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

81%

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

75%Weight 40%Scale 1-5

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 that gates destructive pruning behind an explicit review checkpoint and assumes Claude's competence without over-explaining. The main gap is the absence of an explicit fix-and-re-review feedback loop after the review pack.

Suggestions

Add an explicit feedback loop after the review pack step, e.g. 'If the user rejects or edits a prune/draft, revise the affected queue and re-present the review pack before applying.'

Tighten the Scoring Model section into a short weighted rubric or formula so 'score candidates with explicit reasons' becomes a concrete, repeatable calculation.

Consider moving the full Review Pack Format template into a references/ file and summarizing its structure inline, to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and avoids explaining concepts Claude already knows (e.g., it never defines X or LinkedIn), organized as tight bullet lists, with only minor passages that could be trimmed further.	4 / 5
Actionability	Provides concrete, executable guidance for an instruction-only skill — named modes, explicit positive/negative scoring signals, an 8-step workflow, and a copy-ready Review Pack template — though a few directives like "Score prune candidates with explicit reasons" leave the exact scoring mechanics implicit.	4 / 5
Workflow Clarity	The 8-step workflow is clearly sequenced and the destructive/batch pruning operation is gated by an explicit review checkpoint ("Return a review pack before any apply step", "review-gated before apply"), but there is no explicit fix-and-re-review feedback loop after the review pack.	4 / 5
Progressive Disclosure	The skill is self-contained with well-organized section headers and a Related Skills pointer block, giving clear in-file navigation; no bundle files exist to verify one-level-deep references, and a few inline blocks (scoring model, review pack template) could plausibly live in separate reference files.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 description that clearly states capabilities and provides explicit, natural-language activation triggers tied to a distinct niche. Minor room to expand action coverage and add common synonyms like "unfollow".

Dimension	Reasoning	Score
Specificity	Names the domain ("X and LinkedIn network") and several concrete actions ("review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice"), but stops short of comprehensive coverage of modes, scoring, or the review pack.	4 / 5
Completeness	Explicitly answers both what (reorganize the network via pruning, recommendations, and warm outreach) and when ("Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph"), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("clean up following lists", "grow toward current priorities", "rebalance a social graph") with good keyword coverage, though common synonyms like "unfollow" or "connect" are not present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (X/LinkedIn network reorganization with review-first pruning and warm outreach) with distinct triggers and minimal overlap with adjacent skills like brand-voice or lead-intelligence.	5 / 5
	Total	18 / 20 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: 06c5e11

Reviewed: 3 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.