Name: customer-success-manager
Rating: 72 (1 reviews)
Author: alirezarezvani

customer-success-manager

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success. Use when analyzing customer accounts, reviewing retention metrics, scoring at-risk customers, or when the user mentions churn, customer health scores, upsell opportunities, expansion revenue, retention analysis, or customer analytics. Runs three Python CLI tools to produce deterministic health scores, churn risk tiers, and prioritized expansion recommendations across Enterprise, Mid-Market, and SMB segments.

Quality

88%

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

The canonical home for this skill is customer-success-manager in alirezarezvani/claude-skills

Quality

Content

77%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 is well-organized and richly actionable with a strong validated workflow, but it describes a multi-file bundle (scripts, references, assets) that is not actually shipped, undermining both executability and progressive disclosure.

Suggestions

Ship the referenced bundle: add the three scripts under scripts/, the three guides under references/, the sample JSON and four templates under assets/, so the documented paths resolve.

Remove the redundant per-script Usage command blocks (or the Quick Start block) — the identical `python scripts/… --format json` commands are shown twice — and consider dropping the Table of Contents for a file this short.

Add an automated validation step (e.g., a validate command or schema check) rather than only manual 'confirm non-empty' Verify notes, to harden the batch workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	Largely efficient — the weight/threshold tables are skill-specific data Claude would not know — but the Table of Contents and the repeated `python scripts/…` commands (shown in both Quick Start and each script's Usage block) are minor redundancy that could be trimmed. Not quite anchor-5 lean.	4 / 5
Actionability	Concrete copy-paste commands with explicit paths and `--format` flags plus exhaustively detailed input-field requirements; however the referenced `scripts/*.py` executables are absent from the bundle, so the commands cannot actually run, keeping it short of 'fully executable.'	4 / 5
Workflow Clarity	The Workflow Integration section provides a numbered 1–4 sequence where each step carries an explicit `Verify:` checkpoint, plus a dedicated error-handling feedback loop (check schema → fix → retry); validation is present for this batch operation, so the missing-validation cap does not apply.	5 / 5
Progressive Disclosure	The on-paper structure is well-signaled (references table, templates table, scripts section), but scored against the actual bundle structure the referenced files do not exist — all three reference guides, four templates, three scripts, and the sample JSON are absent — so the promised one-level-deep references point to nothing and content is not actually split into files.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: concrete actions, comprehensive trigger terms with synonyms, and an explicit 'Use when…' clause, all in third person. It closely matches the rubric's good examples and needs no revision.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Monitors customer health, predicts churn risk, and identifies expansion opportunities' plus the three tool outputs and the three segments), giving comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (the monitoring/prediction/identification actions and the three CLI tool outputs) and 'when' via a concrete 'Use when…' clause with multiple triggers.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms with synonyms — 'churn, customer health scores, upsell opportunities, expansion revenue, retention analysis, customer analytics' alongside 'analyzing customer accounts, reviewing retention metrics, scoring at-risk customers' — covering the phrases users would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear SaaS customer-success analytics niche with distinct triggers (churn, health scores, expansion revenue), making conflict with unrelated skills minimal.	5 / 5
	Total	20 / 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
referenced_paths_exist	Referenced path issues: 32 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/customer-success-manager/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours 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.