dialectical_materialism_skill

This skill enforces dialectical reasoning to analyze complex problems, reveal root causes, and optimize architecture under resource and trade-off constraints.
  • Python

2

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill jwcodewrote/agent_skills_plugin --skill dialectical_materialism

  • SKILL.md10.4 KB

Overview

This skill is a cognitive operating system that applies Dialectical Materialism to force objective, non-linear analysis of engineering and logic problems. It grounds decisions in material constraints, system connections, evolutionary stages, and internal contradictions to produce actionable root-cause insights and synthesis strategies. Use it to move from symptom-level fixes to structural, defensible change.

How this skill works

The skill inspects system context across five core modules: material constraints, causal chains, contradictions, development stage, and synthesis. It automatically selects the appropriate dialectical law by parsing keywords and metrics, then runs structured checks (constraints list, cause isolation, polarity definition, threshold detection, thesis/antithesis/synthesis). Outputs are concrete recommendations, trade-offs, and diagram suggestions when visualizing contradictions will clarify outcomes.

When to use it

  • Complex debugging where surface errors may hide architectural causes
  • Strategic planning: deciding between incremental optimization and full rewrite
  • Deployments with strict hardware, latency, or budget constraints
  • Root cause analysis of cascading or intermittent failures
  • Refactoring or migration that must preserve valuable behaviors while removing fatal flaws

Best practices

  • Start by listing immutable material constraints (VRAM, budget, latency) before proposing fixes
  • Isolate external vs. internal causes to avoid misattributing symptoms
  • Name opposing forces explicitly (e.g., performance vs. reliability) and identify the principal contradiction
  • Use quantitative thresholds to detect nodal points that justify architecture change
  • When recommendations are complex, include a contradiction matrix or evolution spiral to communicate trade-offs clearly

Example use cases

  • Diagnose why memory leakage appears only under specific traffic patterns by tracing causality chains
  • Decide whether 50x user growth necessitates microservices and sharding rather than query optimization
  • Evaluate feasibility of running a large model on constrained hardware and propose quantized or cloud alternatives
  • Refactor a monolithic 'God Class' by preserving edge-case handling while decomposing responsibilities
  • Resolve product conflicts where security requirements clash with usability by identifying the principal aspect and proposing a synthesis

FAQ

It analyzes keywords and quantitative signals (e.g., hardware, bottleneck, rewrite, growth) and matches them to the best-fit module: material checks, contradiction analysis, development-stage assessment, or synthesis.

Will it produce diagrams automatically?

It suggests appropriate diagrams (contradiction matrix, dependency graph, evolutionary spiral) and can describe how to draw them, but it does not auto-generate graphical files.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational