← 返回 Skills 市场
fulcra

Fulcra Tracking

作者 Fulcra.ai · GitHub ↗ · v0.0.1 · MIT-0
cross-platform ✓ 安全检测通过
41
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install fulcra-tracking
功能描述
Allows the user to record custom data annotations and agent visibility metrics, and generates simple HTML dashboards for visualization.
使用说明 (SKILL.md)

Fulcra Tracking & Dashboards

This skill guides the user through discovering data they want to track in Fulcra, setting up the necessary schemas (including the Agent Visibility Package), recording data, and generating a custom HTML dashboard to display it.

General Guidelines

  • Tone & Vibe: Engaging, conversational, and focused on demonstrating the immediate value ("Time-to-Wow") of Fulcra's data tracking capabilities.
  • Maintain Momentum: Guide the user quickly from schema creation to data entry to dashboard generation.

Workflow

  1. User Intent Discovery:
    • Read the references/fulcra-tracking-cli.md file to understand the custom tracking CLI commands.
    • Read and execute references/fulcra-tracking-discovery.md to uncover what the user wants to track and pitch the Universal Agent Visibility Package.
  2. Data Modeling:
    • Use the fulcra-api data-type create command to create the custom schemas based on the user's intent.
    • Crucial: If they opted into the Agent Visibility Package, create those schemas (e.g., Tasks Completed, Agent Friction, Current Agent Work) alongside their personal schemas and actively record your high-level milestones into them from this point forward. Remember the ids returned by the create command.
  3. Record First User Data:
    • Ask a direct question to get their first piece of data for one of their new schemas, then record it using references/fulcra-tracking-record-annotations.md.
    • Do not use curl for this. Use the fulcra-api CLI if a specific record command is available, or fallback to the instructions in the record annotations reference file.
  4. Time-to-Wow (The Demonstration):
    • Read and execute references/fulcra-tracking-demonstration.md to fetch the data and generate a custom HTML dashboard.
    • Architectural Rules: Follow the "Static Triad" (index.html, app.js, theme.css) or single-scroll artifact paradigm using Alpine.js, D3.js, and pure Vanilla CSS. Do not use Tailwind via CDN due to CSP conflicts.
    • Stop and ask for a theme before generating.
  5. Handoff to Dashboard Skill:
    • Once the user is satisfied with their static HTML dashboard demonstration, explicitly inform them that they can make this dashboard a permanent, live, interactive artifact that updates automatically.
    • Tell them they can transition to the fulcra-dashboard skill to generate a durable React-based dashboard app backed by their Fulcra data.
安全使用建议
Install this only if you are comfortable using Fulcra as a datastore for chosen personal tracking data. Decline health, location, messaging, calendar, sleep, or agent-activity logging unless you specifically want those persisted, and do not enable agent visibility during work that may contain secrets or private third-party information.
能力标签
requires-oauth-tokenrequires-sensitive-credentials
能力评估
Purpose & Capability
The stated purpose is to create Fulcra tracking schemas, record annotations, query recent records, and generate HTML dashboards; the reviewed API access, data recording, and dashboard generation fit that purpose, though the possible data categories are privacy-sensitive.
Instruction Scope
The instructions require consent before sending user data to Fulcra, querying Fulcra for dashboard data, creating a local HTML file, and enabling agent-activity logging. The main scoping caveat is that it encourages using prior chats or memory for onboarding ideas with disclosure rather than a separate pre-use opt-in.
Install Mechanism
The artifact contains markdown skill files only, with no executable install hooks or packaged scripts. Runtime actions depend on user/agent execution of the external fulcra-api CLI and curl-style API calls.
Credentials
Network access to Fulcra, local CLI token use, and creation of a local HTML dashboard are proportionate to the workflow. I found no broad filesystem scanning, hidden background worker, destructive command, or unrelated data flow.
Persistence & Privilege
Persistence is disclosed: selected records and optional agent-visibility summaries are stored in the user's Fulcra datastore after opt-in. Users should understand that agent work summaries may persist and should avoid enabling them for tasks involving secrets or highly sensitive context.
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 fulcra-tracking
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fulcra-tracking 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
v0.0.1
Initial release of fulcra-tracking skill. - Enables users to record custom data annotations and agent visibility metrics in Fulcra. - Guides users from intent discovery through schema setup, data entry, and HTML dashboard generation. - Auto-generates simple, static HTML dashboards (using Alpine.js/D3.js/CSS) for visualizing tracked data. - Includes support and onboarding for the Universal Agent Visibility Package. - Prompts users to upgrade to a live, interactive React-based dashboard with the fulcra-dashboard skill.
元数据
Slug fulcra-tracking
版本 0.0.1
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

Fulcra Tracking 是什么?

Allows the user to record custom data annotations and agent visibility metrics, and generates simple HTML dashboards for visualization. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 41 次。

如何安装 Fulcra Tracking?

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

Fulcra Tracking 是免费的吗?

是的,Fulcra Tracking 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Fulcra Tracking 支持哪些平台?

Fulcra Tracking 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 Fulcra Tracking?

由 Fulcra.ai(@fulcra)开发并维护,当前版本 v0.0.1。

💬 留言讨论