Draw — Security skill for Claude Code
Run the anti-pattern selector standalone to verify the rotation rule and audit log.
How to install Draw
Installs to ~/.claude/skills/raymondware-kern-draw/SKILL.md
mkdir -p ~/.claude/skills/raymondware-kern-draw && curl -fsSL https://raw.githubusercontent.com/raymondware/kern/HEAD/commands/draw.md -o ~/.claude/skills/raymondware-kern-draw/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Draw does
description: "Run the anti-pattern selector standalone to verify the rotation rule and audit log." allowed-tools: ["Read", "Write", "Bash", "Glob"]
/kern:draw
Runs the anti-pattern-selector by itself, prints the drawn subset, and confirms the audit append. No design, no critique, no implementation. Use this to:
- Verify rotation works (run twice in a row, compare subsets)
- Inspect the audit log
- Sanity-check site-specific inclusions for a given input
- Debug why a recent kern run
Alternatives in Security
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
- Eval Security — /eval-security — Standalone Security Scan 216 ★
- Audit Architecture — Comprehensive architecture audit with pattern recommendations 63 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Skill Detail
Shared model-rubric detail + plan-doc update pattern for gate-a~e, audit, doc-cleanup. Load on demand (not aut
Audit MCP Mock Drift
Catch mock/live divergence in MCP eval golden tests (anti-pattern #2 from eval-mock-mode-discipline)
Ultra Test
Pre-delivery quality audit (Anti-Pattern + Coverage Gap + E2E + Performance + Security)
Review UX Audit
Full UX audit of a frontend codebase. Produces persona cards, journey maps, heuristic sweep, anti-pattern find
Evaluator Library
Dispatch a fresh-context evaluator against a domain rubric. Bundled domains: code-quality, ui-design, prose, s
Push Back
Verify a claim against code+docs+memory before acting. Run when a finding/audit/recommendation looks suspect,
Related Agents
Anti Pattern Selector
Selects a varied subset of anti-patterns for the current kern run. Reads the manifest plus site-specific signa
Code Audit Frontend
Comprehensive code review, security audit, performance analysis, and architectural assessment. Goes beyond lin
Harness Auditor
기존 Claude Code 하네스의 구성 정합성·anti-pattern·권한 안전성·에이전트-플레이북 매핑을 CRITICAL/HIGH/MEDIUM/LOW 4등급으로 진단. /harness-archi