agentleFS
weininghuiweininghui/skills/x-bookmarks/SKILL.md

x-bookmarks

Skill1 starsChanged 17 days agoMITView on GitHub

Fetch, summarize, and manage X/Twitter bookmarks via the `bird` CLI. Use when: (1) user says \"check my bookmarks\", \"what did I bookmark\", \"bookmark digest\", \"summarize my bookmarks\", \"x bookmarks\", \"twitter bookmarks\", (2) user wants a periodic digest of saved tweets, (3) user wants to categorize, search, or analyze their bookmarks, (4) scheduled bookmark digests via cron. Requires `bird` CLI (npm i -g bird-cli) and X/Twitter authentication via browser cookies or manual tokens.

  • Reads credentials
  • Installs packages

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Core philosophy: Don't just summarize — propose actions the agent can execute.

    line 10
  2. Very specific:

    If user has a .env.bird file or env vars AUTH_TOKEN/CT0, source them first: source .env.bird

    line 44
  3. Distinctive:

    When user asks for content ideas from bookmarks:

    line 103
  4. Distinctive:

    When user has enough bookmark history:

    line 111
  5. Very specific:

    Start with -n 20 for quick digests, --all for deep analysis

    line 136
  6. Very specific:

    Use --include-parent to get thread context for replies

    line 137
  7. Very specific:

    Add --sort-chronological for time-ordered output

    line 139

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

X Bookmarks

Turn X/Twitter bookmarks from a graveyard of good intentions into actionable work.

Core philosophy: Don't just summarize — propose actions the agent can execute.

Prerequisites

  • bird CLI: npm install -g bird-cli (v0.8+)
  • Auth (one of):
    • --chrome-profile <name> — auto-extracts cookies from Chrome (recommended)
    • --firefox-profile <name> — Firefox equivalent
    • Manual: --auth-token <token> --ct0 <token> from browser dev tools
    • Config: ~/.config/bird/config.json5 with { chromeProfile: "Default" }
  • See references/auth-setup.md for detailed setup guide

Fetching Bookmarks

# Latest 20 bookmarks (default)
bird bookmarks --json

# Specific count
bird bookmarks -n 50 --json

# All bookmarks (paginated)
bird bookmarks --all --json

# With thread context
bird bookmarks --include-parent --thread-meta --json

# With Chrome cookie auth
bird --chrome-profile "Default" bookmarks --json

# With manual tokens
bird --auth-token "$AUTH_TOKEN" --ct0 "$CT0" bookmarks --json

If user has a .env.bird file or env vars AUTH_TOKEN/CT0, source them first: source .env.bird

JSON Output Format

Each bookmark returns:

{
  "id": "tweet_id",
  "text": "tweet content",
  "createdAt": "Wed Feb 11 01:00:06 +0000 2026",
  "replyCount": 46,
  "retweetCount": 60,
  "likeCount": 801,
  "author": { "username": "handle", "name": "Display Name" },
  "media": [{ "type": "photo|video", "url": "..." }],
  "quotedTweet": { ... }
}

Core Workflows

1. Action-First Digest (Primary Use Case)

The key differentiator: don't just summarize, propose actions the agent can execute.

  1. Fetch bookmarks: bird bookmarks -n <count> --json
  2. Parse and categorize by topic (auto-detect: crypto, AI, marketing, tools, personal, etc.)
  3. For EACH category, propose specific actions:
    • Tool/repo bookmarks → "I can test this, set it up, or analyze the code"
    • Strategy/advice bookmarks → "Here are the actionable steps extracted — want me to implement any?"
    • News/trends → "This connects to [user's work]. Here's the angle for content"
    • Content ideas → "This would make a great tweet/video in your voice. Here's a draft"
    • Questions/discussions → "I can research this deeper and give you a summary"
  4. Flag stale bookmarks (>2 weeks old) — "Use it or lose it"
  5. Deliver categorized digest with actions

Format output as:

📂 CATEGORY (count)
• Bookmark summary (@author)
→ 🤖 I CAN: [specific action the agent can take]

2. Scheduled Digest (Cron)

Set up a recurring bookmark check. Suggest this cron config to the user:

Schedule: daily or weekly
Payload: "Check my X bookmarks for new saves since last check.
  Fetch bookmarks, compare against last digest, summarize only NEW ones.
  Categorize and propose actions. Deliver to me."

Track state by saving the most recent bookmark ID processed. Store in workspace: memory/bookmark-state.json → { "lastSeenId": "...", "lastDigestAt": "..." }

3. Content Recycling

When user asks for content ideas from bookmarks:

  1. Fetch recent bookmarks
  2. Identify high-engagement tweets (>500 likes) with frameworks, tips, or insights
  3. Rewrite key ideas in the user's voice (if voice data available)
  4. Suggest posting times based on the bookmark's original engagement

4. Pattern Detection

When user has enough bookmark history:

  1. Fetch all bookmarks (--all)
  2. Cluster by topic/keywords
  3. Report: "You've bookmarked N tweets about [topic]. Want me to go deeper?"
  4. Suggest: research reports, content series, or tools based on patterns

5. Bookmark Cleanup

For stale bookmarks:

  1. Identify bookmarks older than a threshold (default: 30 days)
  2. For each: extract the TL;DR and one actionable takeaway
  3. Present: "Apply it today or clear it"
  4. User can unbookmark via: bird unbookmark <tweet-id>

Error Handling

ErrorCauseFix
"No Twitter cookies found"Not logged into X in browserLog into x.com in Chrome/Firefox
EPERM on Safari cookiesmacOS permissionsUse Chrome or Firefox instead
Empty resultsCookies expiredRe-login to x.com, retry
Rate limitToo many requestsWait and retry, use --max-pages to limit

Tips

  • Start with -n 20 for quick digests, --all for deep analysis
  • Use --include-parent to get thread context for replies
  • Bookmark folders are supported via --folder-id <id>
  • Add --sort-chronological for time-ordered output

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.