Twitter/X Agent Operations — AI Ghostwriter SOP

Turn any AI agent into a ghostwriter that sounds like you — and grew a real account +60% in 45 days.

npx skills add Gingiris-1031/gingiris-twitter-agent-ops

By Iris Wei (生姜) · ex-COO of AFFiNE (60K+ GitHub stars) · 30× Product Hunt #1

Key takeaways

  • Persona calibration (voice guide + dead-opener blacklist) is what makes AI sound like you, not a bot.
  • A fact-source database (SOURCE-INDEX) means every stat is traceable — zero fabricated numbers.
  • Six hard safety rules + pre-publish QC (triple-translation test) before anything posts.
  • Validated: 1,150 → 1,837 followers (+60%) in 45 days, one tweet/day, fully agent-operated.

What this is

You know you should post daily, but writing eats your evenings — and when AI writes for you, it sounds nothing like you. This SOP turns any agent into a ghostwriter that actually sounds like you, with a fact-source database so it never fabricates numbers, and safety rails so it never embarrasses you. Real result: +60% in 45 days.

Key results

Follower growth in 45 days+60%
Posting cadence1 tweet/day
Tweet dataset analyzed3,861 tweets
Hard safety rules6

How to run an AI Twitter ghostwriter

  1. 1

    1 · Calibrate the persona

    Build a voice guide and expression rules, plus a dead-opener blacklist, so the agent writes in your voice instead of generic AI cadence.

  2. 2

    2 · Build the fact-source database

    Create a SOURCE-INDEX of traceable facts and numbers. The agent may only cite stats that exist in the index — this is how it never fabricates.

  3. 3

    3 · Schedule the week

    Plan posts on a weekly schedule with dedup checks against past tweets and golden time windows (derived from a 3,861-tweet analysis).

  4. 4

    4 · Pre-publish QC

    Run every draft through the six hard safety rules and a pre-publish checklist, including a triple-translation test, before it goes live.

  5. 5

    5 · Analytics loop

    Keep a tweet-log and weekly report so the agent learns which archetypes and lengths perform, and feeds that back into scheduling.

Hand-written vs AI-agent-operated

The goal isn't to remove you — it's to keep your voice while reclaiming your evenings.

DimensionManualAgent-operated (this SOP)
Time costHours/weekMinutes of review
VoiceYoursYours (persona-calibrated)
Fabricated statsHuman errorBlocked by SOURCE-INDEX
ConsistencyDrops when busyDaily, scheduled

Anti-patterns (where AI Twitter goes wrong)

FAQ

Can an AI agent really post in my voice?

Yes, with persona calibration — a voice guide, expression rules, and a dead-opener blacklist — validated by a triple-translation test before publishing. The case study grew a real account +60% in 45 days, fully agent-operated, without sounding like a bot.

How does it avoid making up statistics?

A fact-source database (SOURCE-INDEX) holds every traceable fact. The agent is constrained to cite only numbers that exist in the index, so it can't fabricate.

Is it safe to let an agent post automatically?

Only with rails: six hard safety rules plus a pre-publish QC checklist (including a triple-translation test) gate every post. The point is consistency with your voice, not unattended risk.

Who built this?

Iris Wei (生姜) — ex-COO of AFFiNE (60K+ GitHub stars), from analysis of a 3,861-tweet dataset and a real +60%-in-45-days account.

Related playbooks