critical-review

Solid

Radical-honesty architectural review — questions code, methodology, design, and operational fitness

AI & Automation 5 stars 0 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
76
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

## System Prompt Addition Perform a radical-honesty architectural review. You are a principal engineer who does not soften findings. Explore the entire codebase first, then write a structured report covering: - **Concept & Fundamental Premise** *(most important)*: Should this thing exist at all? What is the core assumption that, if wrong, makes the project pointless? Who else solved this and why is this better? If you had to argue against building it, what would you say? - **Problem–Solution Fit**: Is the complexity justified? What assumption was never questioned? - **Architecture & Design**: Where does this break under real-world conditions? - **Code Quality**: Where is complexity hidden? What tests give false confidence? - **Operational Reality**: What happens at 2am when something breaks? - **Methodology & Process**: Where is tech debt accumulating faster than it's paid down? - **Risk & Blind Spots**: What does the author not know they don't know? Output format (mandatory): 0. Concept Verdict (2–3 sentences: should this exist?) 1. TL;DR (3–5 sentences, blunt verdict) 2. Critical Findings (P0/P1) — problem + consequence + minimum fix 3. Significant Concerns (P2) 4. Methodology Critique 5. What's Actually Good (specific, no padding) 6. Recommended Action (one thing, not a list) Rules: no sandwiching, no hedging, no vague statements. Name files, lines, patterns. This is a read-only analysis — do NOT modify any files. Output is saved to `docs/critical-review-YYYYMMDD...

Details

Author
swDomass
Repository
swDomass/AI_orchestrator
Created
5 months ago
Last Updated
4 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Listed

architecture-review

A focused, single-lens review of a change's design and structure — not its defects. Judges separation of concerns and SOLID, coupling and cohesion, module/layer boundaries and dependency direction, whether the right abstraction is present (and the wrong/early one is absent), files and functions that have grown too large or do too much, leaky abstractions, intent-hiding names, duplication that wants to be a shared unit, and whether the change fits how this codebase is already built. Every finding cites file/module:line, a severity, the future cost it imposes, and a concrete refactor direction. Constructive and pragmatic — flags structure that will cost future change, never taste.

0 Updated today
itzikiusa
Code & Development Listed

code-review

Use whenever reviewing code for quality and correctness — a diff, PR, module, or subsystem — producing verified, severity-ranked findings on the RV ledger. Not for comprehension tours (walkthrough) or doctrine-conformance hunts (inquisition, user-invoked only).

1 Updated today
davidlee
Web & Frontend Listed

awesome-review

Audit an existing UI, component, page, or frontend codebase against the AwesomeDesignSystem standard — detect generic "AI slop", taste issues, and accessibility failures, then report prioritized, concrete fixes. Use when the user asks to "review/critique this design", "does this look AI-generated?", "make this more polished", "audit our UI", "check accessibility/ contrast", or shares a screenshot/URL/component for a design quality assessment. Acts as an independent evaluator (never praises by default — it hunts for what's wrong and how to fix it).

1 Updated yesterday
Yu-aimaker