agentleFS
Sign inStart free
QuixiAIQuixiAI/agi-memory/skills/installed/twitter-x-connector-setup/SKILL.md

twitter-x-connector-setup

Skill617 starsChanged 10 months agoMITView on GitHub

Connect Twitter/X through guided OAuth setup, complete authorization, and revoke local access

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when the user asks to connect Twitter/X, read posts or mentions, search recent posts, import X history, read DMs, or disconnect …

    line 13
  2. Distinctive:

    Treat connection setup as a first-class conversation flow.

    line 17
  3. Very specific:

    Ask what powers the user wants before starting sign-in, and request only those capabilities in connect_twitter_x: reading is not permission …

    line 18
  4. Very specific:

    Never ask the user to paste account passwords or API secrets into chat.

    line 19
  5. Very specific:

    Call connect_twitter_x with the least capabilities that match the user's request.

    line 25
  6. Very specific:

    When the user pastes it, call complete_twitter_x_connection with the authorization_response.

    line 27
  7. Very specific:

    Use revoke_twitter_x_connection only after the user asks to disconnect.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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/X Connector Setup

Use this when the user asks to connect Twitter/X, read posts or mentions, search recent posts, import X history, read DMs, or disconnect Twitter/X.

Principles

  • Treat connection setup as a first-class conversation flow. Do not tell the user to leave chat and figure it out alone.
  • Ask what powers the user wants before starting sign-in, and request only those capabilities in connect_twitter_x: reading is not permission to post, and posting is not permission to send DMs.
  • Never ask the user to paste account passwords or API secrets into chat; client credentials come from the configured environment (use_env_client) or the setup UI.
  • For ongoing post/reply/DM behavior, use connector-action-authorization after connection setup so the grant is scoped and DB-audited.
  • Historical import goes through this skill's sibling flow: after connection, queue history with start_connector_backfill (from integration-connector-setup) only when the user asks to ingest X history.

Flow

  1. Call connect_twitter_x with the least capabilities that match the user's request. The result includes the authorization URL or a structured setup payload — surface it rather than paraphrasing it away.
  2. Tell the user the redirected localhost page may fail to load after approval and that this is expected; they should paste the full redirected URL or code back into chat.
  3. When the user pastes it, call complete_twitter_x_connection with the authorization_response.
  4. Report the connected account and granted capabilities.

Use revoke_twitter_x_connection only after the user asks to disconnect; mention they can also remove the grant on the X side in X settings.

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.

Reviews can't be read right now.

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.

Check your setup, free