CtrlK
BlogDocsLog inGet started
Tessl Logo

clarity

Establish clarity before starting work. Use when beginning any significant task, when input is vague or stream-of-consciousness, or when requirements seem unclear. Handles messy voice input efficiently. This is the first system in the 5-system framework.

76

1.26x

Quality

58%

Does it follow best practices?

Impact

85%

1.26x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/data/1-clarity/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

13%

Onboarding to a New Microservice Project

Full clarity protocol and active-context.md creation

Criteria
Without context
With context

File at correct path

100%

100%

Current Task section

44%

100%

Success Criteria section

55%

100%

In Scope subsection

100%

100%

Out of Scope subsection

100%

100%

Constraints section

77%

100%

Open Questions section

100%

100%

Assumptions section

100%

100%

Last updated timestamp

77%

100%

Specific success criteria

100%

100%

Open questions address unknowns

100%

100%

Without context: $0.1809 · 1m 6s · 8 turns · 11 in / 2,998 out tokens

With context: $0.2801 · 1m 13s · 15 turns · 18 in / 3,440 out tokens

55%

40%

Handling Inbound Feature Requests from Stakeholders

Messy input distillation and minimal clarification questions

Criteria
Without context
With context

WHAT label for Message 1

0%

100%

WHY label for Message 1

0%

100%

SCOPE label for Message 1

0%

100%

Message 1 summary is concise

60%

100%

Message 1 question limit

0%

50%

Message 2 handled efficiently

0%

0%

Message 3 handled efficiently

0%

0%

Specific clarifying questions

90%

100%

No over-documentation of clear requests

0%

0%

Brief confirmation phrase

0%

0%

Without context: $0.1041 · 36s · 8 turns · 13 in / 1,720 out tokens

With context: $0.2403 · 1m 1s · 16 turns · 20 in / 2,828 out tokens

100%

Updating Project Context After a Strategy Change

Scope change handling and active-context.md update

Criteria
Without context
With context

active-context.md updated

100%

100%

Timestamp updated

100%

100%

Multi-currency removed from In Scope

100%

100%

PDF generation added to In Scope

100%

100%

Multi-currency added to Out of Scope

100%

100%

Success criteria updated

100%

100%

SOURCE_OF_TRUTH.md content reflected

100%

100%

New open questions added

100%

100%

Assumptions updated

100%

100%

Constraints reflect PDF library

100%

100%

Without context: $0.1449 · 54s · 9 turns · 14 in / 1,979 out tokens

With context: $0.3123 · 1m 14s · 18 turns · 21 in / 3,382 out tokens

Repository
majiayu000/claude-skill-registry
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.