CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-coder

Agent skill for coder - invoke with $agent-coder

40

1.12x

Quality

13%

Does it follow best practices?

Impact

79%

1.12x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Evaluation results

80%

30%

Inventory Management Module

Module file organization and JSDoc documentation

Criteria
Without context
With context

Service file exists

62%

100%

Controller file exists

62%

100%

Repository file exists

62%

100%

Types file exists

62%

100%

Test file exists

62%

100%

Dependency injection

100%

100%

TypeScript interface

100%

100%

Custom error class

50%

100%

JSDoc on public functions

0%

0%

JSDoc @throws tag

0%

100%

JSDoc @example tag

0%

0%

Without context: $0.7430 · 2m 47s · 34 turns · 41 in / 12,123 out tokens

With context: $0.6854 · 2m 27s · 29 turns · 66 in / 10,676 out tokens

72%

-1%

Notification Delivery Service

Test-driven development and custom error handling

Criteria
Without context
With context

Tests written first

25%

0%

Edge case tests

100%

100%

External dependencies mocked

100%

80%

Custom error class

50%

100%

Error handling with logging

0%

0%

Rethrow as custom error

100%

100%

Async/await modern syntax

100%

100%

Arrow functions used

100%

100%

TypeScript interface defined

100%

100%

Function size constraint

100%

100%

Destructuring used

50%

33%

Without context: $0.5750 · 2m 30s · 31 turns · 79 in / 8,866 out tokens

With context: $0.7956 · 2m 58s · 36 turns · 2,877 in / 10,863 out tokens

87%

-2%

User Analytics Pipeline Optimization

Performance optimization patterns and function size

Criteria
Without context
With context

Map for lookups

100%

100%

Promise.all for batch ops

100%

100%

Memoization applied

100%

100%

Function size constraint

100%

70%

Single responsibility

50%

50%

DRY abstraction

100%

100%

TypeScript typing

100%

100%

Dependency injection

100%

100%

Async/await syntax

100%

100%

Meaningful naming

80%

100%

Lazy loading used

0%

0%

Without context: $0.4218 · 2m 19s · 19 turns · 22 in / 7,463 out tokens

With context: $0.3744 · 1m 52s · 18 turns · 269 in / 5,573 out tokens

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.