CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-refinement

Agent skill for refinement - invoke with $agent-refinement

43

1.23x
Quality

13%

Does it follow best practices?

Impact

96%

1.23x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-refinement/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

88%

34%

Notification Service Implementation

TDD Red-Green-Refactor cycle

Criteria
Without context
With context

Tests written before implementation

100%

100%

Red phase described

100%

100%

Green phase described

100%

100%

Refactor phase described

0%

100%

Test file uses beforeEach setup

100%

100%

Tests use mock dependencies

100%

100%

Private helper methods extracted

0%

0%

Jest coverage configured

0%

100%

Coverage thresholds at 80%

0%

100%

Coverage path exclusions

0%

33%

Tests cover both channels

100%

100%

100%

Slow User Permissions API Optimization

Cache-first query optimization

Criteria
Without context
With context

Cache checked first

100%

100%

Single DB query used

100%

100%

JOIN query used

100%

100%

Results cached after DB query

100%

100%

Cache TTL provided

100%

100%

Cache key uses userId

100%

100%

Cache hit test

100%

100%

Cache miss test

100%

100%

Original problem documented

100%

100%

Caching approach documented

100%

100%

100%

20%

Payment Gateway Resilience Layer

Resilience patterns and error hierarchy

Criteria
Without context
With context

CircuitBreaker three states

100%

100%

CircuitBreaker default threshold=5

100%

100%

CircuitBreaker default timeout=60000

0%

100%

Circuit opens on threshold

100%

100%

Circuit half-open reset attempt

100%

100%

Retry exponential backoff

100%

100%

Retry default attempts=3

100%

100%

AppError base class

30%

100%

Typed error subclasses

100%

100%

Operational vs unexpected error handler

50%

100%

Circuit breaker state test

100%

100%

Retry behaviour test

100%

100%

Repository
ruvnet/claude-flow
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.