CtrlK
BlogDocsLog inGet started
Tessl Logo

diagnose-retention

Diagnose where and why users churn, identify natural usage frequency, build cohort retention curves, and find the behaviors that drive long-term retention. Use when a PM needs to understand churn, improve retention curves, or identify what makes users stick.

74

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable analytical prompt template with clear sequencing and concrete benchmarks. Its main weakness is a verbose, motivational framing that assumes Claude needs persuasion rather than just instruction.

Suggestions

Trim the opening paragraph and the persona lecture ("Retention is the single most important growth lever...", "never accept 'let's improve engagement' as a strategy") to retain only the analytical instructions.

Move the benchmark table and the anti-plays list into a short reference block or keep them but cut redundant restatements of why retention matters.

DimensionReasoningScore

Conciseness

Mostly efficient and information-dense, but the motivational intro ("Retention is the single most important growth lever because it compounds...") and persona lecture ("never accept 'let's improve engagement' as a strategy") explain framing Claude does not need, so it could be tightened.

2 / 3

Actionability

Highly concrete guidance for an instruction-only skill: specific benchmark bands ("Consumer social: D1 ~40%, D30 ~20-25%"), explicit segment dimensions, habit-loop cue/routine/reward, and worked correlation examples ("D60 retention of 72% vs. 31%").

3 / 3

Workflow Clarity

A clearly sequenced five-step process (baseline → segment → behaviors → churn moments → plan) with an explicit output-format checklist; validation checkpoints are not required since this is analytical, not destructive/batch work.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the single-file prompt template is well-organized into headed sections (Steps 1-5, Output Format, Tips) with no nested references, appropriate for a skill meant to be injected as one prompt.

3 / 3

Total

11

/

12

Passed

Description

100%

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: concrete actions, explicit "Use when" trigger guidance, third-person voice, and a clear niche. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Diagnose where and why users churn", "identify natural usage frequency", "build cohort retention curves", "find the behaviors that drive long-term retention" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both what (diagnose churn, find frequency, build curves, find behaviors) and when ("Use when a PM needs to understand churn, improve retention curves, or identify what makes users stick").

3 / 3

Trigger Term Quality

Covers natural terms a PM would say — "churn", "retention curves", "retention", "what makes users stick" — giving good domain coverage rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (cohort retention/churn analysis) with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
amplitude/builder-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.