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

aisa-twitter-engagement-suite

Skill0 starsChanged 7 months agoMITView on GitHub

Research Twitter/X profiles, tweets, and trends, then take approved engagement or posting follow-through through the AIsa relay. Use when: the user needs Twitter/X research plus likes, follows, unfollows, posting, or post-action follow-through without sharing passwords. Supports relay-based reads, OAuth-approved writes, and media-capable posting flows.

  • Reads credentials

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 9 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user needs Twitter/X research plus action-oriented follow-through such as posting, liking, unliking, following, or unfollowing.

    line 23
  2. Very specific:

    When the workflow should keep research and approved write actions in one package while using only AISA_API_KEY for the shipped runtime.

    line 24
  3. Very specific:

    When the task can use the bundled Python clients with network access to api.aisa.one.

    line 25
  4. Distinctive:

    When the user can complete explicit OAuth approval before write actions or media posting.

    line 26
  5. Distinctive:

    When relay-based Twitter/X reads, writes, and media upload are acceptable and the user should not share passwords.

    line 27
  6. Distinctive:

    Do not use this for cookie extraction, password login, or a fully local Twitter/X client.

    line 31
  7. Very specific:

    Do not use this when the workflow must avoid relay-based network calls, remote writes, or relay-based media upload through api.aisa.one.

    line 32
  8. Distinctive:

    Do not use this for undocumented secrets, browser-derived auth values, or hidden credential flows.

    line 33
  9. Very specific:

    Do not use this when the user needs the broader flagship Twitter lane.

    line 34
  10. Very specific:

    Do not use this for watchlists, trend desks, or recurring monitoring-first workflows better matched to aisa-twitter-command-center.

    line 35
  11. Distinctive:

    Keep research and engagement follow-through in one package while making relay target, OAuth approval, upload behavior, and env requirements …

    line 76
  12. Distinctive:

    Run post-research engagement follow-through where remote reads, remote writes, and relay-based media upload are acceptable.

    line 83
  13. Very specific:

    All networked operations go through the AIsa relay at api.aisa.one.

    line 94
  14. Distinctive:

    Write actions require explicit OAuth approval before they can succeed.

    line 96
  15. Distinctive:

    Do not claim a post, like, follow, or unfollow succeeded until the API confirms it.

    line 99

≈ “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 Engagement Suite

Research Twitter/X profiles, tweets, and trends, then take approved engagement or posting follow-through through the AIsa relay.

When to use

  • When the user needs Twitter/X research plus action-oriented follow-through such as posting, liking, unliking, following, or unfollowing.
  • When the workflow should keep research and approved write actions in one package while using only AISA_API_KEY for the shipped runtime.
  • When the task can use the bundled Python clients with network access to api.aisa.one.
  • When the user can complete explicit OAuth approval before write actions or media posting.
  • When relay-based Twitter/X reads, writes, and media upload are acceptable and the user should not share passwords.

When NOT to use

  • Do not use this for cookie extraction, password login, or a fully local Twitter/X client.
  • Do not use this when the workflow must avoid relay-based network calls, remote writes, or relay-based media upload through api.aisa.one.
  • Do not use this for undocumented secrets, browser-derived auth values, or hidden credential flows.
  • Do not use this when the user needs the broader flagship Twitter lane; use aisa-twitter-api for that surface.
  • Do not use this for watchlists, trend desks, or recurring monitoring-first workflows better matched to aisa-twitter-command-center.

Quick Reference

NeedPath / Requirement
API keyAISA_API_KEY
Required binarypython3
Relay targetapi.aisa.one
Read clientscripts/twitter_client.py
Post clientscripts/twitter_oauth_client.py
Engage clientscripts/twitter_engagement_client.py
Referencesreferences/post_twitter.md, references/engage_twitter.md

Setup

export AISA_API_KEY="your-key"

Requirements:

  • python3
  • Internet access to api.aisa.one
  • AISA_API_KEY must be set in the environment before running the clients
  • Explicit OAuth approval before posting or engagement writes
  • Relay-based upload support for approved media posting flows

Common Commands

python3 scripts/twitter_client.py search --query "AI agents" --type Latest
python3 scripts/twitter_oauth_client.py authorize
python3 scripts/twitter_engagement_client.py like-latest --user "@elonmusk"

Capabilities

  • Research Twitter/X accounts, tweets, trends, lists, communities, and Spaces.
  • Publish text, image, and video posts after explicit OAuth approval.
  • Like, unlike, follow, and unfollow after authorization exists.
  • Keep research and engagement follow-through in one package while making relay target, OAuth approval, upload behavior, and env requirements explicit.

High-Intent Workflows

  • Research a topic or account, then take an approved engagement action from the same runtime surface.
  • Review recent Twitter/X activity before deciding whether to like, follow, unfollow, or post.
  • Prepare a post, complete OAuth approval, and publish through the relay-backed write path.
  • Run post-research engagement follow-through where remote reads, remote writes, and relay-based media upload are acceptable.

Example Requests

  • "Research this Twitter/X account, then like the latest post if it matches our topic."
  • "Search Twitter/X for AI agents, review the results, then prepare an approved engagement action."
  • "Authorize posting, then publish a Twitter/X update with media through the relay flow."
  • "Check recent activity from this account and decide whether to follow or unfollow."

Trust and Side Effects

  • All networked operations go through the AIsa relay at api.aisa.one.
  • The shipped runtime requires AISA_API_KEY; do not imply password-based or cookie-based auth.
  • Write actions require explicit OAuth approval before they can succeed.
  • Posting with media uses relay-based upload paths supported by the runtime.
  • Reads, writes, and uploads are remote API operations, not local-only actions.
  • Do not claim a post, like, follow, or unfollow succeeded until the API confirms it.

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.