CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

improve-retention

Diagnose and fix retention problems using behavior design (B=MAP). Use when the user mentions "users sign up but dont stick around", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", or "aha moment". Also trigger when analyzing cohort retention curves, designing activation milestones, reducing time-to-value for new users, or investigating why users quit after their first session. Covers the Ability Chain, prompt design, and tiny behaviors that compound. For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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-structured and highly actionable, with excellent progressive disclosure via real one-level references. Its main weakness is mild over-explanation of the B=MAP model itself and a few diagnoses that would benefit from concrete quantitative thresholds and an explicit verify/retry loop.

Suggestions

Trim conceptual re-explanation of motivation waves and the Action Line narrative where the model is already introduced, trusting Claude to apply the framework once the equation and tables are given.

Add concrete quantitative thresholds to the retention diagnostics (e.g., "Day-1 drop-off > X%") so diagnoses are executable rather than qualitative.

Add an explicit validate→fix→retry loop after the Quick Diagnostic (re-score after each intervention) to turn the scoring rubric into a closed feedback cycle.

DimensionReasoningScore

Conciseness

Largely lean and table-driven, assuming Claude's competence, but a few passages re-explain the underlying model (e.g., "Motivation comes in waves — it spikes... and crashes") that could be trimmed. Not a 5 because minor over-explanation remains; not a 3 because the bulk is efficient and unpadded.

4 / 5

Actionability

Provides concrete, usable artifacts — the Quick Diagnostic table, the retention-metrics→B=MAP→action mapping, copy patterns, and the Tiny Habits recipe template — but lacks executable thresholds/quantitative cutoffs for some diagnoses. Not a 5 due to minor specificity gaps; not a 3 because the guidance is directly applicable rather than abstract.

4 / 5

Workflow Clarity

The 5-step Behavior Design Process is clearly sequenced and the Scoring section supplies explicit pass/fail logic and a subtraction rubric as a checkpoint. Not a 5 because the diagnostic-to-action flow lacks an explicit verify/retry feedback loop; not a 3 because checkpoints (rate rows, state score) are present.

4 / 5

Progressive Disclosure

SKILL.md is a clear overview with well-signaled one-level-deep references — each section ends "See: references/X.md for..." — and all seven referenced files exist with no nested pointer chains, making navigation easy.

5 / 5

Total

17

/

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.

The description is exemplary: it states concrete capabilities, includes abundant natural trigger phrases, answers both what and when explicitly, and carves out a distinct niche with sibling-skill disambiguation. No meaningful gaps to address.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Diagnose and fix retention problems", "analyzing cohort retention curves", "designing activation milestones", "reducing time-to-value" — with comprehensive coverage of the behavior-design domain.

5 / 5

Completeness

Explicitly answers both what ("Diagnose and fix retention problems using behavior design (B=MAP)" plus the Ability Chain, prompt design, tiny behaviors) and when ("Use when the user mentions..." plus an "Also trigger when..." clause with concrete triggers).

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ("users sign up but don't stick around", "activation rate", "onboarding friction", "churn analysis", "aha moment") including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear retention/behavior-design niche with distinct triggers, and it actively disambiguates siblings ("For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation."), minimizing conflict risk.

5 / 5

Total

20

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

wondelai/skills

Path

improve-retention/SKILL.md

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.