social-graph-ranker

Weighted social-graph ranking for warm intro discovery, bridge scoring, and network gap analysis across X and LinkedIn. Use when the user wants the reusable graph-ranking engine itself, not the broader outreach or network-maintenance workflow layered on top of it.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/social-graph-ranker/SKILL.md

Quality

Content

53%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.

The body delivers a precise, well-sectioned ranking model with concrete formulas, a clear workflow, and an output template. Its main gaps are the absence of executable code, a missing validation checkpoint in the batch workflow, and some duplicated trigger framing that could be tightened.

Suggestions

Add an explicit validation/verification step in the workflow (e.g., confirm target-set non-empty, check that computed bridge paths actually exist before ranking) to lift the batch-operation workflow clarity cap.

Provide a runnable snippet or script (even a small Python reference implementation of B_ext and R) so the guidance is copy-paste executable rather than pure math notation.

Merge the redundant "Use this when..." and "When To Use This Standalone" sections into a single trigger/anti-trigger block to remove duplicated framing and tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no padding of concepts Claude already knows, but the "Use this when..." list and "When To Use This Standalone" section overlap, and Inputs/Scoring Signals restate some ideas, so it could be tightened per anchor 3 rather than 4.	3 / 5
Actionability	Provides a precise math model with defined variables and default constants plus a numbered workflow and output template, but offers no executable code or script — the formulas are notation, not runnable — fitting anchor 3 and falling short of the copy-paste-ready anchor 5.	3 / 5
Workflow Clarity	A clear 6-step sequence with tier interpretation and output shape is present, but as a batch graph-ranking operation it lacks any validation/verification checkpoint, which caps workflow clarity at 3 per the rubric's destructive/batch guideline.	3 / 5
Progressive Disclosure	Well-organized into clear sections with no need for external bundle references (none exist), but at ~150 lines with some duplicated trigger sections it carries minor clutter, placing it at anchor 4 rather than the lean one-level overview of anchor 5.	4 / 5
	Total	13 / 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, well-structured description that clearly states capabilities, triggers, and boundaries in third person. Minor room to broaden natural trigger phrasing and make the named actions more concrete.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ("warm intro discovery, bridge scoring, and network gap analysis across X and LinkedIn") but the actions are somewhat abstract rather than a fully comprehensive concrete set, fitting anchor 4 and not 5.	4 / 5
Completeness	Explicitly answers both what ("Weighted social-graph ranking for...") and when ("Use when the user wants the reusable graph-ranking engine itself..."), with concrete trigger phrasing and a boundary clause, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural domain terms ("warm intro discovery," "bridge scoring," "network gap analysis," "X and LinkedIn") with good coverage, but misses a few common user phrasings like "who can introduce me" or "network analysis," so it sits at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear niche and actively disambiguates from siblings ("not the broader outreach or network-maintenance workflow layered on top of it"), giving minimal conflict risk per anchor 5.	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/social-graph-ranker/SKILL.md
Commit: d8409a4

Reviewed: 1 day 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.