connections-optimizer

Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is tdg-personal/connections-optimizer

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill with a clear review-gated workflow and concrete output format. Its main weaknesses are redundancy in the safety/outbound rules and a monolithic layout that bundles material which could live in separate reference files.

Suggestions

De-duplicate the no-auto-send guidance: keep it once in Safety Defaults and reference it from Outbound Rules rather than restating 'Do not send automatically'.

Tighten soft platitudes in Platform Rules (e.g., 'mutuals are stickier than one-way follows', 'engagement, signal quality, and bridge value matter more than raw follower count') into concrete decision rules or fold them into the Scoring Model signals.

Split the Modes, Platform Rules, and Scoring Model sections into separate reference files (e.g., references/modes.md, references/platform-rules.md) referenced one level deep from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of explaining known concepts, but the no-auto-send rule is stated twice ('do not auto-send DMs, invites, or emails' in Safety Defaults and 'Do not send automatically' in Outbound Rules) and some platform rules are soft platitudes ('mutuals are stickier than one-way follows'); not score 3 because there is tightening and de-duplication to be had, not score 1 because it does not pad with concepts Claude already knows.	2 / 3
Actionability	Names concrete tools (x-api, lead-intelligence, social-graph-ranker, brand-voice), explicit modes (light-pass/default/aggressive), an 8-step workflow, and a fill-in Review Pack template — concrete, specific, copy-ready guidance for an instruction-only skill.	3 / 3
Workflow Clarity	The Workflow section is an 8-step numbered sequence with an explicit review-gate validation checkpoint before destructive apply ('Return a review pack before any apply step', 'still review-gated before apply'), satisfying the batch/destructive-operation feedback requirement; not score 2 because validation checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	Well-organized into clear section headers, but the ~183-line body is monolithic with no external file references (references/scripts/assets absent); Modes, Platform Rules, and Scoring Model are inline content that could be split into reference files, so it does not meet the 'content appropriately split' anchor for 3, while exceeding the under-50-line simple-skill exception.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete capabilities and supplies an explicit 'Use when' trigger clause with natural user phrasing. It is specific, complete, and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Quotes 'review-first pruning', 'add/follow recommendations', and 'channel-specific warm outreach drafted in the user's real voice' — three distinct concrete actions matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers what ('Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach') and when ('Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph'), satisfying the 'both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	'clean up following lists', 'grow toward current priorities', and 'rebalance a social graph' are natural phrases a user would say, giving good coverage; not score 2 because it goes beyond a single keyword to several natural variations.	3 / 3
Distinctiveness Conflict Risk	Scoped to X and LinkedIn network rebalancing with platform-specific triggers, a clear niche unlikely to conflict with generic skills; not score 2 because the platform + pruning framing is distinctly bounded.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/connections-optimizer/SKILL.md
Commit: 754b8dd

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.