Connections Optimizer
Prune and rebalance your X and LinkedIn graph with review-first queues, follow targets aligned to current priorities, and warm outreach drafts in your voice.
Overview
Connections Optimizer is an agent skill most often used in Grow (also Launch) that rebalances X and LinkedIn networks with prune queues, follow recommendations, and warm outreach drafts matched to the user's voice.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill connections-optimizerWhat is this skill?
- X following cleanup and expansion plus LinkedIn follow/connection analysis
- Review-first prune queues with light-pass, default, or aggressive modes
- Add/follow recommendations keyed to roles, industries, geos, and active work
- Warm-path identification and drafts for Apple Mail, X DM, and LinkedIn in the user's voice
- Integrates x-api and lead-intelligence when available for graph inspection
- 3 execution modes: light-pass, default, aggressive
Adoption & trust: 3.2k installs on skills.sh; 210k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your following and connection lists are noisy misaligned with what you are building now, so outreach feels cold and low-signal.
Who is it for?
Founders and creators actively growing on X and/or LinkedIn who want graph hygiene and warm reconnection, not spray-and-pray DMs.
Skip if: Builders with no social distribution goals, or users who want fully automated unfollows without a review queue or do-not-touch list.
When should I use this skill?
User wants to prune X following, rebalance LinkedIn, clean up network, or get who to follow/unfollow/reconnect with; outreach depends on graph structure.
What do I get? / Deliverables
You get review-first prune and follow queues, warm-path picks, and drafted Apple Mail, X DM, or LinkedIn messages aligned to current priorities—before you send anything.
- Review-first prune and follow recommendation queues
- Warm-path shortlist
- Channel-specific outreach drafts (Mail, X DM, LinkedIn)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Grow is where relationship quality compounds; this skill treats the social graph as infrastructure for distribution and partnerships. Lifecycle fits ongoing network maintenance, reconnection, and warm-path outreach—not one-off launch blasts.
Where it fits
Run a default-mode pass to queue low-signal X follows for review while recommending accounts in your target ecosystem.
Identify warm paths to re-engage contacts before promoting a new build thread or newsletter issue.
Tighten the graph so launch outreach hits higher-signal DMs and LinkedIn notes instead of a cold list.
How it compares
Network-structure workflow for warm outreach—not a lead-scraper MCP or generic cold email template pack.
Common Questions / FAQ
Who is connections-optimizer for?
Solo builders and founders who use X and LinkedIn for distribution and want their graph pruned and expanded around current product priorities.
When should I use connections-optimizer?
In Grow for lifecycle network maintenance, and in Launch for distribution when outreach quality depends on who you follow and reconnect with—e.g. clean up my network or who should I unfollow.
Is connections-optimizer safe to install?
It is review-first and needs API access for graph tools; confirm scopes, do-not-touch lists, and the Security Audits panel on this page before connecting x-api or mail drafts.
SKILL.md
READMESKILL.md - Connections Optimizer
# Connections Optimizer Reorganize the user's network instead of treating outbound as a one-way prospecting list. This skill handles: - X following cleanup and expansion - LinkedIn follow and connection analysis - review-first prune queues - add and follow recommendations - warm-path identification - Apple Mail, X DM, and LinkedIn draft generation in the user's real voice ## When to Activate - the user wants to prune their X following - the user wants to rebalance who they follow or stay connected to - the user says "clean up my network", "who should I unfollow", "who should I follow", "who should I reconnect with" - outreach quality depends on network structure, not just cold list generation ## Required Inputs Collect or infer: - current priorities and active work - target roles, industries, geos, or ecosystems - platform selection: X, LinkedIn, or both - do-not-touch list - mode: `light-pass`, `default`, or `aggressive` If the user does not specify a mode, use `default`. ## Tool Requirements ### Preferred - `x-api` for X graph inspection and recent activity - `lead-intelligence` for target discovery and warm-path ranking - `social-graph-ranker` when the user wants bridge value scored independently of the broader lead workflow - Exa / deep research for person and company enrichment - `brand-voice` before drafting outbound ### Fallbacks - browser control for LinkedIn analysis and drafting - browser control for X if API coverage is constrained - Apple Mail or Mail.app drafting via desktop automation when email is the right channel ## Safety Defaults - default is review-first, never blind auto-pruning - X: prune only accounts the user follows, never followers - LinkedIn: treat 1st-degree connection removal as manual-review-first - do not auto-send DMs, invites, or emails - emit a ranked action plan and drafts before any apply step ## Platform Rules ### X - mutuals are stickier than one-way follows - non-follow-backs can be pruned more aggressively - heavily inactive or disappeared accounts should surface quickly - engagement, signal quality, and bridge value matter more than raw follower count ### LinkedIn - API-first if the user actually has LinkedIn API access - browser workflow must work when API access is missing - distinguish outbound follows from accepted 1st-degree connections - outbound follows can be pruned more freely - accepted 1st-degree connections should default to review, not auto-remove ## Modes ### `light-pass` - prune only high-confidence low-value one-way follows - surface the rest for review - generate a small add/follow list ### `default` - balanced prune queue - balanced keep list - ranked add/follow queue - draft warm intros or direct outreach where useful ### `aggressive` - larger prune queue - lower tolerance for stale non-follow-backs - still review-gated before apply ## Scoring Model Use these positive signals: - reciprocity - recent activity - alignment to current priorities - network bridge value - role relevance - real engagement history - recent presence and responsiveness Use these negative signals: - disappeared or abandoned account - stale one-way follow - off-priority topic cluster - low-value noise - repeated non-response - no follow-back when many better replacements exist Mutuals and real warm-path bridges should be penalized less aggressively than one-way follows. ## Workflow 1. Capture priorities, do-not-touch constraints, and selected platforms. 2. Pull the current following / connection inventory. 3. Score prune candidates with explicit reasons. 4. Score keep candidates with expl