  • Web search API (via OpenClaw's built-in web_search, provider depends on user config)\r
  • Web pages (via OpenClaw's web_fetch for verification)\r \r Data Handling:\r
  • No credentials required\r
  • No data stored locally\r
  • Search queries sent through OpenClaw's configured search provider\r
  • No autonomous invocation without user intent - activates when queries contain verification language\r \r Trust Statement:\r By using this skill, your search queries are sent through OpenClaw's built-in web search provider. Only install if you trust OpenClaw's data handling practices.\r
安全使用建议
This skill is internally consistent and asks for nothing beyond the platform's built-in web_search and web_fetch. Before installing, consider: (1) search queries will be sent to whatever search provider your OpenClaw instance is configured to use — do you trust that provider with the queries you may send? (2) The skill's confidence scoring is heuristic (tier-based) — treat outputs as guidance, not authoritative proof; inspect the provided source URLs yourself. (3) Although the SKILL.md says it activates only on verification-language queries, the platform's default allows autonomous invocation; if you are concerned about any skill running without an explicit prompt, review platform-level settings for autonomous skill invocation. Otherwise, the skill presents no disproportionate permissions or surprising behavior.
功能分析
Type: OpenClaw Skill Name: fact-cross-check Version: 1.0.3 The skill bundle provides a structured framework for an AI agent to perform fact-checking and multi-source verification. It utilizes built-in OpenClaw tools (web_search and web_fetch) and contains no evidence of malicious intent, data exfiltration, or unauthorized execution logic across its files (SKILL.md, README.md, and the references directory).
能力评估
Purpose & Capability
Name/description (multi-source verification) aligns with the instructions: it requires web_search and web_fetch (platform tools) and the included reference docs support the workflow. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
SKILL.md gives a constrained workflow: optimize query, run web_search first, use web_fetch only to verify specific URLs, classify sources, and present clickable URLs. It does not instruct reading local files, exfiltrating secrets, or contacting external endpoints beyond the platform's web tools. The included references only contain query and research guidance.
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are required. Declared data handling matches the skill's needs (search queries via platform provider).
Persistence & Privilege
Skill does not request always:true or other elevated privileges. The SKILL.md states it won't autonomously invoke except on user intent, but the registry flags show normal autonomous-invocation capability (disable-model-invocation: false), which is the platform default. This is expected but worth noting: the platform could invoke it autonomously according to platform rules.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install fact-cross-check
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fact-cross-check 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.3
Force web_search first, enforce source URLs with example
v1.0.1
Fix autonomous invocation wording inconsistency
v1.0.0
Initial release
元数据
Slug fact-cross-check
版本 1.0.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 3
常见问题

Fact Cross Check 是什么?

Multi-source verification with confidence ratings. Use for verifying factual claims, finding examples and verifying they match criteria, statistics, or resea... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 172 次。

如何安装 Fact Cross Check?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install fact-cross-check」即可一键安装,无需额外配置。

Fact Cross Check 是免费的吗?

是的,Fact Cross Check 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Fact Cross Check 支持哪些平台?

Fact Cross Check 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Fact Cross Check?

由 marianachow0321(@marianachow0321)开发并维护,当前版本 v1.0.3。

💬 留言讨论