功能描述

Use when the user has Fload MCP tools available and asks about mobile app analytics, reviews, growth metrics, ad performance, anomalies, or app store optimiz...

使用说明 (SKILL.md)

Fload — Mobile App Analytics via MCP

Name: Fload
Author: hassanbazzi

You have access to Fload MCP tools for mobile app analytics. Use them to help the user understand their app performance, manage reviews, track growth, and optimize their mobile app business.

What Is Fload?

Fload is a SaaS platform for mobile app publishers. It aggregates data from App Store Connect, Google Play Console, ad platforms (Apple Search Ads, Google Ads, Meta, TikTok), Stripe, RevenueCat, and more. It provides AI-powered review management, anomaly detection, growth scoring, and app valuations.

Available Tools

App Data

list_apps — List all apps in the user's organization. Use first to discover what apps are available.
get_app_details — Get detailed app info (metadata, valuation, platform). Accepts assetId or bundleId.

Reviews

get_reviews — Get app reviews with filtering (rating, date range, replied status, platform). Essential for sentiment analysis and support workflows.

Metrics & Analytics

discover_metrics — Discover what metrics are available for an app. Always call this first before querying data.
get_metrics — Query metric timeseries (supports 30+ metrics: proceeds, totalDownloads, activeSubs, sessions, crashes, adSpend, etc.). Can query multiple metrics at once and break down by dimension.
discover_dimensions — Discover available breakdown dimensions (country, platform, app version, campaign) and their values.

AI Agents

list_agents — List Fload's AI agents (review, monitoring, forecasting, growth, ASO, ads, product, submission review).
get_agent_details — Get agent configuration for a specific app.
get_agent_run_history — Get execution history for an agent.

Anomalies

get_anomalies — Get detected metric anomalies (surges/declines). Filter by severity, type, status, date range.

Ads

get_ads_performance — Get ad campaign data across Apple Search Ads, Google Ads, Meta, TikTok.

Growth

get_growth_audit — Comprehensive growth assessment synthesizing reviews, anomalies, valuations, and connector health.
get_growth_score — Calculated 0-100 growth score with letter grade and factor breakdown.

Forecasting

get_forecasts — Valuation-based forecasts with trend analysis and projections.

Dashboard

get_dashboard_overview — Organization-wide portfolio overview with revenue, downloads, and connector health.

Actions

list_pending_actions — List AI-generated review replies awaiting approval.
approve_action — Approve a pending review reply (optionally edit first).
reject_action — Reject and delete a pending review reply.

Common Workflows

"How is my app doing?"

list_apps to find the app
get_growth_score for a quick health check
discover_metrics to see what data exists, then get_metrics for revenue/downloads trends
get_anomalies for any recent issues

"Show me my reviews"

get_reviews with appropriate filters
For negative reviews: filter by rating 1-2
For unreplied: filter by replied=false
list_pending_actions to see AI-drafted replies

"What's happening with my ads?"

get_ads_performance — optionally filter by platform
Combine with get_metrics for downloads to calculate organic vs paid

"Give me a full business overview"

get_dashboard_overview for portfolio-level metrics
list_apps then get_growth_score for each app
get_anomalies for anything needing attention

"Help me understand this metric change"

get_metrics for the affected metric
get_anomalies to see if Fload detected it
get_growth_audit for broader context

Tips

Always start with list_apps if you don't know the user's app IDs
Use get_growth_score for a quick pulse check — it synthesizes multiple signals
The get_growth_audit tool is the most comprehensive single-call assessment
Review tools work across platforms (iOS + Android) simultaneously
Anomaly detection covers: revenue, downloads, active subscriptions, trials, and more
When presenting data, format numbers nicely (currency for revenue, comma separators for counts)
Use discover_metrics before get_metrics to know what metrics are available for an app
Use discover_dimensions to find breakdown options (country, platform, etc.) before using dimensional queries

安全使用建议

Before installing, note these inconsistencies and take precautions: (1) The skill metadata lists no install or credentials but the docs instruct you to run `npx @fload-ai/mcp` and create a FLOAD_API_KEY — ask the publisher to reconcile the manifest with the docs. (2) Treat any npx/npm install as potentially risky: verify the @fload-ai/mcp package on the npm registry and inspect its repository/source before running it (or run in an isolated sandbox). (3) Only provide a least-privilege API key (read-only if possible), rotate keys after testing, and monitor activity logs. (4) Confirm what actions the skill will perform on your behalf (e.g., approving review replies) and ensure you consent to that capability. (5) If the vendor has no homepage or verifiable source, prefer to test in a controlled environment or ask for a signed/package release you can audit. These gaps make the skill suspicious but not clearly malicious; requesting clarifying information from the publisher would reduce risk.

功能分析

Type: OpenClaw Skill Name: fload Version: 0.1.0 The 'fload' skill bundle is a legitimate integration for the Fload mobile app analytics platform. It provides a comprehensive set of MCP tools for managing app reviews, tracking growth metrics, and analyzing ad performance via the '@fload-ai/mcp' package. The instructions in SKILL.md and AGENTS.md are consistent with the stated purpose, and there are no indicators of data exfiltration, malicious execution, or harmful prompt injection.

能力评估

ℹ Purpose & Capability

Name/description match the declared tools: analytics, reviews, anomalies, ads, forecasts. The capabilities described (list_apps, get_metrics, approve_action, etc.) are coherent with a mobile analytics/management platform.

⚠ Instruction Scope

The SKILL.md and AGENTS.md instruct the agent to install and use an MCP server and to obtain a FLOAD_API_KEY from app.fload.app. Those runtime instructions go beyond the registry metadata (which lists no required env vars or install). The instructions also include action verbs (approve_action/reject_action) that imply the skill may act on the user's behalf in third-party systems — which requires clear credentialing and authorization but none is declared in the registry manifest.

⚠ Install Mechanism

Although the skill package itself has no install spec, AGENTS.md tells users to run an npx command to fetch @fload-ai/mcp. npx executes code pulled from the npm registry at runtime (moderate risk). The skill's registry entry provides no homepage or verified source to validate that package, increasing the risk of executing unreviewed third-party code.

⚠ Credentials

The registry declares no required environment variables, yet AGENTS.md and the instructions reference FLOAD_API_KEY and imply connectors to App Store Connect, Google Play, ad platforms, Stripe, RevenueCat, etc. Required credentials are not declared in the skill metadata, making it unclear what secrets the skill actually needs and how they will be used.

✓ Persistence & Privilege

The skill is not marked always:true and does not request unusual platform privileges in the manifest. There is no indication it will modify other skills or force-install itself.

版本历史

v0.1.0

Initial release of the Fload skill for mobile app analytics and growth management. - Provides access to 18 Fload MCP tools for app data, reviews, analytics, ads, anomalies, and forecasting. - Supports workflows for app health checks, review management, ad performance analysis, and business overviews. - Tools available include growth score, growth audit, dashboard overview, anomaly detection, review management (including AI-generated replies), and ad campaign reporting. - Integrates data across app stores, ad platforms, and analytics connectors. - Includes actionable tips for tool selection and workflow guidance.

元数据

Slug fload

版本 0.1.0

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

Fload 是什么？

Use when the user has Fload MCP tools available and asks about mobile app analytics, reviews, growth metrics, ad performance, anomalies, or app store optimiz... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 101 次。

如何安装 Fload？

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

Fload 是免费的吗？

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

Fload 支持哪些平台？

Fload 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 Fload？

由 Hassan Bazzi（@hassanbazzi）开发并维护，当前版本 v0.1.0。

Fload