← 返回 Skills 市场

Evidence Gap Mapper

Name: Evidence Gap Mapper
Author: 52yuanchangxing

作者 vx：17605205782 · GitHub ↗ · v1.0.0 · MIT-0

darwinlinuxwin32 ✓ 安全检测通过

172

总下载

当前安装

版本数

在 OpenClaw 中安装

/install evidence-gap-mapper

功能描述

在报告、方案或演示稿中定位结论先行但证据不足的位置，并给出补证优先级。；use for evidence, gap-analysis, research workflows；do not use for 伪造数据支撑结论, 忽略高风险假设.

使用说明 (SKILL.md)

证据缺口绘图师

你是什么

你是“证据缺口绘图师”这个独立 Skill，负责：在报告、方案或演示稿中定位结论先行但证据不足的位置，并给出补证优先级。

Routing

适合使用的情况

找出这份报告里证据不足的地方
给我一个补证优先级
输入通常包含：文稿、结论、现有证据
优先产出：主要结论、证据现状、下一步

不适合使用的情况

不要伪造数据支撑结论
不要忽略高风险假设
如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。

工作规则

先把用户提供的信息重组成任务书，再输出结构化结果。
缺信息时，优先显式列出“待确认项”，而不是直接编造。
默认先给“可审阅草案”，再给“可执行清单”。
遇到高风险、隐私、权限或合规问题，必须加上边界说明。
如运行环境允许 shell / exec，可使用：
- python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
如当前环境不能执行脚本，仍要基于 {baseDir}/resources/template.md 与 {baseDir}/resources/spec.json 的结构直接产出文本。

标准输出结构

请尽量按以下结构组织结果：

主要结论
证据现状
缺口列表
补证优先级
可降级表述
下一步

本地资源

规范文件：{baseDir}/resources/spec.json
输出模板：{baseDir}/resources/template.md
示例输入输出：{baseDir}/examples/
冒烟测试：{baseDir}/tests/smoke-test.md

安全边界

适合作为质检器使用。
默认只读、可审计、可回滚。
不执行高风险命令，不隐藏依赖，不伪造事实或结果。

安全使用建议

This skill appears to do exactly what it claims: local, template-driven evidence-gap analysis using a Python helper script. Before running it, review the included scripts (scripts/run.py) yourself. Only pass the files or directories you intend it to analyze — avoid pointing it at entire system roots, home directories, or other places containing secrets. The script will read text files you point it to and may surface snippets (it masks long secret-like tokens partially), so sanitize inputs if they contain sensitive data or run the tool inside an isolated workspace. If you need networked or automated publishing, perform change/write steps separately after manual review.

功能分析

Type: OpenClaw Skill Name: evidence-gap-mapper Version: 1.0.0 The 'evidence-gap-mapper' skill is a document analysis tool designed to identify logical gaps and insufficient evidence in reports. The core logic in `scripts/run.py` is a well-structured Python script that generates Markdown summaries from input text, directories, or CSV files. While the script contains regex patterns to detect secrets and dangerous shell commands (e.g., `curl|bash`), these are used for auditing purposes rather than execution. The `SKILL.md` file includes clear safety boundaries, instructing the AI agent to avoid high-risk commands and data fabrication, and the overall bundle lacks any indicators of malicious intent or unauthorized data exfiltration.

能力评估

✓ Purpose & Capability

Name and description match the included assets: SKILL.md, resources/spec.json/template.md, and scripts/run.py implement local evidence-gap analysis, directory/csv/pattern audits, and structured brief generation. Declared requirement (python3) is proportional.

ℹ Instruction Scope

SKILL.md correctly instructs running the local script or falling back to templates. The script reads the input path (file or directory) and samples many text file types (.md, .py, .csv, .sh, etc.) to produce reports; this is expected for a local audit tool. Caution: if you pass broad system paths (e.g., /, ~, or your repo root) the script will read and summarize those files and may surface snippets that look like secrets (it attempts partial redaction for secret-like patterns). The skill does not instruct any network calls or remote posting.

✓ Install Mechanism

No install spec is provided (instruction-only with an included helper script). That is low-risk: nothing is downloaded from external URLs and no packages are installed automatically. The only runtime requirement is a local python3 interpreter.

✓ Credentials

No environment variables, credentials, or config paths are requested. The script operates on user-supplied input paths only, so requested privileges are minimal and appropriate.

✓ Persistence & Privilege

The skill is not set to always:true and does not request persistent system or agent-level changes. It only writes output when you specify an --output path (or the agent chooses to), and SKILL.md emphasizes read-only / audit-first behavior.

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 evidence-gap-mapper
安装完成后，直接呼叫该 Skill 的名称或使用 /evidence-gap-mapper 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 evidence-gap-mapper. - Identifies insufficiently evidenced conclusions in reports and presentations. - Provides prioritized recommendations for additional evidence collection. - Clearly distinguishes suitable and unsuitable use cases to ensure responsible application. - Defines a structured workflow and output format for consistency and clarity. - Includes built-in safety boundaries to prevent data fabrication, unauthorized actions, and ensure auditability.

元数据

Slug evidence-gap-mapper

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题