- Home
- Skills
- Social Media
- x-reply: replies to bigger X accounts that add something
Works with the AI Agents you already use
x-reply: replies to bigger X accounts that add something
**What it does.** On a small account, a good reply under a bigger account's post can reach more people than your own posts do.
Free
x-reply: replies to bigger X accounts that add something
Example session with this skill installed
Find fresh posts in AI and dev from this morning and write my reply drafts.
- Read your context and instructions
- Compiled the x-reply
Found 2026-11-17 ~8:25 AM IST via X search (Latest). All 10 drafts pass the checker (--tags 0-0 --limit 200): READY. Two of the ten are shown here, with the other accounts' handles left out.
7. Large account, posted ~7:09 AM IST, 56 replies (busy thread)
Post: AI progress is much clearer on programming tasks than on other things.
Type: 9 · Reframe · 187/200
Code comes with a grader: it runs or it doesn't, tests pass or fail. Models get a clean signal there. Writing and analysis have no compiler, so progress is harder to train for and to see.
9. Posted ~7:52 AM IST, 6 replies (freshest, best odds)
Post: asks for a correction: the frontier vs open-source gap feels like 12-18 months now, not 6.
Type: 7 · Real question · 176/200
Which tasks is that measured on? A model can be 6 months behind on single-turn answers and much further behind on multi-hour agent runs, and those two gaps get lumped together.
Next step: you post these by hand, starting with the freshest thread.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does. On a small account, a good reply under a bigger account's post can reach more people than your own posts do. This skill helps you write the good ones.
How it works. Paste the posts, or let an agent with a browser read X for you, read only. It filters for size, freshness and fit, skips outrage and engagement-farming posts, and won't reply to the same account twice in a day. Each draft uses one of ten reply types, comes from your own positions and proof in voice.md, and is checked with the bundled checker at 200 characters with no hashtags. The batch goes into your log, so tomorrow's targets don't repeat.
Where it stops. You post every reply yourself. It never posts, likes, follows or reposts, because automated replies are the fastest way to get an account limited. It won't write "we saw the same thing" unless you did.
Part of x-skills, ten free MIT-licensed skills for X.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Social Media.
It only knows what you paste, your files in ~/.x-skills/ and what a browser shows it. It can't promise reach or predict X's ranking. It assumes 280-character posts. You post every reply by hand.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
- Software
Python 3.8+
- Optional
- A browser signed in to X (read only, only if you ask)
On Windows, if python3 is not found, run the checker with python instead.
Permissions
File Scopes
Reads ~/.x-skills/voice.md and appends each batch to ~/.x-skills/log.md. Runs the bundled checker on local draft files. Can read X in a browser where you are signed in, read only. Never posts, likes, follows or reposts.