Delegate independent tasks to specialized agents working concurrently with isolated context.
Safe Rewriting Advisor
**Category**: Graph Optimization + Remediation **Type**: Strategic Edge Removal Analysis **Language**: Julia **Status**: Production Ready **Version**: 1.0.0 **Date**: December 22, 2025
SKILL.md
Full skill instructions
Safe Rewriting Advisor
Category: Graph Optimization + Remediation Type: Strategic Edge Removal Analysis Language: Julia Status: Production Ready Version: 1.0.0 Date: December 22, 2025
Overview
Strategic selective edge removal maintaining spectral gap ≥ 0.25. Analyzes edge criticality via betweenness centrality to identify which proof dependencies can be safely removed without breaking system connectivity (Ramanujan property).
Key Data Structures
struct EdgeImportance
edge_id::Tuple{Int, Int}
betweenness_centrality::Float64
gap_sensitivity::Float64
redundancy_score::Float64
recommendation::String
end
struct RewritePlan
edges_to_remove::Vector{Tuple{Int, Int}}
edges_to_split::Vector{Tuple{Int, Int}}
cycle_breakers::Vector{String}
expected_gap_before::Float64
expected_gap_after::Float64
safe::Bool
complexity::String
end
Key Functions
compute_edge_importance(adjacency): Betweenness centrality analysisidentify_redundant_edges(edges): Find safe-to-remove edgesgenerate_rewrite_plan(adjacency, gap): Strategic remediationgenerate_rewrite_report(adjacency, gap): Human-readable analysis
Mathematical Foundation
Edge Criticality Classification
gap_sensitivity > 80% : CRITICAL - essential for connectivity
40-80% : IMPORTANT - remove only if necessary
< 40% : REDUNDANT - safe to remove
Uses betweenness centrality to measure how many paths depend on each edge. Recommends cycle-breaking via intermediate theorems for low-gap systems.
Usage
using SafeRewriting
# Analyze current system
plan = generate_rewrite_plan(adjacency, current_gap)
# Check if transformation is safe
if plan.safe && plan.expected_gap_after >= 0.25
println("✓ Safe to apply $(length(plan.edges_to_remove)) edge removals")
println(" Gap projection: $(plan.expected_gap_before) → $(plan.expected_gap_after)")
end
# Get recommendations
report = generate_rewrite_report(adjacency, current_gap)
Integration Points
- Week 4 remediation planning phase
- Automated maintenance pipeline for continuous-inverter
- Gap recovery strategy after tangled dependencies identified
Performance
- Edge analysis: < 2 seconds
- Plan generation: < 1 second
- Scales to 100,000+ edges
References
- Betweenness centrality: Freeman (1977)
- Graph remediation strategies for network optimization
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
