什么是 个人 X (Twitter) 分析？

X (Twitter) 个人分析技能是为开发者和高级用户设计的强大工具集，旨在精确监控其社交存在感。通过利用 Openclaw Skills，此集成提供了一种程序化方法来分析时间线参与度、追踪粉丝变化并管理书签。它专门为成本效益而设计，利用持久性本地存储来减少昂贵的 API 调用，同时提供透明的预算管理系统。

该技能使用户能够通过自动化的每日简报和问责检查保持信息灵通，无需手动浏览平台。它作为终端与 X API v2 之间的桥梁，确保通过可定制的预算层级和执行模式，使每一次交互都既是数据驱动的，又在财务上受到保护。

下载入口:https://github.com/openclaw/skills/tree/main/skills/nevaaron/x-smart-read

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

个人 X (Twitter) 分析 应用场景

• 生成全面的早间简报，包括帖子、提及和个人资料更新。
• 在特定的回顾期内监控账户参与度和粉丝增长趋势。
• 通过 URL 或 ID 获取并存档完整的推文线程或单个帖子。
• 进行问责检查，以监控个人活动水平和在平台上花费的时间。
• 管理书签并保存重要的推文，供未来参考或研究。

1. 用户通过运行设置脚本来初始化技能，以安全地存储 X API v2 凭据并定义每日预算层级。
2. 当触发命令时，系统首先根据本地持久性存储评估请求，查看是否可以在不产生费用的情况下提供数据。
3. 如果需要 API 调用，技能将根据选定的执行模式（受保护、宽松或无限制）验证剩余的每日预算。
4. 从 X API 获取数据，处理参与度指标，并同时缓存在本地存储中，以便将来零成本检索。
5. 该技能输出详细摘要，包括请求的数据以及交易成本和每日总支出的透明报告。

个人 X (Twitter) 分析 配置指南

要将此功能集成到您的 Openclaw Skills 工作流中，请确保已安装 uv 软件包管理器。首先运行交互式设置脚本来配置您的环境：

uv run scripts/x_setup.py

配置完成后，您可以使用以下命令验证您的凭据并查看支出报告：

# 验证您的设置
uv run scripts/x_setup.py --check

# 查看您当前的 API 支出
uv run scripts/x_setup.py --spend-report

个人 X (Twitter) 分析 数据架构与分类体系

该技能通过结构化的本地数据库和元数据分类法管理信息，以确保数据持久性和成本效率。

name: x-twitter
description: >
  Personal X (Twitter) analytics — timeline engagement, mentions, follower tracking,
  read any tweet/thread, bookmarks, and combined briefings via X API v2.
  Cost-optimized with persistent local store and daily budget guards.
metadata: {"openclaw":{"emoji":"??","requires":{"bins":["uv"]}}}

X (Twitter) Personal Analytics

Monitor your X account — posts, engagement, mentions, followers. Read any tweet. Built for daily briefings and accountability.

Triggers

Use this skill when the user asks about:

• Their X / Twitter posts, timeline, or engagement
• Mentions, replies, or who's talking about them on X
• Follower count, profile stats, follower growth
• "What's happening on my X?" / "How are my posts doing?"
• "Check my Twitter mentions" / "Any new replies?"
• Morning briefing / daily social media summary
• "Am I on X too much?" / accountability check
• Reading a specific tweet or thread (user sends a tweet URL)
• "What did @someone say?" / reading other people's tweets
• Bookmarking or saving tweets for later
• X/Twitter analytics or performance

Prerequisites

Run setup first (imports credentials from ~/.openclaw/.env or prompts interactively):

uv run scripts/x_setup.py

Commands

Briefing — combined morning summary

# Full briefing: your posts + mentions + profile (last 24h, ~$0.02)
uv run scripts/x_briefing.py

# Custom lookback period
uv run scripts/x_briefing.py --hours 48

# Preview cost
uv run scripts/x_briefing.py --dry-run

Timeline — your posts + engagement

# Recent posts with engagement metrics
uv run scripts/x_timeline.py recent

# Last 5 posts
uv run scripts/x_timeline.py recent --max 5

# Posts from last 24 hours
uv run scripts/x_timeline.py recent --hours 24

# Top posts by engagement (from local store, no API call)
uv run scripts/x_timeline.py top --days 7

# Refresh metrics for a specific tweet
uv run scripts/x_timeline.py refresh TWEET_ID

# Accountability check — are they on X right now?
uv run scripts/x_timeline.py activity

Mentions — who's talking to/about you

# Recent mentions
uv run scripts/x_mentions.py recent

# Mentions from last 24 hours
uv run scripts/x_mentions.py recent --hours 24

# Mentions with context (shows what they replied to — costs extra)
uv run scripts/x_mentions.py recent --context

Read — fetch any tweet or thread

# Read a tweet by URL
uv run scripts/x_read.py https://x.com/user/status/123456

# Read by bare ID
uv run scripts/x_read.py 123456

# Fetch full thread
uv run scripts/x_read.py 123456 --thread

# Preview cost
uv run scripts/x_read.py --dry-run https://x.com/user/status/123456

Bookmarks — save and manage

# List your bookmarks
uv run scripts/x_bookmarks.py list

# Bookmark a post
uv run scripts/x_bookmarks.py add TWEET_ID

# Remove a bookmark
uv run scripts/x_bookmarks.py remove TWEET_ID

User Profile — stats + follower tracking

# Your profile stats
uv run scripts/x_user.py me

# Track follower changes over time
uv run scripts/x_user.py me --track

# Look up another user
uv run scripts/x_user.py lookup someuser

Setup & Spend

# Validate credentials
uv run scripts/x_setup.py --check

# Show config (secrets redacted)
uv run scripts/x_setup.py --show

# Weekly spend summary
uv run scripts/x_setup.py --spend-report

# 30-day spend report
uv run scripts/x_setup.py --spend-report --days 30

# Set budget mode
uv run scripts/x_setup.py --budget-mode relaxed

# Print version
uv run scripts/x_setup.py --version

Cost Control Flags (all scripts)

# Preview cost without making the API call
uv run scripts/x_timeline.py --dry-run recent

# Override budget guard
uv run scripts/x_timeline.py --force recent

# Skip all budget checks and warnings
uv run scripts/x_timeline.py --no-budget recent

Workflows

Morning Brief

uv run scripts/x_briefing.py

Single command replaces running timeline + mentions + user separately. Costs ~$0.02.

Accountability Check

uv run scripts/x_timeline.py activity

Use this when the user should be working — it shows when they last posted and how active they've been. Nudge them if they're spending too much time on X.

Weekly Review

uv run scripts/x_timeline.py top --days 7
uv run scripts/x_user.py me --track

Agent Guidelines — READ THIS BEFORE CALLING ANY COMMAND

Every command costs real money. The X API charges per request. Follow these rules to minimize spend:

Rules

1. Never call the same command twice in one conversation unless the user explicitly asks for fresh data. The scripts cache locally — if you already ran recent this session, just reference those results.
2. Prefer top over recent for repeat questions. top reads from the local store for free ($0). recent hits the API ($0.005).
3. Don't use --context on mentions by default. It costs an extra $0.005 per reply thread it fetches. Only add it if the user specifically asks "what were they replying to?"
4. Use --max 5 for quick checks. Default is 10-20. If the user just wants a summary, pull fewer.
5. Use --hours 24 for briefings. Don't pull the full timeline when they just want "what happened today."
6. Never run all scripts unprompted. If the user asks "what's happening on my X?", use x_briefing.py instead of running 3 separate commands.
7. For accountability checks, use activity only. It's a single API call. Don't also pull mentions and profile — that triples the cost.
8. top and refresh are your friends. top is free (local data). refresh TWEET_ID updates just one tweet ($0.005) — use it when they ask "how's my last post doing?" instead of re-pulling the whole timeline.
9. Watch the daily spend total. Every command output shows "Today's spend: $X.XXX". If it's approaching the budget limit, tell the user before making more calls.
10. Never loop or retry on your own. If a command fails (402, rate limit, etc.), report the error. Don't retry automatically.
11. x_read.py caches tweets — if the user asks about the same tweet again, it's already in the local store. No need to re-fetch.
12. Use x_briefing.py for morning briefings instead of running timeline + mentions + user separately. It's cheaper ($0.02 vs $0.02 for 3 separate commands) and cleaner output.

Cost Reference

Budget Modes

The user can set a budget enforcement mode via x_setup.py --budget-mode:

• guarded (default): Warn at 50/80/100%, block at limit
• relaxed: Warn at 50/80/100%, never block
• unlimited: No warnings, no blocks

Budget Tiers

The user set a daily budget during setup. The scripts will warn and block when the limit is hit:

• lite: $0.03/day (~1 briefing)
• standard: $0.10/day (~3-5 checks)
• intense: $0.25/day (~10+ checks)

If blocked, tell the user: "Daily X API budget reached. Use --force to override, or wait until tomorrow."

What NOT to do

• Don't run commands "just to have fresh data" — only fetch when the user needs it
• Don't use --no-cache unless debugging
• Don't call user lookup on multiple accounts in a loop
• Don't refresh every tweet's metrics — only refresh specific ones the user asks about
• Don't combine recent + mentions + user in one response — use x_briefing.py instead