← 返回 Skills 市场
Research Claim Checker
作者
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
140
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install research-claim-checker
功能描述
检查一篇研究或分析里的结论是否被证据支撑，指出证据链断点。；use for research, claims, evidence workflows；do not use for 伪造出处, 替代同行评议.
安全使用建议
This skill appears coherent and local-only, but follow these precautions before running: (1) review scripts/run.py yourself (it is included) to confirm behavior; (2) avoid pointing --input at home, /, or any directory containing secrets or private keys because the script will read many text files and may include snippets in its report; (3) run the smoke test in an isolated environment or with --dry-run and an example input first; (4) provide only sanitized inputs if they contain personal or sensitive data; (5) there are no network calls in the bundle, but if you modify the skill, re-check for added external endpoints.
功能分析
Type: OpenClaw Skill
Name: research-claim-checker
Version: 1.0.0
The skill bundle is a legitimate research analysis tool designed to verify evidence chains in documents. The included Python script (scripts/run.py) provides utility functions for structured reporting and directory auditing, including a defensive 'pattern_audit' mode that scans for (and masks) potential security risks like hardcoded secrets or dangerous shell commands. All operations are local, lack network access, and align strictly with the stated purpose in SKILL.md and README.md.
能力评估
Purpose & Capability
Name/description (claim checking, evidence audit) align with included files and the provided script. The only run-time requirement is python3 and there are no environment variables, credentials, or external services requested.
Instruction Scope
SKILL.md confines behavior to producing structured audit output and suggests running the bundled scripts. The script legitimately reads input files or directories and produces reports. Caution: when pointed at a directory it recursively reads many text file types and emits sampled content (including masked secret-like snippets), so do not run it against directories containing sensitive secrets or private data unless you intend to audit them.
Install Mechanism
No install spec; this is an instruction-only skill with a local Python script. There are no downloads, package installs, or external installers in the bundle.
Credentials
The skill requests no environment variables, no credentials, and requires only python3—proportionate for a local auditing/templating tool.
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or system-wide configuration. It writes output only when invoked with an explicit output path (or will write if default behavior used), which is normal for a report generator.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install research-claim-checker - 安装完成后，直接呼叫该 Skill 的名称或使用
/research-claim-checker触发 - 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
v1.0.0
Initial release of research-claim-checker.
- Provides tools to assess whether research conclusions are supported by evidence and identify gaps in the evidence chain.
- Produces structured outputs: conclusions, corresponding evidence, gaps, required additional evidence, suggested revisions, and confidence assessments.
- Designed for research, claims, and evidence workflows; not for fabricating sources or replacing peer review.
- Includes explicit boundaries for safety, privacy, and compliance.
- Supports both script execution (if permitted) and direct text outputs using provided templates and specs.
元数据
常见问题
Research Claim Checker 是什么？
检查一篇研究或分析里的结论是否被证据支撑，指出证据链断点。；use for research, claims, evidence workflows；do not use for 伪造出处, 替代同行评议. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 140 次。
如何安装 Research Claim Checker？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install research-claim-checker」即可一键安装，无需额外配置。
Research Claim Checker 是免费的吗？
是的，Research Claim Checker 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Research Claim Checker 支持哪些平台？
Research Claim Checker 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, win32）。
谁开发了 Research Claim Checker？
由 vx：17605205782（@52yuanchangxing）开发并维护，当前版本 v1.0.0。
推荐 Skills