← 返回 Skills 市场

Account Handoff Builder

Name: Account Handoff Builder
Author: 52yuanchangxing

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

darwinlinuxwin32 ✓ 安全检测通过

162

总下载

当前安装

版本数

在 OpenClaw 中安装

/install account-handoff-builder

功能描述

将销售到交付的客户信息整理成交接包，识别承诺风险与实施前提。；use for handoff, customer-success, sales-to-cs workflows；do not use for 删掉不利信息, 替代合同文本.

使用说明 (SKILL.md)

客户交接包构建器

你是什么

你是“客户交接包构建器”这个独立 Skill，负责：将销售到交付的客户信息整理成交接包，识别承诺风险与实施前提。

Routing

适合使用的情况

把销售资料整理成客户交接包
找出承诺风险
输入通常包含：商机信息、承诺内容、客户背景
优先产出：客户摘要、已承诺事项、下一步计划

不适合使用的情况

不要删掉不利信息
不要替代合同文本
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：

客户摘要
已承诺事项
实施前提
承诺风险
需要确认的问题
下一步计划

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

默认强调信息透明，避免交接断层。
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 what it says: generate reviewable handoff packages and optionally audit supplied directories/files. Before running it, inspect scripts/run.py yourself (it is included and uses only Python stdlib). When using the script, avoid pointing --input at broad system locations (e.g., /, your home directory) to prevent reading unrelated or sensitive files. Prefer providing a specific project or export directory, run with --dry-run first, and sanitize PII/sensitive data before feeding inputs. If you plan to let an autonomous agent invoke the skill, ensure the agent is restricted to appropriate input paths and does not run it against system or multi-tenant directories.

功能分析

Type: OpenClaw Skill Name: account-handoff-builder Version: 1.0.0 The skill bundle is a legitimate tool designed to organize customer handoff information and identify implementation risks. The core logic in `scripts/run.py` is limited to text processing, directory scanning, and CSV parsing using standard Python libraries, with no network access or dangerous system calls. Notably, the script includes a security-positive feature that scans input files for high-risk patterns (e.g., hardcoded secrets, `curl|bash`) and masks sensitive data before reporting. The AI instructions in `SKILL.md` are well-defined, emphasizing transparency and explicitly prohibiting the deletion of unfavorable information or the execution of high-risk system changes.

能力评估

✓ Purpose & Capability

Name/description, declared dependency (python3), resources (spec.json, template.md) and the included script align with producing structured handoff briefs and lightweight audits. The script's modes (structured_brief, directory/csv/pattern/skill audit) are reasonable extensions for preparing/reviewing handoff materials and detecting issues in supplied sources.

ℹ Instruction Scope

SKILL.md instructs agents to either produce output from templates or run the bundled script. The script reads files and directories and can scan many file types (.md, .py, .js, .sh, .csv, etc.) and report found headings/patterns. That is coherent for auditing input material, but it means running the script with an overly broad input path (e.g., home directory or /) could cause the skill to read unrelated or sensitive files. The SKILL.md does include safety boundaries (read-only, audit/dry-run) and cautions against executing high-risk actions.

✓ Install Mechanism

Instruction-only skill with no install spec and a small Python script that uses only the standard library. No downloads, third-party registries, or unusual install steps are declared.

✓ Credentials

No environment variables, credentials, or config paths are requested. The script operates on user-supplied input paths and local resources bundled with the skill; this matches the described functionality.

✓ Persistence & Privilege

always is false and the skill does not request persistent or elevated platform privileges. It does not modify other skills or system-wide agent settings. Autonomous invocation is permitted (platform default) but not combined with other concerning factors here.

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 account-handoff-builder
安装完成后，直接呼叫该 Skill 的名称或使用 /account-handoff-builder 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 account-handoff-builder. - Organizes customer information from sales to delivery into a structured handoff package. - Identifies promise risks and implementation prerequisites in the handoff process. - Provides review-ready drafts, structured output, and outlines next steps. - Clearly highlights required confirmations and compliance boundaries. - Emphasizes transparency, auditability, and avoids risky or misleading actions.

元数据

Slug account-handoff-builder

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