Twitter Cultivate

Twitter account health check, growth strategy, and engagement optimization

Security Scan

The skill's requirements and instructions are coherent for doing a Twitter account health check and engagement analysis, but it asks you to supply browser session cookies and to install unvetted Python packages which are sensitive and merit caution.

Purpose & Capability

The name/description (account health, growth, engagement) match the instructions: the SKILL.md shows analysis and search routines that use an authenticated client. Requiring python3 and a path to Twitter cookies is consistent with using a user session to query Twitter without official API keys.

Instruction Scope

Instructions explicitly tell the agent/user to extract Chrome cookies (auth_token and ct0) and load them from TWITTER_COOKIES_PATH, and include example Python code that uses those cookies to query user data and search tweets. This is within the skill's stated scope but is sensitive because those cookies can grant full account access if mishandled. The SKILL.md does not instruct exfiltration to unrelated endpoints.

Install Mechanism

There is no formal install spec in the registry, but the README advises installing a pre-release pip package (rnet>=3.0.0rc20 --pre) and a third-party GitHub client (rnet-twitter-client). Installing pre-release/unvetted packages from PyPI/GitHub carries risk; the lack of an explicit install block means the agent or user will need to run pip manually or otherwise install these components.

Credentials

The only required environment variable is TWITTER_COOKIES_PATH, which is appropriate for a cookie-based client. However, the required value is highly sensitive (session cookies). No unrelated credentials or config paths are requested.

Persistence & Privilege

The skill does not request always:true, does not declare modifications to other skills or system-wide settings, and is user-invocable. Autonomous invocation is allowed by default but is not combined with any unusual extra privileges.

Assessment

This skill appears to do what it says, but before installing or using it: (1) understand that the skill requires your browser session cookies (auth_token and ct0). Those cookies effectively let code act as your account — treat them like a password. Only provide them in a secure, trusted environment and delete/rotate them if you suspect misuse. (2) The instructions tell you to pip install a pre-release package and a GitHub client; review the package source code (rnet and rnet-twitter-client) before installing and prefer running installs in an isolated virtualenv or disposable container. (3) If you prefer safer alternatives, use official API credentials (if available) or a read-only approach rather than sharing session cookies. (4) Avoid running unreviewed automation that performs mass unfollows or posts on your behalf without auditing the code first. If you want help vetting the rnet package or the GitHub client, provide the repo URLs and I can summarize potential risks.

Twitter Account Cultivation Skill

Systematic approach to growing Twitter presence based on the open-source algorithm analysis. Check account health, find engagement opportunities, optimize content strategy.

---

Prerequisites

• rnet installed (pip install "rnet>=3.0.0rc20" --pre)
• rnet_twitter.py — lightweight GraphQL client (https://github.com/PHY041/rnet-twitter-client)
• Twitter cookies exported to path specified by TWITTER_COOKIES_PATH env var Format: [{"name": "auth_token", "value": "..."}, {"name": "ct0", "value": "..."}]

Getting Cookies

1. Open Chrome -> go to x.com -> log in
2. DevTools -> Application -> Cookies -> https://x.com
3. Copy auth_token and ct0 values
4. Save as JSON. Cookies last ~2 weeks. Refresh when you get 403 errors.

---

Core Metrics to Track

Metric	Healthy Range	Impact
Following/Follower Ratio	< 0.6	TweepCred score
Avg Views/Tweet	20-40% of followers	Algorithm favor
Media Tweet %	> 50%	10x engagement
Link Tweet %	< 20%	Avoid algorithm penalty
Reply Rate	Reply to 100% of comments	+75 weight boost

---

Workflow: Full Health Check

Step 1: Analyze Account

import asyncio, os
from rnet_twitter import RnetTwitterClient

async def analyze(username: str):
    client = RnetTwitterClient()
    cookies_path = os.environ.get("TWITTER_COOKIES_PATH", "twitter_cookies.json")
    client.load_cookies(cookies_path)

    user = await client.get_user_by_screen_name(username)
    followers = user.get("followers_count", 0)
    following = user.get("friends_count", 0)
    ratio = following / max(followers, 1)

    tweets = await client.get_user_tweets(user["rest_id"], count=20)

    return {
        "username": username,
        "followers": followers,
        "following": following,
        "ratio": round(ratio, 2),
        "tweet_count": user.get("statuses_count", 0),
        "recent_tweets": len(tweets),
    }

Step 2: Check Shadowban Status

Manual check: shadowban.yuzurisa.com

Step 3: Analyze Following List

Recommends accounts to unfollow based on:

• No tweets in 90+ days (inactive)
• Never interacted with you (no value)
• Low follower count + high following (likely bots)
• No mutual engagement

Step 4: Find Engagement Opportunities

async def find_opportunities(niche_keywords: list[str]):
    client = RnetTwitterClient()
    cookies_path = os.environ.get("TWITTER_COOKIES_PATH", "twitter_cookies.json")
    client.load_cookies(cookies_path)

    opportunities = []
    for keyword in niche_keywords:
        tweets = await client.search_tweets(
            f"{keyword} lang:en -filter:replies",
            count=50, product="Top"
        )
        for t in tweets:
            if t["favorite_count"] >= 50 and t["reply_count"] < 20:
                opportunities.append(t)

    return sorted(opportunities, key=lambda t: t["favorite_count"], reverse=True)

---

Account Health Scoring (TweepCred)

Based on Twitter's open-source algorithm:

Score = PageRank x (1 / max(1, following/followers))

Ratio	Estimated TweepCred	Algorithm Treatment
< 0.6	65+ (healthy)	All tweets considered
0.6 - 2.0	40-65	Limited consideration
2.0 - 5.0	20-40	Severe penalty
> 5.0	< 20	Only 3 tweets max

---

Unfollow Strategy

Priority Order

1. Inactive Accounts — No tweets in 90+ days
2. Non-Engagers — Never liked/replied to your tweets
3. Low-Value Follows — High following/low followers (bot-like)

Execution Plan

Week 1: Unfollow 30 inactive accounts
Week 2: Unfollow 30 non-engagers
Week 3: Unfollow 30 low-value follows
Week 4: Evaluate ratio improvement

---

Content Strategy (Algorithm-Optimized)

Tweet Types by Algorithm Weight

Type	Weight	Recommendation
Tweet that gets author reply	+75	ALWAYS reply to comments
Tweet with replies	+13.5	Ask questions
Tweet with profile clicks	+12.0	Be intriguing
Tweet with long dwell time	+10.0	Use threads
Retweet	+1.0	Low value
Like	+0.5	Lowest value

Content Mix

• 40% Value content (insights, tips, frameworks)
• 30% Engagement bait (questions, polls, hot takes)
• 20% Build-in-public (progress updates, wins, losses)
• 10% Promotion (with value attached)

Media Requirements

Every tweet should have ONE of: Image, Video (< 2:20), Poll, or Thread (7-10 tweets).

---

Weekly Routine

Daily (15 min)

• Post 1-3 tweets with media
• Reply to ALL comments on your tweets
• Engage with 5-10 tweets in your niche
• Check notifications and respond

Weekly (Saturday)

• Run full health check
• Review what content performed best
• Unfollow 10-20 low-value accounts
• Plan next week's content themes

Monthly

• Full ratio review (target < 2.0)
• Shadowban check
• Content audit (media %, link %)
• Milestone check (follower goals)