CtrlK
BlogDocsLog inGet started
Tessl Logo

requirements-clarity

Clarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are complex (>2 days), or involve cross-team coordination. Ask two core questions - Why? (YAGNI check) and Simpler? (KISS check) - to ensure clarity before coding.

76

1.63x
Quality

62%

Does it follow best practices?

Impact

100%

1.63x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/requirements-clarity/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

20%

Requirements Intake Triage

Activation detection and initial assessment

Criteria
Without context
With context

Activate on Request 1

100%

100%

No activation on Request 2

100%

100%

Correct non-activation reason

100%

100%

Clarity score shown

0%

100%

Clear aspects listed

100%

100%

Gaps listed

100%

100%

Score reflects low clarity

0%

100%

Identifies functional gaps

100%

100%

Identifies technical gaps

100%

100%

Announces clarification intent

100%

100%

responses.md created

100%

100%

100%

44%

Requirements Clarification Dialogue

Multi-round clarification dialogue and scoring

Criteria
Without context
With context

Initial score shown

0%

100%

Low initial score

0%

100%

Questions per round limited

100%

100%

Category labels in questions

100%

100%

Score update after round 1

0%

100%

Summarizes new content

57%

100%

Lists remaining gaps

42%

100%

Continues if below 90

100%

100%

Score update after round 2

0%

100%

Declares readiness at 90+

60%

100%

Covers all four gap dimensions

100%

100%

clarification-dialogue.md created

100%

100%

Final Assessment section

75%

100%

100%

53%

Feature Requirements to PRD

PRD generation and file structure

Criteria
Without context
With context

Correct directory created

0%

100%

Correct file path

0%

100%

Kebab-case filename

100%

100%

Version in filename

100%

100%

Requirements Description section

28%

100%

Design Decisions section

42%

100%

Acceptance Criteria with checkboxes

100%

100%

Functional acceptance items

71%

100%

Quality Standards items

50%

100%

Execution Phases present

62%

100%

Document Version in footer

0%

100%

Clarification Rounds in footer

42%

100%

Quality Score in footer

42%

100%

Created timestamp in footer

0%

100%

Repository
softaworks/agent-toolkit
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.