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

aisa-twitter-api

Skill0 starsChanged 7 months agoMITView on GitHub

Twitter/X research, monitoring, watchlists, and OAuth-approved posting through AIsa. Use when: the user needs one flagship Twitter skill for trend tracking, competitor monitoring, timeline analysis, watchlist review, or approved posting through the relay without sharing passwords. Supports relay-based reads, search, watchlists, and OAuth-gated text or media posting through https://api.aisa.one.

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. About 0 are common, 13 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    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. Distinctive:

    When the user needs one primary Twitter/X skill for search, monitoring, trend discovery, timeline review, watchlists, or content research.

    line 23
  2. Distinctive:

    When the user wants to inspect profiles, timelines, mentions, trends, replies, quotes, lists, communities, or Spaces from one command …

    line 24
  3. Distinctive:

    When the user wants to draft or publish posts after explicit OAuth approval without sharing passwords or browser cookies.

    line 25
  4. Very specific:

    When the workflow should use AISA_API_KEY and relay-based access to https://api.aisa.one instead of local credential extraction.

    line 26
  5. Distinctive:

    Do NOT use this for password-based login, cookie extraction, or browser credential scraping.

    line 30
  6. Very specific:

    Do NOT use this when the workflow must avoid relay-based requests to https://api.aisa.one.

    line 31
  7. Very specific:

    Do NOT use this as the primary skill for like, follow, reply, or growth-action workflows better handled by aisa-twitter-engagement-suite.

    line 32
  8. Distinctive:

    Read behavior: Twitter/X read requests are sent through the relay

    line 42
  9. Distinctive:

    Read user data, timelines, mentions, followers, followings, and related profile information.

    line 63
  10. Distinctive:

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

    line 64
  11. Distinctive:

    Run watchlist, monitoring, and research workflows from one Twitter/X command surface.

    line 65
  12. Distinctive:

    Do not ask for Twitter/X passwords or browser cookies.

    line 85
  13. Distinctive:

    Do not invent captions, tweet URLs, or attachment files.

    line 86
  14. Distinctive:

    Do not claim external posting succeeded until the API confirms success.

    line 87
  15. Distinctive:

    Do not imply OAuth is optional for posting.

    line 88
  16. Distinctive:

    Read operations use the relay path.

    line 100

≈ “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

AIsa Twitter API Command Center

Flagship Twitter/X skill for research, monitoring, watchlists, and OAuth-approved posting through the AIsa relay at https://api.aisa.one.

When to use

  • When the user needs one primary Twitter/X skill for search, monitoring, trend discovery, timeline review, watchlists, or content research.
  • When the user wants to inspect profiles, timelines, mentions, trends, replies, quotes, lists, communities, or Spaces from one command surface.
  • When the user wants to draft or publish posts after explicit OAuth approval without sharing passwords or browser cookies.
  • When the workflow should use AISA_API_KEY and relay-based access to https://api.aisa.one instead of local credential extraction.

When NOT to use

  • Do NOT use this for password-based login, cookie extraction, or browser credential scraping.
  • Do NOT use this when the workflow must avoid relay-based requests to https://api.aisa.one.
  • Do NOT use this as the primary skill for like, follow, reply, or growth-action workflows better handled by aisa-twitter-engagement-suite.

Quick Reference

  • Required environment variable: AISA_API_KEY
  • Required binary: python3
  • Read client: scripts/twitter_client.py
  • OAuth and posting client: scripts/twitter_oauth_client.py
  • Posting guide: references/post_twitter.md
  • Relay target: https://api.aisa.one
  • Read behavior: Twitter/X read requests are sent through the relay
  • OAuth behavior: posting requires explicit user approval through the OAuth flow
  • External writes: posting happens only after explicit OAuth approval
  • Upload behavior: image and video posting sends user-selected media through the relay

Setup

export AISA_API_KEY="your-key"

Requirements:

  • python3
  • AISA_API_KEY
  • Internet access to https://api.aisa.one
  • Explicit OAuth approval before posting
  • User-provided media files when posting images or videos

Capabilities

  • Read user data, timelines, mentions, followers, followings, and related profile information.
  • Search tweets and users, inspect replies, quotes, retweeters, thread context, trends, lists, communities, and Spaces.
  • Run watchlist, monitoring, and research workflows from one Twitter/X command surface.
  • Publish text, image, and video posts after explicit OAuth approval.

High-Intent Workflows

  • Research a creator, competitor, brand, or narrative before writing.
  • Monitor a keyword, launch, or watchlist and pull representative tweets quickly.
  • Review timelines, mentions, replies, and trend movement from one command surface.
  • Draft and publish a post only after the user explicitly approves OAuth.

Common Commands

python3 scripts/twitter_client.py search --query "AI agents" --type Latest
python3 scripts/twitter_oauth_client.py authorize
python3 scripts/twitter_oauth_client.py post --text "Hello from AIsa"

Guardrails

  • Do not ask for Twitter/X passwords or browser cookies.
  • Do not invent captions, tweet URLs, or attachment files.
  • Do not claim external posting succeeded until the API confirms success.
  • Do not imply OAuth is optional for posting.

Example Requests

  • Research what builders on X are saying about AI agents this week.
  • Track reactions to our product launch and pull representative tweets.
  • Build a small watchlist of competitor accounts and summarize what changed today.
  • Authorize and publish a short Twitter post with an attached image.

Security Notes

  • This skill sends Twitter/X API requests through the relay target https://api.aisa.one.
  • Read operations use the relay path.
  • OAuth authorization and posting also use the relay path and require explicit user approval before any external write can occur.
  • Approved image and video posting sends user-selected media through the relay for upload.
  • Required secret: AISA_API_KEY.
  • This workflow does not require passwords or browser cookie extraction.

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.