fresh-eyes

Propose simpler first-principles redesigns of modules, configs, and workflows validated against existing constraints.

4|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/staticaland/skills --skill fresh-eyes-staticaland
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fresh-eyes
Source: https://github.com/staticaland/skills/tree/main/plugins/fresh-eyes/skills/fresh-eyes
Command: npx skills add https://github.com/staticaland/skills --skill fresh-eyes-staticaland

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Complex systems accumulate accidental complexity over time, and teams stop questioning why things are built the way they are. This Skill performs a structured fresh-eyes review: it designs the simplest possible solution from the stated purpose alone, then tests each proposal against the real constraints that shaped the current implementation. ## Core Features & Use Cases - Purpose-First Design: Writes a one-paragraph purpose statement free of current implementation details, then designs naive proposals from it without anchoring to the existing mechanism. - Fence Walking: Investigates every difference between a proposal and the current shape using git log, blame, comments, issues, and tests, classifying each constraint as live, dead, or unknown. - Survivor Report: Delivers ranked proposals with verdicts on each constraint, the cost of absorbed constraints, evidence for dead ones, and flagged unknown risks. - Use Case: When a developer asks "why is this config pipeline so complicated?" or "why don't we just use a single file?", the Skill produces a first-principles redesign and an evidence-backed explanation of which simplifications are safe. ## Quick Start Ask the AI to do a fresh-eyes review of the authentication module and explain why it is so complicated.

Frequently Asked Questions about fresh-eyes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I do a first-principles review of an existing module?▼

State the module's purpose in one paragraph without naming any current classes, files, or steps, then design the simplest thing that could serve that purpose. Finally, test each proposal against the constraints that shaped the current implementation before recommending changes.

How to tell if code complexity is necessary or accidental?▼

Investigate each difference between a simpler proposal and the current shape using git log, blame, comments, linked issues, and tests. Classify each as live (constraint still holds), dead (constraint no longer applies, with evidence), or unknown (no reason found).

Does a fresh-eyes review modify my code?▼

No. The deliverable is a report of surviving proposals with their constraint verdicts; the target module, config, or workflow is left untouched. Any redesign is only proposed, never applied.

What happens when no simpler design survives the review?▼

That outcome is itself the report: the current shape is earned, justified by the list of live constraints discovered during the investigation. You get documented evidence for why the complexity exists rather than a forced simplification.

When should I not use a fresh-eyes simplification review?▼

Avoid it when you need a bug fix or feature implemented directly, since the Skill only produces analysis and proposals. It also requires access to history such as git logs, issues, or tests to classify constraints reliably.