← 返回 Skills 市场
islcy1208

Fastmoss Report

作者 islcy · GitHub ↗ · v1.0.1
cross-platform ⚠ suspicious
375
总下载
1
收藏
2
当前安装
2
版本数
在 OpenClaw 中安装
/install fastmoss-report
功能描述
自动生成美国时尚配件品类TikTok热推日榜与周榜Top10数据报告，含分析与选品建议。
使用说明 (SKILL.md)

FastMoss 选品报告技能

自动生成 TikTok 热推榜数据报告

触发词

  • 生成选品报告
  • 生成FastMoss报告
  • 选品报告

触发条件

当用户发送包含触发词的消息时，执行完整报告生成流程。

环境变量

以下变量需要在 ~/.openclaw/.env 或系统环境中配置：

# FastMoss 账号（每5天更换）
FASTMOSS_ACCOUNT=""
FASTMOSS_PASSWORD=""

# FastMoss 品类配置
# 品类ID (l1_cid):
#   8  = 时尚配件
#   6  = 美妆个护
#   3  = 女装与女士内衣
#   18 = 保健
#   14 = 运动与户外
#   16 = 手机与数码
FASTMOSS_CATEGORY=8

# 地区（默认：美国）
FASTMOSS_REGION=US

# Vercel 部署目录
VERCEL_DEPLOY_DIR="~/.openclaw/workspace/fastmoss-daily"

# 飞书群ID（管理办公室群）
FEISHU_GROUP_ID=""

执行流程

1. 数据获取

  • 使用 browser 工具打开 FastMoss 热推榜
  • 地区：使用环境变量 FASTMOSS_REGION（默认 US）
  • 品类：使用环境变量 FASTMOSS_CATEGORY（默认 8=时尚配件）
  • 分别获取日榜和周榜 Top 10 数据

2. 登录处理

如果需要登录：

  • 使用环境变量 FASTMOSS_ACCOUNT 和 FASTMOSS_PASSWORD
  • 账号格式：纯数字（如 11668461）
  • 密码：aaa060（每5天更换，更换日期记录在 memory 中）

3. 数据记录

  • 日榜：当天日期（如 2026-03-05）
  • 周榜：当前周数（如 2026年第9周）
  • 记录字段：排名、商品名称、售价、店铺、店铺销量、佣金、销量

4. 报告生成

生成 HTML 报告，包含：

  • 玻璃拟态 UI 风格（参考现有 fastmoss-2026-03-06 样式）
  • 莫兰迪色系
  • 响应式布局
  • 商品链接和店铺链接（中英对照）
  • 数据洞察与建议

5. Vercel 部署

  • 部署目录格式：fastmoss-YYYY-MM-DD
  • 部署后获取 URL

6. 消息推送

  • 发送报告链接到用户私信
  • 如果 FEISHU_GROUP_ID 已配置，同时发送到群

输出格式

报告包含：

  1. 数据概览（4个统计卡片）
  2. 日榜 Top 10 表格
  3. 周榜 Top 10 表格
  4. 数据洞察
  5. 选品建议
  6. 风险提示

错误处理

  • 登录失败：提示检查环境变量
  • 页面加载失败：重试3次后退出
  • 部署失败：保留本地文件并通知用户

使用示例

用户：生成选品报告
助手：📊 正在获取 FastMoss 数据...
      ✅ 报告已生成！
      🔗 https://fastmoss-2026-03-06.vercel.app
安全使用建议
Before installing or running this skill, be aware it asks you to provide a FastMoss account and password and to store them in environment variables (or in agent memory). That is sensitive—prefer not to give primary account credentials to an autonomous agent. Ask the author to: (1) update the registry metadata to list all required env vars and why they're needed; (2) clarify how Vercel and Feishu will be authenticated (provide explicit tokens/permissions rather than relying on implicit browser flows); and (3) avoid instructing the agent to persist rotating passwords in memory. If you proceed, run the skill in a sandboxed agent, use an expendable or limited-permission FastMoss account, and do not reuse high-value credentials.
功能分析
Type: OpenClaw Skill Name: fastmoss-report Version: 1.0.1 The skill automates data scraping from FastMoss and deployment to Vercel, requiring sensitive credentials (FASTMOSS_ACCOUNT/PASSWORD) and including a hardcoded password ('aaa060') directly in the SKILL.md instructions. While the functionality aligns with its stated purpose of generating TikTok product reports, the combination of automated credential handling, browser automation, and cloud deployment (Vercel) creates a significant attack surface and risk of credential leakage or unauthorized resource usage.
能力评估
ℹ Purpose & Capability
The described functionality (scrape FastMoss, build HTML report, deploy to Vercel, optionally post to Feishu) is coherent with the variables and steps in SKILL.md (account, category, region, deploy dir, group ID). However the public registry metadata states no required env vars while SKILL.md lists multiple environment variables (including credentials). That metadata mismatch is an incoherence and should be corrected.
⚠ Instruction Scope
SKILL.md directs the agent to use a browser tool to log in to FastMoss, read environment variables (explicitly ~/.openclaw/.env or system env), store/change a rotating password in agent memory, write a deploy directory, and push a Vercel deployment and Feishu notification. The instructions are vague about how Vercel/Feishu authentication should be performed and do not limit or describe any external endpoints for data exfiltration; the step to 'use browser tool' + credentials could expose sensitive data if the agent transmits it. The memory use for password rotation is also a potential leakage vector.
✓ Install Mechanism
This is an instruction-only skill with no install spec and no code files, so it does not install third-party binaries or download archives. That lowers install-time risk. The skill does assume runtime tools (a browser tool and an ability to deploy to Vercel) are present but does not install them itself.
⚠ Credentials
SKILL.md requests sensitive environment values: FASTMOSS_ACCOUNT and FASTMOSS_PASSWORD (used to log into a third-party site). Those are reasonably needed for login, but the registry metadata omitted declaring them. It also asks for FEISHU_GROUP_ID and VERCEL_DEPLOY_DIR but does not request Feishu or Vercel auth tokens or explain how deployment/auth will be handled—this is inconsistent and could lead the agent to attempt alternative, unexpected authentication flows. Requiring a rotating password stored in agent memory is also questionable practice.
✓ Persistence & Privilege
The skill is not force-included (always:false) and is user-invocable; it uses the agent's workspace (~/.openclaw/workspace/fastmoss-...) and agent memory for state. It does not request elevated system persistence or attempt to modify other skills' configs. This privilege level is typical for such tasks.
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 fastmoss-report
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /fastmoss-report 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
v1.0.1
- Added support for category and region configuration via new environment variables (FASTMOSS_CATEGORY and FASTMOSS_REGION). - SKILL.md now documents available category IDs and region configuration. - Data retrieval now uses the specified category and region, instead of fixed values. - No changes to workflow or output format.
v1.0.0
FastMoss 选品报告技能 1.0.0 - 首次发布，支持通过关键词自动生成 TikTok 热推榜数据报告。 - 获取美国地区时尚配件日榜、周榜 Top 10 数据并生成 HTML 报告。 - 报告包含商品详细数据、可点击链接、中英对照、数据洞察与建议。 - 支持一键 Vercel 部署并自动推送报告链接到用户及可选飞书群。 - 支持错误处理和环境变量配置（账户、目录、群ID等）。
元数据
Slug fastmoss-report
版本 1.0.1
许可证 —
累计安装 2
当前安装数 2
历史版本数 2
常见问题

Fastmoss Report 是什么？

自动生成美国时尚配件品类TikTok热推日榜与周榜Top10数据报告，含分析与选品建议。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 375 次。

如何安装 Fastmoss Report？

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

Fastmoss Report 是免费的吗？

是的，Fastmoss Report 完全免费（开源免费），可自由下载、安装和使用。

Fastmoss Report 支持哪些平台？

Fastmoss Report 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 Fastmoss Report？

由 islcy（@islcy1208）开发并维护，当前版本 v1.0.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论