Claude Skills by baekenough

Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts

Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile

Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation

Quantitative agent evaluation using 4-metric framework (correctness/step_ratio/tool_call_ratio/latency_ratio) with ideal trajectory annotation and capability-categorical taxonomy. Use when measuring agent efficiency, comparing agent variants, or gating new agents through correctness→efficiency phases. Complements harness-eval (SE benchmarks) and evaluator-optimizer (qualitative rubric).

Use when a design or decision needs adversarial multi-round scrutiny from several independent model vendors. Runs anonymized A/B/C reviewer rounds with a rotating judge and produces a consensus report.

Apache Airflow best practices for DAG authoring, testing, and production deployment

Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration

Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)

Analyze project and auto-configure agents, skills, rules, and guides

Audit agent dependencies and references

AWS patterns from Well-Architected Framework

Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.

Monitor Claude Code releases and auto-generate GitHub issues for each new version

Create a new agent with complete structure

code-review-graph (CRG) MCP wrapper — token-efficient context retrieval via AST knowledge graph. Exposes 4 core tools from CRG.

CVE triage workflow for vulnerability analysis, reproduction assessment, and patch verification

YAML-based DAG workflow engine with topological execution and failure strategies

dbt best practices for SQL modeling, testing, and analytics engineering workflows

Routes data engineering tasks to the correct DE expert agent. Use when user requests data pipeline design, DAG authoring, SQL modeling, stream processing, or warehouse optimization.

Research-validated planning — research → plan → verify cycle for high-confidence implementation plans

Multi-angle release quality verification using parallel expert review teams

Generate 4-6 parallel design mockups for rapid visual comparison — adapted from gstack /design-shotgun pattern

Routes development tasks to the correct language or framework expert agent. Use when user requests code review, implementation, refactoring, or debugging.

Refactor code for better structure and patterns

Review code against language-specific best practices

Brand-consistent editorial diagrams — SVG generation for release notes, architecture docs, and marketing materials

Django patterns for production-ready Python web applications

Docker patterns for optimized containerization

Parameterized evaluator-optimizer loop for quality-critical output with configurable rubrics

FastAPI patterns for high-performance async APIs

Fix broken agent references and symlinks

Flutter/Dart development best practices for widget composition, state management, and performance

Full Self Driving — autonomous release loop that processes all auto-dev-eligible GitHub issues until none remain, by repeatedly running /pipeline auto-dev then /homework.

Go backend patterns from Uber style and standard layout

Idiomatic Go patterns from Effective Go

Disciplined goal-to-execution workflow for any user task. Parses objective, asks only for materially missing requirements via ambiguity-gate, inspects repo via idea, plans via sdd-dev or deep-plan, executes safely under project conventions, verifies completion per R020, and reports changed files with evidence. Use when user invokes /goal <task>.

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

hada.io RSS feed monitoring with LLM pre-scout filtering for oh-my-customcode relevance

Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research

Synthesize code harnesses for agent action validation — AutoHarness-inspired verifier/filter/policy generation

Show help information for commands and system

On explicit /homework invocation, analyze the current and linked previous sessions, extract mistakes (찐빠), and report them via omcustom-feedback with a confirmation gate. Auto-activation on session cleanup/session-end signals is OPT-IN (default OFF) — requires an explicit project/user directive. Use when explicitly auditing recent work for harness gaps.

Analyze a natural language idea against the project codebase and return structured issue specs

AI design language for production-grade UI — 10 commands covering typography, color, motion, layout, and UX writing quality

다중 세션 transcript에서 반복 실패 패턴(instinct)을 자동 채굴하여 신규 skill candidate 생성

Automatically detect user intent and route to appropriate agent

Modern Java 25 LTS patterns from Virtual Threads, Pattern Matching, Records, and Sealed Classes

Apache Kafka 4.2 best practices for event streaming, topic design, and producer-consumer patterns

Idiomatic Kotlin patterns from JetBrains conventions

Show all available commands