CtrlK
BlogDocsLog inGet started
Tessl Logo

epic-hypothesis

Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning.

72

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

77%

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

The content is well-structured and highly actionable with a clear validated workflow, but it is over-long for what it teaches and references bundle files (template.md, examples/sample.md) that are not actually present in the skill bundle.

Suggestions

Trim the duplicate Purpose paragraph and the 'Why This Structure Works'/'Anti-Patterns' sections that restate Lean UX concepts Claude already knows, to reduce token cost.

Create the referenced template.md and examples/sample.md files (or remove the references and keep that content inline), since progressive disclosure points to files that do not exist.

Consolidate the six Common Pitfalls into a tighter list; several (e.g. Pitfall 5) restate guidance already given in the Anti-Patterns section.

DimensionReasoningScore

Conciseness

The body repeats the description in the Purpose section and the 'Why This Structure Works' / 'Anti-Patterns' sections explain Lean UX concepts Claude already knows; the long examples and pitfalls block could be tightened.

2 / 3

Actionability

Provides concrete fill-in templates, specific contrastive quality checks (e.g. 'Not "improve the product" but "add one-click Slack notifications..."'), and concrete ✅/❌ examples — fully actionable guidance.

3 / 3

Workflow Clarity

A clear 6-step sequence (Gather Context → Draft → Experiments → Validation → Run & Evaluate → Convert) with explicit decision points and a ✅/❌/⚠️ validation feedback loop in Step 5.

3 / 3

Progressive Disclosure

The body references template.md and examples/sample.md, but neither file exists in the bundle, and substantial template/example content is inlined rather than split out; structure is present but the references are dangling.

2 / 3

Total

10

/

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.

The description is concise, action-oriented, and clearly states both what the skill does and when to use it, in third person. It is well above the rubric's good-example bar with no padding.

DimensionReasoningScore

Specificity

Names multiple concrete components of the work — 'target user, expected outcome, and validation method' — describing specific actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what it does (frame an epic as a testable hypothesis) and when to use it ('Use when defining a major initiative before roadmap, discovery, or delivery planning').

3 / 3

Trigger Term Quality

Uses natural product-management phrasing a user would say ('defining a major initiative', 'roadmap, discovery, or delivery planning') with good coverage of relevant terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — epic-hypothesis framing for product planning — with distinct triggers, third-person voice, and low risk of conflicting with other 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
deanpeters/Product-Manager-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.