CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

product-collapse

Find simpler product behavior by questioning assumed requirements and working backward from a shared vision. Use when exploring simpler workflows, settings, modes, fidelity, or scope and the product direction needs judgment.

Quality

85%

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

86%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.

An exemplary instruction-only judgment skill: lean, well-structured, with concrete directives and a clean one-level reference to worked examples. The only soft spots are that the in-body workflow leans on the external dialectic skill for its core method and the guidance, while specific, stops short of fully prescriptive steps.

DimensionReasoningScore

Conciseness

The body is lean and dense with no padding and no explanation of concepts Claude already knows; every sentence carries a directive (e.g., "Treat existing workflows and guarantees as evidence of earlier choices"), matching the 'every token earns its place' anchor.

5 / 5

Actionability

Concrete, specific directives are present ("Establish the job in the person's terms", "Before calling state redundant, identify the information it carries", "Use disposable data for app experiments") with explicit delegation to sibling skills for execution, but the judgment guidance leaves some steps implicit and the worked examples sit one reference away, so it is not fully copy-paste actionable.

4 / 5

Workflow Clarity

A clear sequence runs from establishing the job, through the greenfield vision and tradeoff comparison, to working backward and delegating the change via collapse-pass; verification checkpoints appear ("Distinguish possible deletions from claims traced against the code", "verify the result"), but the core conversation method is delegated to the dialectic skill, leaving minor gaps in the in-body sequence.

4 / 5

Progressive Disclosure

The body is under 50 lines with well-organized sections and a single one-level-deep reference (references/examples.md) that exists in the bundle and is clearly signaled ("Read [the examples](references/examples.md) for product decisions developed through this method"); sibling-skill links are cross-references, not nested content.

5 / 5

Total

18

/

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 strong description that clearly and explicitly states both what the skill does and when to use it, with natural trigger terms and a distinct niche. Its main weakness is specificity: the stated actions are methods of inquiry rather than concrete capabilities, which slightly blurs what the skill actually produces.

Suggestions

Add one or two concrete outcome-oriented actions to the 'what' clause (e.g., 'compare concrete product experiences and identify which mechanisms could be removed') to lift specificity beyond method-level description.

Consider adding common user phrasings such as 'simplify', 'reduce complexity', or 'cut features' to the trigger clause to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

Names the domain and two method-level actions ("questioning assumed requirements", "working backward from a shared vision") but offers no concrete deliverables or comprehensive action list, matching the 'domain plus 1-2 concrete actions' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

Explicitly answers both: the what ("Find simpler product behavior by questioning assumed requirements and working backward from a shared vision") and an explicit "Use when..." clause with concrete trigger phrases, matching the top anchor; the when clause is already specific so the score-4 anchor (when could be more explicit) does not fit.

5 / 5

Trigger Term Quality

"simpler workflows, settings, modes, fidelity, or scope" gives good natural keyword coverage a user would plausibly say, though common variations like "simplify", "reduce complexity", or "cut features" are absent, keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The product-simplification judgment niche ("the product direction needs judgment") is mostly distinct with clear triggers, with only minor overlap risk against general planning or refactoring skills.

4 / 5

Total

16

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/product-collapse/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.