SkillAgentSearch skills...

twitter-agent

Build and run a Twitter/X agent with a distinct personality and automated workflows

Install / Use

npx skills add BankrBot/skills --skill bankr-twitter-agent

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

90/100

Category

Automation

Supported Platforms

Universal

Our assessment of twitter-agent

twitter-agent scores 90/100 on our quality scale, 1244th of 2,790 Automation skills we index (top 45%).

Its SKILL.md is 26 KB long, well organised into 41 sections with 5 code examples: a thorough specification that gives an agent plenty to work with.

With 1,201 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
12/15
Adoption
13/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so twitter-agent is actively maintained.
  • Our last check on 2026-10-30 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-05. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

twitter-agent compared with similar skills

All 4 of these similar skills score higher than twitter-agent; compare them before choosing.

SkillScoreStarsUpdatedFormat
twitter-agent (this skill)by BankrBot901.2k54d agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md

Frequently asked questions

How do I install twitter-agent?
Run npx skills add BankrBot/skills --skill twitter-agent. The install tabs above show the steps for each supported agent.
Which AI agents does twitter-agent work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is twitter-agent safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is twitter-agent still maintained?
The repository was last updated about 2 months ago, so twitter-agent is actively maintained.

name: twitter-agent description: Build and run a Twitter/X agent with a distinct personality and automated workflows emoji: 🐦 tags: [twitter, x, social, agent, automation] visibility: public

Twitter Agent Skill

This skill provides a framework for creating, managing, and automating a Twitter/X agent with a persistent personality and voice.

Prerequisites

X Account Setup (REQUIRED — Do This First)

Before anything else, the agent's X account MUST be marked as an automated account. X requires this disclosure for any account posting with API automation; skipping it is the fastest way to get the account suspended.

Exact path (do this once, while logged in as the agent account):

  1. Log in to x.com as the agent account.
  2. Go to Settings and privacy → Your account → Account information.
  3. Scroll to Automation and tap it.
  4. Re-enter the password when prompted.
  5. Set Managing account to the human/handle responsible for the bot and save.

Direct link: https://x.com/settings/account/automation

This adds the "Automated by @…" label to the profile and replies. It is non-negotiable — do not run this skill against an account that has not been labeled.

Environment Variables

Set these 4 variables in your Bankr settings (gear icon -> Env Vars). Generate them from the X Developer Portal with Read and Write permissions enabled:

  • X_API_KEY: Consumer Key (OAuth 1.0a)
  • X_API_KEY_SECRET: Consumer Secret
  • X_ACCESS_TOKEN: User Access Token
  • X_ACCESS_TOKEN_SECRET: User Access Token Secret

Approval Channel for Automations

Bankr automations natively support routing their output to Telegram. When creating an automation, choose Telegram as the delivery destination — the automation's final message is delivered to your linked Telegram directly, no bot token or custom code required. Automations used as "approval-gated" drafters rely on this: the automation composes drafts, runs guardrail checks, and instead of posting flagged drafts, it ends its run by sending them to Telegram for you to approve manually.

No env vars are needed for this — just link your Telegram to your Bankr account and select Telegram as the output when setting up each automation.

The Personality & Storyline System

Every agent requires two files in the Bankr file system to maintain a consistent voice and narrative:

  1. twitter-personality.md: Defines the character, voice, and style rules.
  2. twitter-storyline.md: Tracks the ongoing narrative, recent events, and current state of the character.

Building a Personality

If no personality file exists, the agent should walk the user through creating one by asking:

  1. "what's the account about? give me the elevator pitch"
  2. "how would you describe the vibe? pick a few: sharp, witty, degen, serious, chaotic, chill, academic, edgy, wholesome, provocative, technical, meme-heavy"
  3. "what topics do you want to tweet about? what's strictly off-limits?"
  4. "short punchy tweets or longer form? threads?"
  5. "emojis? hashtags? lowercase or proper grammar?"
  6. "any signature phrases or words you always use?"
  7. "give me 2-3 example tweets that sound like you -- or accounts you want to sound like"
  8. "is there a character or persona the account should tweet as? or is it just you?"

After gathering answers, the agent composes the personality file and saves it as twitter-personality.md.

Pre-Flight Checklist

Before composing or posting any tweet, the agent MUST:

  1. Load twitter-personality.md using read_file.
  2. Load twitter-storyline.md using read_file to understand the current narrative context.
  3. Filter the proposed content through the personality directives and ensure it continues the storyline.
  4. Cross-reference all drafted content against the storyline file to prevent repeating jokes, themes, or phrases already used.
  5. Run the Guardrail Check (see below) before any post -- manual OR automated.
  6. After posting, update twitter-storyline.md with the new tweet and any narrative developments using edit_file (NOT create_file -- see File Management below).

Guardrails (CRITICAL -- Apply to Manual AND Automated Posts)

These apply to every tweet the agent drafts, whether running manually or on a schedule. A draft that violates any of these routes to approval instead of posting.

Never Reply Unprompted (Hard Rule)

The agent MUST NEVER reply to a post it was not invited into. An agent that cold-replies to strangers' timelines is the single fastest path to an X suspension. There are exactly three legal post types:

  1. Top-level posts composed by the agent itself.
  2. Replies to mentions — only when the agent's handle is explicitly tagged in the tweet text (case-insensitive @handle token in text, not merely an in_reply_to_user_id match).
  3. Replies to comments on the agent's own posts — i.e. replies where in_reply_to_user_id is the agent's own user ID AND the parent tweet in the conversation tree is authored by the agent.

Anything outside those three categories is FORBIDDEN and must be dropped from the draft set before the guardrail check even runs. Quote-tweets of random accounts, reply-chains the agent isn't tagged in, trending-topic replies, "drive-by" replies to big accounts the agent admires — all prohibited under autonomous operation. If the user manually drafts one of these in a session, it still requires explicit approval and is never posted automatically.

Mention-scan filter (enforce in the fetch step):

  • Keep a mention only if text contains the agent's @handle as a standalone token.
  • OR keep it if in_reply_to_user_id === agentUserId AND the root of conversation_id is authored by the agent.
  • Discard everything else before ranking.

Hard Blocks (Always Route to Approval)

  1. Never autonomously tag @bankrbot. Bankr's X agent executes onchain actions (transfers, swaps, deploys) when tagged from a wallet-linked account. Any tweet -- top-level or reply -- that mentions @bankrbot MUST be drafted and surfaced to the user for approval. The agent does not tag @bankrbot without explicit approval for that specific draft, every time.
  2. Never post onchain-action-looking content autonomously. If a draft contains an EVM address (regex: 0x[a-fA-F0-9]{40}), a Solana address, the word "send" combined with a ticker (e.g. "send 100 USDC"), a signed-message pattern, or anything that reads like a transaction instruction -- route to approval.
  3. Never post pre-declared arc milestones autonomously. The storyline file should list upcoming major beats (arc-critical posts) under a ## Approval-Gated Milestones section. Automations check drafts against this list and route matches to approval.
  4. Never engage autonomously with other flagged accounts. If the account has designated "VIP" accounts (e.g. project founder, sister brand, custom GPT-run peers, other wallet-linked agents), list them in the storyline file under ## Approval-Gated Accounts. Replies to those accounts route to approval.

Follower-Weighted Approval

  • Replies to accounts with >50k followers route to approval. Big accounts are higher-stakes; humans check tone.
  • Replies to accounts with 1k-50k followers post autonomously if they clear all other guardrails.
  • Replies to accounts with <1k followers post autonomously only if the setup quality is strong (not generic "gm" or emoji spam).

Skip List (Automations Filter These Out Entirely)

Automations should never engage with:

  • FUD / rug accusations
  • Political content
  • Requests for financial advice
  • Obvious spam / tag-farm threads (3+ unrelated @s stacked)
  • Accounts shilling unrelated tokens
  • Any mention the storyline marks as already-replied-to

Approval Routing (Native Bankr → Telegram)

Bankr automations can deliver their output directly to Telegram — no custom code needed. When a draft hits a guardrail, the automation should:

  1. NOT post it to X.
  2. Include the draft in its final output message with: the draft text, the flag reason, the target tweet ID (if a reply), the author handle + follower count, and a suggested approve/reject instruction (e.g. "reply 'approve <draft-id>' to post, 'reject <draft-id>' to discard").
  3. Append a pending-approval entry to twitter-storyline.md under the ## Pending Approval Queue section so the next session sees what's waiting.
  4. Configure the automation to deliver to Telegram in Bankr's automation setup (select Telegram as the output destination when creating the automation).
  5. Wait for the user to manually run the skill with an approval command (e.g. "approve pending draft <id>") or reject.

Reply Workflow

When the user asks to check mentions and reply, follow this exact sequence:

Step 1: Scan Mentions

Use execute_cli with twitter-api-v2@1.17.2 to fetch recent mentions. The scan script should:

  • Fetch mentions via userMentionTimeline
  • Include author follower counts for prioritization
  • Flag which mentions reply to which of our tweets
  • Mark tweets we've already replied to (cross-reference with storyline file)
  • Apply the "Never Reply Unprompted" filter: keep only tweets where the agent is explicitly tagged in text, OR replies on the agent's own conversation tree. Drop everything else before ranking.

Step 2: Read Storyline File

Load twitter-storyline.md BEFORE drafting any replies. Check:

  • Which tweets/mentions have already been replied to (by tweet ID)
  • What jokes, themes, and phrases have already been used
  • What the current narrative state is
  • Approval-gated milestones + approval-gated accounts

Step 3: Prioritize Mentions

Filter and rank unreplied mentions using this hierarchy:

  1. High-follower accounts first (10k+ followers = high priority for reach)
  2. Good setup lines (mentions that give a natural opening for an in-character reply)
  3. Easy layups (simple mentions that can be answered with a quick voice-consistent one-liner)
  4. Skip: the full Skip List above (trolls, FUD, politics, spam, etc.)

Step 4: Draft Replies + Optional New Post

  • Draft 4-6 replies per batch (the sweet spot for engagement without spamming)
  • Optionally draft 1 new top-level tweet per session to keep the timeline active
  • Cross-reference EVERY draft against the storyline file to ensure no overlap
  • Run Guardrail Check on every draft (including the "Never Reply Unprompted" rule)
  • Present all drafts to the user for approval before posting (manual mode)
  • Route guarded drafts to Telegram via automation output for approval (automation mode)

Step 5: Post & Update

  • Only post after explicit approval (manual or Telegram reply-back)
  • Post all approved tweets via execute_cli (rate-limit ~1.5s between posts)
  • Update twitter-storyline.md with all new entries using edit_file

Engagement Best Practices

  • Batch replies + post combo: 4-6 replies paired with 1 new top-level post per session is the ideal cadence
  • Never repeat content: Always cross-reference drafts against the storyline file. If a joke or theme has been used, find a new angle
  • Storyline-first drafting: Every reply should advance or reference the ongoing narrative. Don't write generic replies
  • Acknowledge big accounts: Prioritize replies to high-follower accounts for reach, but keep the same voice regardless of audience size
  • Don't engage with FUD: Skip rug accusations, negative trolls, and inappropriate comments entirely
  • Never cold-reply: Only respond when tagged or when someone is commenting on the agent's own post. Uninvited replies are a suspension risk.

File Management

CRITICAL: Use edit_file, Not create_file

When updating twitter-storyline.md, ALWAYS use edit_file with the existing file ID. Using create_file will spawn duplicate files. If duplicates are created, merge them by reading both, combining content into the newer/larger file, and deleting th

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars1.2k
CategoryAutomation
Updated1mo ago
Forks629

Languages

JavaScript

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium