Tessl • The management layer for AI agent skills

SkillPublic

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.

Quality

78%

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 ./packages/skills-catalog/skills/(gtm)/expansion-retention/SKILL.md

Quality

Content

63%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 rich, unusually concrete GTM reference with good internal sequencing and feedback loops, undermined by monolithic structure and padding. Its biggest lever is moving benchmark tables, tech-stack lists, and detailed scoring models into references/ files while trimming duplicated and time-sensitive content from SKILL.md.

Suggestions

Split reference data into one-level-deep bundle files (e.g., references/benchmarks.md, references/pqa-model.md, references/tech-stack.md) and keep SKILL.md as a concise overview that links to them, rather than inlining all tables.

Remove duplication between the Quick Reference section and earlier sections (Time to First Expansion, expansion revenue metrics appear twice), and drop or trim the Tech Stack tool lists, which mostly restate tools Claude already knows.

Move dated statistics ("2025-2026 NRR Benchmarks," growth-comparison percentages) into a clearly dated reference file or a benchmarks section marked as time-sensitive, so the core skill body stays evergreen.

Dimension	Reasoning	Score
Conciseness	The body is packed with domain data Claude does not know, but includes unnecessary padding: time-sensitive stats ("2025-2026 NRR Benchmarks," "38% faster revenue growth") sit inline rather than in a dated/deprecated section, the Quick Reference duplicates earlier tables (Time to First Expansion, expansion metrics), and the Tech Stack lists tools Claude already knows.	3 / 5
Actionability	Highly concrete for an instruction-only skill — NRR threshold decision framework, trigger matrix with specific actions/timings/owners, day-by-day email sequences, and save plays with success rates — but occasional abstract directives ("Competitive displacement content," "CSM war room") keep it short of fully copy-paste-ready guidance.	4 / 5
Workflow Clarity	Clear entry sequence (Before Starting questions -> NRR-level decision framework -> segment playbooks), escalation ladders (renewal timeline 180 to 7 days), and a Troubleshooting section giving cause->fix recovery loops. Not a destructive/batch skill, so no validation cap applies, but there is no consolidated end-to-end workflow per request type, leaving minor sequencing gaps.	4 / 5
Progressive Disclosure	No bundle files exist; the ~450-line body inlines reference material (benchmark tables, the PQA scoring model, tech-stack and capacity-planning tables) that clearly belongs in separate references/ files. Section headers are well organized, placing it above 'minimal structure,' but nothing is offloaded and navigation relies on sheer length.	3 / 5
	Total	14 / 20 Passed

Description

82%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 with explicit trigger clauses, an acronym-plus-synonym keyword set, and a clear negative boundary. Its main weakness is a somewhat abstract statement of what the skill covers rather than a concrete enumeration of its capabilities.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("reduce churn, build expansion revenue, automate customer success, or optimize net revenue retention") but omits body-level capabilities like health scoring, PQA routing, and closed-lost re-engagement, leaving minor coverage gaps.	4 / 5
Completeness	Both what and when are present — explicit "When the user wants to..." and "Also use when the user mentions..." clauses plus a "Do NOT use for..." boundary — but the what ("covers expansion and retention systems from usage triggers through automated customer success") is more abstract than a concrete capability list, so it falls short of the anchor-5 example.	4 / 5
Trigger Term Quality	Comprehensive natural trigger terms ("churn," "upsell," "NRR," "net revenue retention," "land and expand," "closed-lost," "renewal") including both acronym and full-form synonyms; only marginal variants like GRR or win-back are absent.	5 / 5
Distinctiveness Conflict Risk	Distinct niche triggers (NRR, land-and-expand, closed-lost) and an explicit exclusion clause make it mostly distinct, but terms like "customer success" and "upsell" carry minor overlap risk with adjacent GTM skills it itself references (ai-pricing, sales-motion-design).	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(gtm)/expansion-retention/SKILL.md
Revision: 1da2195

Reviewed: 2 months ago

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.

expansion-retention

Table of Contents

Is this your skill?