agentleFS
alanalvestechalanalvestech/hitank/skills/x/SKILL.md

x

Skill38 starsChanged 8 months agoMITView on GitHub

Post and manage tweets on X (formerly Twitter) via API v2

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the output is OK, proceed to the Flow section.

    line 35
  2. Very specific:

    If the output is SETUP_NEEDED, guide the user step by step.

    line 37
  3. Distinctive:

    If the script outputs an error, the credentials are invalid.

    line 69
  4. Distinctive:

    Ask the user what they want to do:

    line 87
  5. Very specific:

    If $ARGUMENTS looks like tweet text (not a number), offer to post it.

    line 97
  6. Distinctive:

    Ask the user to type the tweet text.

    line 103

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Connect to the X (formerly Twitter) API v2 to post tweets, search, view timelines and manage likes. Pure Ruby, zero gems — stdlib only.

Structure

scripts/
├── auth.rb          # OAuth 1.0a signature + twitter_request helper (required by all scripts)
├── check_setup.rb   # Check if credentials exist (outputs OK or SETUP_NEEDED)
├── save_token.rb    # Save and validate API credentials
├── me.rb            # Get authenticated user info
├── tweets.rb        # List recent tweets for a user
├── tweet.rb         # Get tweet details by ID
├── post_tweet.rb    # Post a new tweet (requires confirmation)
├── delete_tweet.rb  # Delete a tweet (requires confirmation)
├── search.rb        # Search recent tweets
├── likes.rb         # List liked tweets
└── like.rb          # Like a tweet (requires confirmation)

Setup (check before using)

ruby ~/.claude/skills/x/scripts/check_setup.rb

If the output is OK, proceed to the Flow section.

If the output is SETUP_NEEDED, guide the user step by step. Present ONE step at a time, wait for the user to confirm before moving to the next.

Step 1 — Ask the user to create a Twitter Developer app:

You need Twitter API credentials. Go to the Developer Portal and create a project and app:

https://developer.x.com/en/portal/dashboard

  1. Create a new Project (or use an existing one)
  2. Create an App inside that project

Step 2 — Ask the user to generate credentials:

In your app settings, go to "Keys and tokens" and generate all 4 credentials:

  • API Key (also called Consumer Key)
  • API Key Secret (also called Consumer Secret)
  • Access Token
  • Access Token Secret

Copy all 4 values.

Step 3 — Ask the user to check permissions:

Make sure your app has Read and Write permissions. You can check this under your app's "User authentication settings" in the Developer Portal.

Step 4 — When the user pastes the credentials, save them:

ruby ~/.claude/skills/x/scripts/save_token.rb 'API_KEY' 'API_SECRET' 'ACCESS_TOKEN' 'ACCESS_TOKEN_SECRET'

If the script outputs an error, the credentials are invalid. Ask the user to double-check and try again.

If setup is not complete, DO NOT proceed to the Flow. Complete all steps first.

Flow

The argument $ARGUMENTS may contain tweet text or a tweet ID.

Step 1: Check account info

ruby ~/.claude/skills/x/scripts/me.rb

Present the account info to the user.

Step 2: Present options

Ask the user what they want to do:

  • Post a tweet
  • List recent tweets
  • Search tweets
  • View a tweet
  • Delete a tweet
  • View liked tweets
  • Like a tweet

If $ARGUMENTS looks like tweet text (not a number), offer to post it. If it looks like a tweet ID (numeric), offer to view it.

Step 3: Actions

Post a tweet (requires user confirmation):

Ask the user to type the tweet text. Show a preview of the tweet and its character count. Ask: "Do you want to post this tweet?" Only execute after a "yes".

ruby ~/.claude/skills/x/scripts/post_tweet.rb 'TWEET_TEXT'

List recent tweets:

ruby ~/.claude/skills/x/scripts/tweets.rb
ruby ~/.claude/skills/x/scripts/tweets.rb --user_id USER_ID

View a tweet:

ruby ~/.claude/skills/x/scripts/tweet.rb TWEET_ID

Search recent tweets:

ruby ~/.claude/skills/x/scripts/search.rb 'SEARCH_QUERY'

Delete a tweet (requires user confirmation):

Show the tweet details first, then ask: "Do you want to delete this tweet?" Only execute after a "yes".

ruby ~/.claude/skills/x/scripts/delete_tweet.rb TWEET_ID

View liked tweets:

ruby ~/.claude/skills/x/scripts/likes.rb
ruby ~/.claude/skills/x/scripts/likes.rb --user_id USER_ID

Like a tweet (requires user confirmation):

Show the tweet details first, then ask: "Do you want to like this tweet?" Only execute after a "yes".

ruby ~/.claude/skills/x/scripts/like.rb TWEET_ID

Notes

  • Pure Ruby, zero gems — stdlib only (json, net/http, uri, fileutils, openssl, base64, securerandom)
  • OAuth 1.0a with HMAC-SHA1 signature — full signature generation implemented in auth.rb
  • Twitter API v2 endpoints — all scripts use the v2 API
  • Free tier allows 1,500 tweets/month (posting) and limited reads
  • Token files stored at ~/.config/x/ (4 files, never commit)
  • Post, delete, and like require explicit user confirmation
  • Base URL: https://api.twitter.com

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.