refactor-pass

Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior.

Install with Tessl CLI

npx tessl i github:pgplex/pgconsole --skill refactor-pass

What are skills?

1.00x

Review — 77%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 97%

↑ 1.00x

Agent success when using this skill

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

91%

-9%

Cleanup Pass: Data Processor Module

Dead code removal and logic simplification

Criteria

Without context

With context

Dead feature flag removed

100%

Dead function removed

100%

Unused imports removed

100%

Loop logic straightened

100%

Ratio calculation simplified

100%

Misplaced indentation fixed

100%

Tests executed

100%

Tests pass

100%

Without context: $0.4282 · 4m 35s · 25 turns · 32 in / 4,866 out tokens

With context: $0.4313 · 4m 27s · 24 turns · 62 in / 4,455 out tokens

100%

Cleanup Pass: Notification Service

Excessive parameter reduction and premature optimization removal

Criteria

Without context

With context

send_notification params reduced

100%

format_log params reduced

100%

Pre-computed priority cache removed

100%

lru_cache removed from channel key

100%

hashlib import removed

100%

Tests updated to match new signature

100%

Tests executed

100%

Tests pass

100%

Without context: $0.4086 · 3m 46s · 23 turns · 71 in / 5,571 out tokens

With context: $0.5468 · 4m 30s · 27 turns · 280 in / 7,016 out tokens

100%

Cleanup Pass: Financial Report Builder

Abstraction suggestion quality and brevity

Criteria

Without context

With context

Dead debug block removed

100%

Misplaced variable fixed in build_chargeback_report

100%

Tests executed

100%

Tests pass

100%

Abstraction suggested for repeated pattern

100%

Abstraction not applied

100%

Suggestions file is concise

50%

100%

No unwarranted abstractions

80%

100%

Without context: $0.3511 · 4m 13s · 18 turns · 25 in / 5,104 out tokens

With context: $0.5230 · 4m 39s · 27 turns · 436 in / 6,430 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Cleanup Pass: Data Processor Module Cleanup Pass: Notification Service Cleanup Pass: Financial Report Builder

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.