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 drop off", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", "user activation", or "aha moment". Also trigger when analyzing cohort retention curves, designing activation milestones, reducing time-to-value for new users, or investigating why users stop 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

88%

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

75%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 strong instruction-only skill: highly actionable diagnostic tables, templates, and copy patterns with well-organized one-level-deep references. The main costs are token padding (author bio, further reading, repeated bullet lists) and a body that carries more framework detail than an overview needs, duplicating content that already lives in the reference files.

Suggestions

Remove or drastically shorten the "About the Author" and "Further Reading" sections — the bio and affiliate book links add ~200 tokens with no operational value.

Cut the "Key insights" bullet lists that restate each element's "Core concept" paragraph, keeping only genuinely additive insights such as the Fogg quotes.

Slim the inlined Action Line and Tiny Habits sections to overviews and push their detail into behavior-model.md and tiny-habits.md, which already cover it, so SKILL.md functions as a true index.

DimensionReasoningScore

Conciseness

The core guidance is dense and table-formatted, but there is real padding: an "About the Author" bio of BJ Fogg, affiliate-tagged "Further Reading" links, and "Key insights" bullet lists that largely repeat each section's "Core concept" paragraph.

3 / 5

Actionability

For an instruction-only skill the guidance is fully actionable: the fill-in recipe "After I [ANCHOR MOMENT], I will [TINY BEHAVIOR], then I [CELEBRATION]", metric→diagnosis→action retention tables, concrete copy patterns, a "rate each of the six factors 1-5" friction audit, and a 0-10 scoring instruction with required output.

5 / 5

Workflow Clarity

The 5-step Behavior Design Process (Clarify → Explore → Match → Start Tiny → Optimize) is clearly sequenced and the Quick Diagnostic table serves as a checkpoint, but steps lack explicit validation/feedback loops such as how to verify a tiny behavior is wired before scaling.

4 / 5

Progressive Disclosure

All 7 bundle files exist, are one level deep, and are well signaled both inline ("See: references/… for deep dive on…") and in a Reference Files index; the ~250-line body still inlines substantial detail (Action Line, Tiny Habits) that overlaps the reference files, keeping it shy of a pure overview.

4 / 5

Total

16

/

20

Passed

Description

95%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 capabilities in third person, a rich set of natural trigger phrases, explicit what/when guidance, and explicit disambiguation against adjacent skills. The only weakness is that some of the skill's actual tools (friction audits, Tiny Habits recipe) are only gestured at rather than named as actions.

DimensionReasoningScore

Specificity

Names concrete actions ("Diagnose and fix retention problems", "analyzing cohort retention curves, designing activation milestones, reducing time-to-value") in third-person voice, with minor coverage gaps — the friction audit and Tiny Habits recipe are only implied via "Covers the Ability Chain, prompt design, and tiny behaviors that compound".

4 / 5

Completeness

Explicitly answers both what ("Diagnose and fix retention problems using behavior design (B=MAP)… Covers the Ability Chain, prompt design, and tiny behaviors") and when ("Use when the user mentions…", "Also trigger when…") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases with synonyms a user would actually say: "users drop off", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", "aha moment", "time-to-value", "cohort retention curves".

5 / 5

Distinctiveness Conflict Risk

Clear retention/behavior-design niche with distinct triggers, and it explicitly routes overlapping topics to neighbors: "For habit loops and variable rewards, see hooked-ux. For intrinsic motivation, see drive-motivation."

5 / 5

Total

19

/

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

valeriibeck-star/claude-skills

Path

skills/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.