PreToolUse
01RaNDoM6913/claude-code-superkit
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing superkit-meta-check.sh and superkit-counts-verify.sh (2 commands). From RaNDoM6913/claude-code-superkit.
RaNDoM6913/claude-code-superkit
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing superkit-meta-check.sh and superkit-counts-verify.sh (2 commands). From RaNDoM6913/claude-code-superkit.
RaNDoM6913/claude-code-superkit
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse).
RaNDoM6913/claude-code-superkit
Instructions file
Instructions for RaNDoM6913/claude-code-superkit, covering claude-code-superkit, project structure, current counts, conventions and mandatory documentation updates.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Clean AI-generated code patterns — redundant comments, unnecessary abstractions, over-engineering, template code.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Verify OpenAPI/Swagger spec matches actual route registrations and handler implementations.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
System design advisor — evaluates trade-offs, proposes architecture for new features, reviews refactoring plans.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Audit backend code for SQL safety, error handling, auth coverage, PII exposure, dead code, TODO density.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Audit frontend code for hardcoded values, console.log, TypeScript strict, dead imports, design tokens, accessibility.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Audit infrastructure — secrets, Docker, deps, CORS, webhooks, migrations, CI/CD, monitoring.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Run comprehensive parallel audit — dispatches specialized agents by scope (frontend, backend, infra, security).
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Behavioral psychology specialist for retention, habit loops, and notification cadence. Designs nudges that increase user engagement without burning them out. Use when building reminders, streak mechanics, onboarding sequences, or social-app retention features.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Run Go benchmarks with statistical analysis and optional comparison.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Review chat bot code (Telegram, Discord, Slack) for callback safety, state machines, rate limits, and production readiness.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Generic code review — layers, error handling, naming, DI, SQL safety, auth, tests.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
First-pass analyst for unfamiliar codebases — maps tech stack, architecture layers, conventions, hot paths, and known constraints into a concise onboarding brief.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Detect stale comments, outdated TODOs, doc rot -- comments that lie about the code.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Conventional commit helper — analyze changes, detect secrets, create well-formatted commit.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Final quality gate — multi-perspective review (security, new-hire, ops) with gap analysis, pre-commitment predictions, and a single APPROVE/CONCERN/BLOCK verdict.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
PostgreSQL database specialist — query optimization, schema design, index strategy, migration safety, anti-patterns.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Multi-source debug — Docker logs, Redis inspection, SQL diagnostics, git blame, execution traces.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Audit dependencies — npm audit, govulncheck, pip-audit, cargo-audit, outdated packages, update plan.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Review UI components against the project's design system tokens — colors, spacing, typography, z-index, animations.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Full-stack development orchestrator -- always-on, 16 phases (0-15): read-docs -> understand -> architect -> pseudocode -> plan -> contract -> validate -> implement -> evaluate -> verify -> test -> goals -> review -> critic -> document -> report.
RaNDoM6913/claude-code-superkit
Skill Claude CodeCodex
Documentation review — freshness check (git diff vs docs) + accuracy validation (claims vs code) + coverage audit.