agentleFS
baofeng-techbaofeng-tech/agent-skills-so/openclaw-twitter/SKILL.md

openclaw-twitter

Skill0 starsChanged 7 months agoMITView on GitHub

Search X/Twitter profiles, tweets, trends, lists, communities, and Spaces through the AISA relay, then publish approved posts with OAuth. Use when: the user asks for Twitter/X research, monitoring, or posting without sharing passwords. Supports read APIs, authorization links, and media-aware posting.

  • 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:

    All network calls go to https://api.aisa.one/apis/v1/....

    line 44
  2. Distinctive:

    Read user data, timelines, mentions, followers, followings, verified followers, and follow relationships.

    line 48
  3. Distinctive:

    Search tweets and users, inspect replies, quotes, retweeters, thread context, and Spaces.

    line 49
  4. Very specific:

    When the user asks to send, publish, reply, or quote on X/Twitter, follow ./references/post_twitter.md.

    line 66
  5. Very specific:

    Use --media-file only for user-provided workspace files.

    line 69
  6. Distinctive:

    Do not invent captions, remote URLs, or extra media attachments.

    line 70

≈ “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

Twitter

Runtime-focused skill package for Twitter/X search and posting through the AISA relay.

When to use

  • The user wants to read profiles, timelines, mentions, followers, tweet search results, trends, lists, communities, or Spaces.
  • The user wants to draft or publish posts after completing OAuth without sharing passwords.
  • The task needs a Python client for repeatable Twitter/X automation backed by AISA_API_KEY.

When NOT to use

  • The user needs cookie extraction, browser credential scraping, or direct password login.
  • The workflow must avoid sending requests, OAuth state, or approved media through api.aisa.one.
  • The request is for likes, follows, or other engagement actions not covered by this package.

Quick Reference

  • Required env: AISA_API_KEY
  • Read client: ./scripts/twitter_client.py
  • Post workflow guide: ./references/post_twitter.md

Setup

export AISA_API_KEY="your-key"

All network calls go to https://api.aisa.one/apis/v1/....

Capabilities

  • Read user data, timelines, mentions, followers, followings, verified followers, and follow relationships.
  • Search tweets and users, inspect replies, quotes, retweeters, thread context, and Spaces.
  • Publish text, image, and video posts after explicit OAuth approval.
  • Split long posts into threaded chunks when the publish script needs it.

Common Commands

python3 scripts/twitter_client.py user-info --username elonmusk
python3 scripts/twitter_client.py search --query "AI agents" --type Latest
python3 scripts/twitter_client.py trends --woeid 1
python3 scripts/twitter_oauth_client.py status
python3 scripts/twitter_oauth_client.py authorize
python3 scripts/twitter_oauth_client.py post --text "Hello from AIsa"

Posting Workflow

When the user asks to send, publish, reply, or quote on X/Twitter, follow ./references/post_twitter.md.

  • Return the authorization link first when posting is not yet approved.
  • Use --media-file only for user-provided workspace files.
  • Do not invent captions, remote URLs, or extra media attachments.

Runtime Boundary

  • The package is relay-based: read calls, OAuth requests, and approved media uploads go to api.aisa.one.
  • The package is API-key-first: it requires AISA_API_KEY and does not ask for passwords, cookies, CT0, or other legacy secrets.
  • The package does not include cache sync, self-install logic, home-directory persistence, browser-cookie extraction, or external agent CLI wrappers.
  • Browser opening is optional and not the default workflow; returning the authorization link is the preferred path for this release.

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.