CtrlK
BlogDocsLog inGet started
Tessl Logo

expansion-retention

When the user wants to reduce churn, build expansion revenue, automate customer success, or optimize net revenue retention. Also use when the user mentions 'churn,' 'retention,' 'expansion revenue,' 'upsell,' 'NRR,' 'net revenue retention,' 'customer success,' 'land and expand,' 'closed-lost,' or 'renewal.' This skill covers expansion and retention systems from usage triggers through automated customer success. Do NOT use for technical implementation, code review, or software architecture.

67

Quality

58%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./packages/skills-catalog/skills/(gtm)/expansion-retention/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

89%

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

This is a strong description with excellent trigger term coverage and clear 'when to use' guidance including both positive triggers and negative exclusions. Its main weakness is that the 'what it does' portion is somewhat abstract—it describes the domain well but doesn't enumerate specific concrete actions or deliverables the skill produces. Adding 2-3 specific actions would elevate the specificity score.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Designs churn prediction frameworks, creates upsell playbooks, builds renewal pipeline models, and maps customer health scoring systems.'

DimensionReasoningScore

Specificity

The description mentions some domain-specific concepts like 'reduce churn,' 'build expansion revenue,' 'automate customer success,' and 'optimize net revenue retention,' but it doesn't list concrete, specific actions (e.g., 'create churn prediction models,' 'design upsell playbooks,' 'build renewal dashboards'). The phrase 'covers expansion and retention systems from usage triggers through automated customer success' is somewhat vague about what it actually does.

2 / 3

Completeness

The description explicitly answers both 'what' (expansion and retention systems, usage triggers, automated customer success) and 'when' (with a clear 'Use when' equivalent at the start and explicit trigger terms listed). It also includes a helpful 'Do NOT use' exclusion clause for disambiguation.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'churn,' 'retention,' 'expansion revenue,' 'upsell,' 'NRR,' 'net revenue retention,' 'customer success,' 'land and expand,' 'closed-lost,' 'renewal.' These are all terms a user working in SaaS/customer success would naturally use.

3 / 3

Distinctiveness Conflict Risk

The description carves out a clear niche in customer success/revenue retention with distinct trigger terms like 'NRR,' 'churn,' 'land and expand,' and 'closed-lost.' The explicit exclusion of technical implementation and code review further reduces conflict risk with engineering-focused skills.

3 / 3

Total

11

/

12

Passed

Implementation

27%

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

This skill is comprehensive in coverage but severely over-engineered for a SKILL.md file. It reads as a complete playbook/handbook rather than a concise skill that leverages Claude's existing knowledge. The content would be far more effective as a brief overview with references to detailed sub-files for each of the 9 sections, and with significant trimming of general business knowledge that Claude already possesses.

Suggestions

Reduce the main SKILL.md to a concise overview (~50-80 lines) covering the decision framework and key principles, then move detailed sections (health scoring, PQA models, closed-lost playbooks, etc.) into separate referenced files like HEALTH-SCORING.md, EXPANSION-TRIGGERS.md, etc.

Remove or drastically condense explanatory content Claude already knows (e.g., what NRR is, what land-and-expand means, general definitions of pricing models) and focus only on the specific frameworks, thresholds, and decision logic that are unique to this skill.

Add validation/feedback loops to key workflows - for example, how to verify health score accuracy quarterly, how to measure whether expansion triggers are firing correctly, and how to assess if closed-lost re-engagement cadences are working.

Trim benchmark tables to only the most critical reference data, or move them to a separate BENCHMARKS.md file, as many of these statistics are time-sensitive and will become outdated.

DimensionReasoningScore

Conciseness

This is an extremely long skill (~500+ lines) that reads like a comprehensive textbook rather than a concise skill file. It includes extensive benchmark tables, general business knowledge Claude already knows (what NRR is, how land-and-expand works), and verbose explanations that could be dramatically condensed. Much of this content (e.g., advocacy program tiers, CS capacity planning ratios, tool lists) is general knowledge that doesn't need to be spelled out at this length.

1 / 3

Actionability

The skill provides concrete frameworks, scoring models, trigger matrices, and specific metrics/thresholds that are actionable for strategic guidance. However, it lacks executable artifacts - no code, no templates to copy-paste, no specific scripts or automation configurations. The guidance is structured but remains at the advisory/framework level rather than being directly implementable.

2 / 3

Workflow Clarity

Several workflows are presented (onboarding sequences, renewal timelines, closed-lost re-engagement phases) with clear sequencing and timing. However, there are no validation checkpoints or feedback loops - for example, the health scoring system has no guidance on how to validate its accuracy, and the expansion trigger matrix doesn't include verification steps to confirm triggers are working correctly.

2 / 3

Progressive Disclosure

The entire skill is a monolithic wall of content with 9 major sections all inline. There are references to related skills at the bottom, but the massive amount of detail (benchmark tables, scoring models, email sequences, tool lists) should be split into separate reference files. The skill would benefit enormously from a concise overview pointing to detailed sub-documents for each section.

1 / 3

Total

6

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
tech-leads-club/agent-skills
Reviewed

Table of Contents

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.