Description

Automatically scrapes, categorizes, and summarizes your X bookmarks into actionable insights delivered to your preferred messaging channel for easy review.

README (SKILL.md)

ADHD X Bookmark Analysis

Name: ADHD X Bookmark Analyzer
Author: adambrainai

Your bookmarks are a graveyard. This brings them back to life.

What This Skill Does

You bookmark 50 tweets a day. You read maybe 2. That thread about the $200K agency architecture? Buried. The AI tool that would save you hours? Forgotten.

This skill turns your X bookmark chaos into actionable intelligence. Your agent scrapes your bookmarks, categorizes them by topic, extracts the key insights, and delivers a summary to your preferred channel.

No more bookmark graveyards. No more "I saved something about that..." Just organized, searchable knowledge from everything you thought was worth saving.

Built for ADHD brains who collect everything and process nothing.

Capabilities

✅ Automatic X bookmark scraping (scheduled or on-demand)
✅ Smart categorization by topic (AI, business, tools, threads)
✅ Key insight extraction from threads and long-form content
✅ Channel delivery (Discord, Slack, Telegram, or file-only)
✅ Searchable archive of everything you saved

Requirements

X Authentication (Required)

Option A: bird CLI (Recommended)

# Install bird CLI
npm install -g bird-cli

# Authenticate (opens browser for OAuth)
bird login

# Verify access
bird whoami
bird bookmarks --limit 5

Credentials are stored securely in ~/.bird/ by the CLI. The skill never handles raw tokens directly.

Option B: Browser Session (Advanced)

If you prefer browser cookies:

Log into X in Chrome/Safari
OpenClaw's browser tool can access your session
Less reliable than bird CLI — session expires, requires re-login

⚠️ Security Note: Never paste raw session cookies into config files. Use bird CLI for persistent, secure auth.

Message Delivery (Optional)

To receive summaries in Discord/Slack/Telegram, configure via environment variables (not plaintext files):

# Discord (using OpenClaw's built-in message tool)
# No extra config needed — just specify channel ID in your prompt

# Or use a webhook (store securely):
export BOOKMARK_DISCORD_WEBHOOK="https://discord.com/api/webhooks/..."

# Slack
export BOOKMARK_SLACK_WEBHOOK="https://hooks.slack.com/services/..."

The skill reads these from environment. Never commit webhooks to files.

Installation

clawhub install adhd-bookmark-analyzer

Or manually copy to your workspace:

~/.openclaw/workspace/skills/adhd-bookmark-analyzer/
├── SKILL.md           # This file (instructions for your agent)
├── bookmark-rules.md  # Categorization logic & settings

Usage

On-Demand Analysis

Just ask your agent:

"Analyze my X bookmarks from this week"
"What did I bookmark about AI agents?"
"Summarize my bookmarks and send to Discord"

The agent will:

Run bird bookmarks to fetch your saves
Categorize and extract insights per bookmark-rules.md
Deliver summary to your specified channel (or just reply inline)

Scheduled Daily Reports

Add to your agent's cron schedule (via OpenClaw cron or HEARTBEAT.md):

# Daily at 9 AM: Analyze yesterday's bookmarks
"Check my X bookmarks from the last 24 hours, categorize them, and post summary to Discord channel 123456789"

Search Your Archive

"Search my bookmark archive for 'pricing strategy'"

The agent searches bookmark-archive/ and returns matching entries with context.

Example Output

📚 X Bookmark Summary — Feb 15, 2026

You saved 18 bookmarks in the last 24 hours:

🤖 AI & Tech Tools (7)
• New Claude API pricing ($0.25/M output tokens)
• OpenClaw 0.7.0 release notes  
• Thread on RAG vs fine-tuning tradeoffs

💼 Business & Strategy (5)
• How @username built $50K MRR with AI agents
• Pricing psychology thread (15 tactics)
• Case study: AI replacing $200K/year ops role

🔧 Development & Code (4)
• Python async patterns for LLM calls
• GitHub repo: AI code review automation

📖 Threads Worth Reading (2)
• @username's 20-tweet thread on AI safety
• Founder story: 0 to $1M in 8 months

Categorization

Default categories in bookmark-rules.md:

Category	Matches
AI & Tech Tools	Product launches, tool reviews, API updates
Business & Strategy	Growth tactics, pricing, case studies
Development & Code	Code snippets, repos, technical threads
Threads Worth Reading	Long-form content, storytelling
Resources	Books, courses, guides, lists
Other	Doesn't fit above

Customize by editing bookmark-rules.md:

categories:
  - name: "Indie Hacking"
    keywords: ["indie hacker", "SaaS", "MRR", "bootstrap"]
  - name: "Crypto Alpha"
    keywords: ["alpha", "degen", "airdrop", "farming"]

File Structure

After running, the skill creates:

~/.openclaw/workspace/skills/adhd-bookmark-analyzer/
├── SKILL.md              # Instructions (this file)
├── bookmark-rules.md     # Categories & settings
└── bookmark-archive/     # Created by agent
    ├── 2026-02-15.json   # Daily snapshots
    └── index.json        # Searchable index

Security Notes

Authentication: Use bird login for X access. Credentials stored in ~/.bird/, managed by the CLI.
Webhooks: Store Discord/Slack webhook URLs in environment variables, not config files:
```
export BOOKMARK_DISCORD_WEBHOOK="https://..."
```
Data Storage: Bookmark archives are stored locally in your workspace. No data is sent to external services except your configured delivery channel.
Permissions: The skill only reads your bookmarks and writes to your local archive. It does not post to X, modify bookmarks, or access DMs.

Troubleshooting

"No bookmarks found"

bird whoami          # Check auth
bird bookmarks --limit 1  # Test access

Categories seem wrong

Edit keywords in bookmark-rules.md
Add domain-specific terms for your niche

Want file-only (no notifications)

Just don't configure a webhook
Ask agent to "save to archive only"

Tips

Bookmark liberally — The skill handles organization
Review weekly — Skim the summaries, dig into what matters
Customize categories — Match your actual interests
Use search — Your archive becomes a second brain

The goal: Make the good stuff findable when you need it. Not inbox zero for bookmarks — just signal over noise.

Usage Guidance

Before installing or enabling this skill: 1) Verify you want a tool to read and archive your X bookmarks and to optionally post summaries to external channels. 2) Vet the recommended bird-cli npm package (publisher, source repo, and permissions) before installing; consider running bird CLI commands manually to confirm behavior. 3) Prefer bird CLI OAuth over pasting cookies; avoid giving the agent direct access to browser sessions if you can. 4) If you must configure delivery, store webhook URLs in a secrets manager or environment variables and limit their scope; test with file-only delivery first. 5) Confirm you are comfortable with the skill writing archives to ~/.openclaw/workspace/... and review those files periodically. 6) If you want higher assurance, ask the author for a link to the bird-cli project and a minimal example run or request the skill include an explicit list of required binaries/env vars in its registry metadata. If the skill later includes code that sends data to unknown endpoints or requests additional credentials, treat it as higher risk.

Capability Analysis

Type: OpenClaw Skill Name: adhd-bookmark-analyzer Version: 1.0.1 The skill 'adhd-bookmark-analyzer' is designed to scrape, categorize, and summarize X (formerly Twitter) bookmarks. Its instructions in SKILL.md and configuration in bookmark-rules.md are transparent and align with its stated purpose. It instructs the agent to use the `bird` CLI to fetch bookmarks and store processed data locally in `bookmark-archive/`. Summaries are sent to user-configured Discord/Slack webhooks, with explicit statements that no data is sent to other external services. There is no evidence of intentional data exfiltration, unauthorized command execution, persistence mechanisms, or malicious prompt injection attempts against the agent. While the agent's execution of `bird bookmarks` could be a shell injection vulnerability if not properly sanitized by the OpenClaw platform, this is a platform vulnerability, not malicious intent within the skill itself.

Capability Assessment

ℹ Purpose & Capability

The name and description match the runtime instructions: fetch X bookmarks, categorize, summarize, and deliver to a channel or archive locally. However, the registry metadata declares no required binaries or env vars while the SKILL.md expects the 'bird' CLI or browser session access and local archive writes. That mismatch (documented runtime dependencies not reflected in metadata) is unexpected and should be reconciled.

⚠ Instruction Scope

Instructions explicitly tell the agent to run `bird bookmarks`, read bookmark data, write a local archive under ~/.openclaw/workspace/skills/..., and optionally deliver summaries to external webhooks or OpenClaw messaging. The SKILL.md also suggests using OpenClaw's browser tool to access your logged-in session (browser cookies). Reading browser sessions/cookies and using external webhooks are legitimate for this task but increase exposure; the SKILL.md does not clearly limit what session data is accessed or how it's protected.

ℹ Install Mechanism

This is an instruction-only skill (no install spec), which is low risk. However the docs recommend installing `bird-cli` via npm (`npm install -g bird-cli`). Because the skill relies on a third-party npm CLI, users should vet that package (its publisher, permissions, and behavior) before installing. The skill itself does not automate this install.

⚠ Credentials

Registry metadata lists no required env vars, but the SKILL.md expects users to optionally set webhook URLs (BOOKMARK_DISCORD_WEBHOOK, BOOKMARK_SLACK_WEBHOOK). Those are sensitive secrets and the skill will read them from the environment at runtime. The documentation claims credentials for X are stored by bird CLI in ~/.bird/ and that the skill 'never handles raw tokens directly' — reasonable if you trust bird-cli — but the SKILL.md also offers a browser-cookie option which could expose more data. The skill will also write archives to the user's workspace; that filesystem access is not declared in metadata.

ℹ Persistence & Privilege

always is false (normal). The skill recommends adding a scheduled cron job for regular runs, which is user-controlled. Scheduled/autonomous runs combined with external delivery channels (webhooks) increase the impact of any misconfiguration, but the skill does not request permanent platform-wide privileges or modify other skills.

Version History

v1.0.1

Security fixes: clarified credential handling, removed references to non-existent script, added env var guidance for webhooks

v1.0.0

Initial release: Turn your X bookmark graveyard into organized, searchable intelligence

Metadata

Slug adhd-bookmark-analyzer

Version 1.0.1

License —

All-time Installs 1

Active Installs 1

Total Versions 2

Frequently Asked Questions

What is ADHD X Bookmark Analyzer?

Automatically scrapes, categorizes, and summarizes your X bookmarks into actionable insights delivered to your preferred messaging channel for easy review. It is an AI Agent Skill for Claude Code / OpenClaw, with 384 downloads so far.

How do I install ADHD X Bookmark Analyzer?

Run "/install adhd-bookmark-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is ADHD X Bookmark Analyzer free?

Yes, ADHD X Bookmark Analyzer is completely free (open-source). You can download, install and use it at no cost.

Which platforms does ADHD X Bookmark Analyzer support?

ADHD X Bookmark Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created ADHD X Bookmark Analyzer?

It is built and maintained by adambrainai (@adambrainai); the current version is v1.0.1.

More Skills

ADHD X Bookmark Analyzer