openclaw 网盘下载
OpenClaw

技能详情(站内镜像,无评论)

首页 > 技能库 > Source Trace Builder

为分析稿建立引用索引和原始出处映射,区分一手与二手来源。;use for sources, citations, research workflows;do not use for 编造文献出处, 替代正式文献管理软件.

开发与 DevOps

作者:vx:17605205782 @52YuanChangXing

许可证:MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本:v1.0.0

统计:⭐ 0 · 20 · 0 current installs · 0 all-time installs

0

安装量(当前) 0

🛡 VirusTotal :良性 · OpenClaw :良性

Package:52yuanchangxing/source-trace-builder

安全扫描(ClawHub)

  • VirusTotal :良性
  • OpenClaw :良性

OpenClaw 评估

The skill's declared purpose (building citation/source mappings) matches its code and runtime instructions: it is a local, Python-based reporter that reads local inputs and emits structured Markdown with no network calls or secret access.

目的

Name/description, SKILL.md, resources/spec.json, README, and the included scripts/run.py are all aligned: the tool ingests citation text, drafts or directories and produces structured Markdown reports and audits. Required binary (python3) is appropriate and minimal.

说明范围

SKILL.md restricts behavior to read-only, review-first outputs and suggests running the bundled script. The script itself only reads local files and writes local output; it contains code to make structured reports, directory audits, CSV audits, pattern scans, and skill audits. Caution: if invoked with a directory (or a broad path), the script will recursively read many file types (md, py, js, json, csv, sh, etc.), so avoid pointing it at large…

安装机制

No install spec; instruction-only skill with an included local Python script. No downloads, no external package installation, and no extract-from-URL behavior are present.

证书

No environment variables, credentials, or config paths are required. The script reads local files only and contains patterns to detect secrets, but it does not attempt to access remote endpoints or request unrelated credentials.

持久

The skill does not request persistent or elevated platform privileges (always:false). It does not modify other skills or system-wide configuration. Its only write behavior is optional local output file generation (or stdout) when run with --output and not in --dry-run mode.

综合结论

This skill appears coherent and local-only, but take these precautions before running: - Review scripts/run.py yourself (it's included) to confirm behavior matches your expectations. The code is readable and uses only standard library operations. - When testing, run in a safe/isolated directory and use --dry-run or supply a specific input file rather than a broad path (do not point --input at your home directory or repositories with secrets). …

安装(复制给龙虾 AI)

将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Source Trace Builder」。简介:为分析稿建立引用索引和原始出处映射,区分一手与二手来源。;use for sources, citations, research workflows;do …。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/52yuanchangxing/source-trace-builder/SKILL.md
(来源:yingzhi8.cn 技能库)

SKILL.md

打开原始 SKILL.md(GitHub raw)

---
name: source-trace-builder
version: 1.0.0
description: "为分析稿建立引用索引和原始出处映射,区分一手与二手来源。;use for sources, citations, research workflows;do not use for 编造文献出处, 替代正式文献管理软件."
author: OpenClaw Skill Bundle
homepage: https://example.invalid/skills/source-trace-builder
tags: [sources, citations, research, traceability]
user-invocable: true
metadata: {"openclaw":{"emoji":"🧷","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
---
# 来源追踪构建器

## 你是什么
你是“来源追踪构建器”这个独立 Skill,负责:为分析稿建立引用索引和原始出处映射,区分一手与二手来源。

## Routing
### 适合使用的情况
- 帮我建立这篇分析的来源索引
- 区分一手与二手来源
- 输入通常包含:引用文本、出处线索、草稿
- 优先产出:来源目录、一手/二手区分、维护建议

### 不适合使用的情况
- 不要编造文献出处
- 不要替代正式文献管理软件
- 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
1. 先把用户提供的信息重组成任务书,再输出结构化结果。
2. 缺信息时,优先显式列出“待确认项”,而不是直接编造。
3. 默认先给“可审阅草案”,再给“可执行清单”。
4. 遇到高风险、隐私、权限或合规问题,必须加上边界说明。
5. 如运行环境允许 shell / exec,可使用:
   - `python3 "{baseDir}/scripts/run.py" --input <输入文件> --output <输出文件>`
6. 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:
- 来源目录
- 一手/二手区分
- 引用映射
- 缺失出处
- 风险说明
- 维护建议

## 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
- 会把无法核实的引用标为待确认。
- 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。