CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hierarchy-of-engagement

Use when asked to "define our core action", "North Star metric", "accruing benefits", "improve retention mechanics", "hierarchy of engagement", or "Sarah Tavel framework". Helps consumer products identify the actions and benefits that drive long-term retention. The Hierarchy of Engagement framework (created by Sarah Tavel at Benchmark) maps progression from core action to mounting loss.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/hierarchy-of-engagement/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

18%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 a conceptual overview of the Hierarchy of Engagement framework with good use/not-use scoping, but it contains no actionable procedure, no application steps, and no worked example — it tells Claude what the framework is without how to execute it. Boilerplate sections and conceptual padding further reduce its value per token.

Suggestions

Add a step-by-step application workflow (e.g., 1. List candidate core actions with usage data, 2. Classify each benefit as tier 1/2/3, 3. Test for accruing benefits and switching costs, 4. Derive the North Star metric and validation checkpoints), replacing the conceptual 'What It Is' padding.

Include a worked example showing a sample product's core action, its three benefit tiers, and the resulting North Star metric, so Claude has a concrete pattern to imitate rather than only a description.

Remove the boilerplate 'Domain Context' section and merge the redundant 'Resources' and 'Further Reading' sections into one clearly signaled list.

DimensionReasoningScore

Conciseness

Noticeably verbose for what it delivers: the "Domain Context" section is pure boilerplate filler ("combines best practices from industry leaders"), and passages like "Most consumer products fail not because they lack users... Getting someone to sign up is one thing; getting them to stay is everything" re-explain a well-known framework concept Claude already knows. It is not 3 because multiple padded sections add no actionable value.

2 / 5

Actionability

The body only describes the framework ("a three-level framework for building consumer products that retain users") and when to use it, but never instructs how to apply it — no steps for identifying a core action, no questions to ask, no worked example, no evaluation criteria for the three tiers. This matches the anchor "only describes rather than instructs".

1 / 5

Workflow Clarity

There is no sequenced process at all: applying this framework is inherently multi-step (surface core-action candidates, categorize benefits into the three tiers, assess accruing benefits and switching costs, derive the North Star metric), yet the body presents no steps or checkpoints in any order. Steps are missing, not merely incomplete, so it is below the level-2 anchor.

1 / 5

Progressive Disclosure

The skill is short (~50 lines) with clear sections (What It Is, When to Use, When Not to Use) and one-level-deep external links, which per the simple-skill guideline could merit a 5. Minor organization gaps hold it to 4: the "Domain Context" section is filler, and "Resources" and "Further Reading" are two redundant sections listing external articles that should be merged.

4 / 5

Total

8

/

20

Passed

Description

78%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 well-constructed description with an explicit trigger list and a clear statement of what the skill does. The main gaps are slightly thin capability coverage relative to the body's claims and a couple of missing natural synonyms in the trigger terms.

DimensionReasoningScore

Specificity

Names the domain ("consumer products") and one or two concrete actions ("identify the actions and benefits that drive long-term retention", "maps progression from core action to mounting loss"), but coverage is not comprehensive — the body claims the framework also supports North Star definition, onboarding design, and feature prioritization, none of which the description mentions.

3 / 5

Completeness

Explicitly answers both questions: the "what" ("Helps consumer products identify the actions and benefits that drive long-term retention") and a fully explicit "when" with concrete quoted trigger phrases ("Use when asked to..."). This matches the anchor-5 example structure closely; it is not level 4 because the when-clause is maximally explicit rather than merely adequate.

5 / 5

Trigger Term Quality

Includes six natural, quotable trigger phrases a PM would actually say ("define our core action", "North Star metric", "improve retention mechanics", "hierarchy of engagement", "Sarah Tavel framework"), but misses common synonyms such as "churn", "stickiness", "switching costs", or "engagement loop".

4 / 5

Distinctiveness Conflict Risk

The named-framework triggers ("hierarchy of engagement", "Sarah Tavel framework") create a clear niche with minimal conflict risk, but broader triggers like "North Star metric" and "improve retention mechanics" could overlap with general metrics or retention skills. Not 5 due to this minor overlap risk; not 3 because the framework-specific triggers dominate.

4 / 5

Total

16

/

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

saski/arnesto

Path

.agents/skills/hierarchy-of-engagement/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.