Metalnib

Dotnet Refactor — Security skill for Claude Code

Security community

Phase-gated refactoring/design loop - session-blind subagents build the map and traces, empirical probes precede the design, an approval gate guards implementation, and a conformance audit re-checks t.

How to install Dotnet Refactor

Installs to ~/.claude/skills/metalnib-dotnet-episteme-skills-dotnet-refactor/SKILL.md

Terminal
mkdir -p ~/.claude/skills/metalnib-dotnet-episteme-skills-dotnet-refactor && curl -fsSL https://raw.githubusercontent.com/Metalnib/dotnet-episteme-skills/HEAD/commands/dotnet-refactor.md -o ~/.claude/skills/metalnib-dotnet-episteme-skills-dotnet-refactor/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Dotnet Refactor does

description: Phase-gated refactoring/design loop - session-blind subagents build the map and traces, empirical probes precede the design, an approval gate guards implementation, and a conformance audit re-checks the whole branch after any design change. State persists in .episteme/DESIGN-.md so the loop survives compaction and fresh sessions. argument-hint: " [--design-file ] [--lite] e.g. YB-1234 or 'error handling in OrderService'"

/dotnet-refactor - orchest

Alternatives in Security

  • Security Ownership Map — Map people-to-file ownership, compute bus factor, and identify risks 14.6k ★
  • Skill Coverage Audit — Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs 2.8k ★
  • Engage.Exploit — Execute Phase 4 - Exploitation and Access Establishment 348 ★

Full documentation available on GitHub

View Source Repository

Related Skills

UX UI Audit — Security skill for Claude Code

UX UI Audit

Evidence-backed UX/UI audit skill for Claude. Browser probes that measure real numbers — WCAG contrast, Fitts,

Security community
Cve Freshness Loop — Security skill for Claude Code

Cve Freshness Loop

Turn a fresh CVE disclosure into a running probe in minutes — KEV/EPSS feed → variant pack or ad-hoc probe → o

Security community
Loongsuite Pilot — Security skill for Claude Code

Loongsuite Pilot

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cu

Security community
Dotnet Review — Security skill for Claude Code

Dotnet Review

Multi-agent .NET code review - up to five reviewers in parallel (correctness, performance, security/observabil

Security community
Security Audit Database — Security skill for Claude Code

Security Audit Database

Use when auditing a database-backed app for the most common database security mistakes — multi-tenant data lea

Security community
Millieskills — Security skill for Claude Code

Millieskills

Research-driven universal AI Agent Skills for UI/UX, code repair, security, testing, architecture, backend/API

Security community

Related Agents

Biz Planner — Project Management agent for Claude Code

Biz Planner

Autonomous idea-to-execution planner — runs the biz-planner workflow (scoping, decision questions, criteria-dr

Project Management community
Blind Probe Author — Development agent for Claude Code

Blind Probe Author

Writes efficacy-eval scenarios, retrieval probes, and held-out criteria for a document type WITHOUT reading th

Development community
What If — Development agent for Claude Code

What If

Opus 5 plan prober that walks a handed plan against a facet checklist and returns ranked blind-spot probes, ea

Development community